On May 22, at the age of 100 1/2, my grandmother Flora passed away. This post is transcript of the eulogy that I gave at her memorial service. My previous post about my grandfather is here.

It is hard to speak about my grandmother without also speaking about my grandfather. They were such different people, and yet their lives were so deeply woven together that it feels somehow complete that they are together again now.

But I will try.

When someone lives to be 100, you learn very quickly that they did not get there by accident. In my grandmother Flora’s case, I think part of the secret was that she wasted absolutely nothing.

Not food. Not money. Not paper. Not a single rubber band.

When I was little, I would come over to her house and there was a drawer that seemed magical to me. It had two things in it: piles of S&H Green Stamps and countless rubber bands from the newspapers. I would lick the stamps and put them carefully into booklets. A full booklet of 1,200 stamps was worth $1.20 in cash, or $2 off household items, and Grandma Flora made sure we understood that those stamps were worth saving.

And the rubber bands? I turned those into rubber band balls.

Looking back, I realize she was teaching me something. Flora was a child of the Depression, and frugality was not just a habit for her. It was a way of respecting what you had, taking nothing for granted, and understanding that small things, saved and cared for, could add up to something meaningful.

That lesson stayed with me.

Years later, when I was in college, I had jobs and internships, and after my first high-paying internship at Hewlett-Packard. It paid $2,235 a month, which felt like a fortune at the time, and Grandma Flora taught me about saving and investing. She taught me about CDs and mutual funds, and I remember driving down to the Fidelity office in Palo Alto to open my first account in person, because the web wasn’t really a thing yet.

She understood money in a deeply practical way. She did her taxes by hand, in pencil. She believed in being careful, being prepared, and learning how things worked. And for me, those conversations were not just about finances. They were about responsibility, independence, and building a future one careful decision at a time.

This year marks my 10th year teaching Personal Finance at Stanford, and thousands of students have now heard me explain the Rule of 72, a simple way to figure out how long it takes an investment (or a debt) to double in size. They all hear that it’s a lesson I learned from my grandmother.

But when I think about Grandma Flora, I always think about her together with my grandfather. They were very different people, and yet they were always somehow in sync. There was something special about their relationship. It created a home that became a center for our family.

Their house was where we gathered for birthdays, holidays, celebrations, and even weddings. It was not just a house. It was a place where family gathered.

That is something Carolyn and I still aspire to today: to build a home that is not only where we live, but where the people we love feel welcomed, rooted, and connected.

A meaningful life is built the same way those stamp books were filled — one small act at a time. One stamp, one meal, one lesson, one holiday, one conversation, one kindness, one careful choice.

And in the end, if we are lucky, those small things become a legacy.

Grandma Flora’s legacy is all around us. It is in the family she helped build, the home she helped create, the lessons she passed down, and the love that continues in each of us.

May her memory be a blessing.

Note: On September 16, 2022, I wrote a post about Figma after the announcement of a $20B acquisition offer from Adobe. As it turns out, that acquisition didn’t happen, but this story deserves to live. So this post has been updated to reflect the journey to the Figma IPO (Ticker: FIG) on July 31, 2025.

On June 25, 2013, Dylan Field, one of my favorite interns from LinkedIn dropped by Wealthfront headquarters in Palo Alto to catch up and get some advice about his new startup, Figma.

At the time, I was up to ears with work as the new CEO, trying to sell the crazy idea that someday millions of people would let computers, rather than humans, manage their money.

But I always take time for people, particularly students just coming out of college and embarking on a career in Silicon Valley. So I met with Dylan for an hour, and we walked around the City Center in Palo Alto talking about his new company. The next day, I sent him a note asking if there was any more room in his seed round, offering to help him with product, growth, and recruiting.

Today, that company (Figma) went public in one of the largest IPOs in Silicon Valley history.

From Intern to Founder

In 2010, Dylan was an intern at LinkedIn, on the data science team overseen by my friend DJ Patil. However, search & data science were closely intertwined at LinkedIn, and since search was an area that I was responsible for, I spent a lot of time with team brainstorming new ideas and working through product problems. For some reason, I distinctly remember that Dylan was the first intern to ever make me feel old, based on one offhand comment about how he was too young to see the Star Wars prequels when they came out.

Regardless, Dylan was brilliant and delight to talk to about almost any topic, and we kept in touch loosely through social media when he went back to school. He ended up interning at Flipboard, a company that happened to be founded by an engineer from Apple who co-taught CS 196P at Stanford with me, their first class on iPhone development. Dylan stayed close to the data science team at LinkedIn, and so we ended up with more than a few reasons to stay connected. I had left LinkedIn to take an EIR role at Greylock, so was just starting to become an active angel investor.

All of this led to that one walk around Palo Alto.

The Figma Pitch

There was no deck involved, and the meeting was not about fund raising. As it turned out, Dylan had already largely raised his seed round. In fact, a TechCrunch article came out about it that day. Going into the meeting, I had absolutely no idea what Dylan was working on, and knowing Dylan, it literally could have been anything and it wouldn’t have surprised me.

Instead, Dylan & I talked about the transition from Desktop to Web 2.0, and whether now was the right time to bring graphic design to the cloud. John Lilly & I had discussed a hypothesis about this while I was at Greylock, and it was one where I had come to have conviction. The basic premise was that the combination of Web 2.0, Social, and Mobile had finally created the possibility of building truly useful and user-friendly collaborative software in the cloud that was an order of magnitude better than desktop software and would finally drive the migration of professionals to web applications. More importantly, we believed that the history of desktop software contained clues to which types of software would be converted first: productivity applications (late 70s/early 80s), then enterprise applications, graphic design & desktop publishing, and finally personal finance. In fact, this theory is part of the reason I spent 2012 exploring the idea of bringing financial software to the cloud, eventually leading me to the sector now called “fintech” and my role at Wealthfront.

As we talked about this theory, Dylan then shared with me one of those simple insights that seems so obvious in hindsight, but was anything but obvious at the time. He told me that with WebGL in the browser, he thought now was the time to move graphic design to the cloud. As someone who had spent significant time in grad school on computer graphics, my initial reaction was very negative. In my mind, graphic design was incredibly compute intensive, to the point where professionals used highly optimized $10K workstations, multiple GPUs, and optimized data storage to get the local performance they desired.

Dylan was not deterred. He explained that the heavy compute was the exact reason why moving to the cloud made sense. By providing high powered machines in the cloud, anyone could get access to an almost arbitrary amount of power without spending $10K, and latency & bandwidth had progressed to the point where shipping the UI bits to the client was a solved problem.

He was right.

It was a simple moment, but I had to admit that multiplayer gaming had already solved problems of low latency, collaborative UI, and that it might be possible to extend that to the web now. Graphic design wasn’t just going to move to the web – eventually it was going to be better, faster, and cheaper online. On top of that, collaboration would be the killer feature that desktop couldn’t match.

The initial product idea, a photo editor in the cloud, turned out to not be the right way to ride this wave. But in the end, Dylan & team were intelligent and flexible enough to clearly iterate to a product that not only is riding that wave, but is also defining it.

Silicon Valley is about People

When I graduated from business school, my first job was as an Associate at a venture capital firm in Menlo Park. 2001 was a rough time to start in venture capital, but I was excited because I loved the idea of investing capital with founders when everyone else had pulled back. Our office, however, was too large, built out for a boom that had been cut short in 2000. As a result, they gave me a choice of offices.

I picked the one no one wanted, adjacent to the reception area. People thought it was too noisy, but I always left the door open. The reason was quite simple: when founders came in, I wanted to overhear how they treated our receptionist. You can learn a lot about a person based on how they treat people with less power when no one else is around.

Success in Silicon Valley is a dizzying combination of skill and luck, execution, and timing. But first and foremost, it is about people. One of the reasons that the most successful software cultures struggle to avoid hierarchy, is that the rapid change in platform capabilities means that the half-life of experience is brutal. The best solution for a problem five years ago may not be the the best solution today, and it very likely won’t be the best solution five years from now. As a result, young engineers approaching problems for the first time can sometimes see opportunities that the most experienced can’t. Other times, a “new” problem can actually just be a rehash of a problem that was common decades ago. The key is always to work the problem, and always work to avoid the destructive HiPPO anti-pattern. (HiPPO = the highest paid person’s opinion)

These days, online discussion is filled with debates about impressing your boss, impressing your CEO, impressing the company. To me, this misses the real opportunity. For most people, their best opportunities are likely ahead of them, and the connection to that opportunity will mostly come from a co-worker, a “weak connection,” and likely someone who isn’t above you in power and hierarchy.

Dylan was an intern, and not even an intern on my team. There was no obvious reason for me to spend time with him, other than that he is an amazing human being. Very intelligent, and also very kind. A long term, first principles thinker, but also someone who gets his hands dirty building. Ambitious, not to be a billionaire, but ambitious to make a difference and have an impact.

As an angel investor, I tend to look for a strong, authentic connection between a founder and the product they are building. For me to invest, I have to believe the founder is not only tackling a problem big enough to generate venture returns, but also is someone who is intelligent, trustworthy, and ambitious.

Dylan might have been an intern, but even as a teenager, he was all three.

A True Silicon Valley Story

Our careers are built based on the overlay of networks that we build. Every school, every job, every company is an opportunity to connect with people. It will only be obvious with hindsight which connections will generate the most value in your career, but try to remember that everyone may have something you can learn from.

There were quite a few executives at LinkedIn, and more than a few interns. There was no way to predict this type of outcome. Twelve years ago, I became an investor in Figma, and five years ago Dylan became an investor in my new startup, Daffy. Last year, as a credit to the culture that Dylan built at Figma, they became the first company to launch our innovative new program to allow any employee to donate private stock to charity.

Roles change fairly quickly, but relationships with good people last decades.

This milestone is just one more step in the fulfillment of a broad vision to elevate design in every organization. With the ongoing wave of rapid innovation in AI, it seems likely that in the near future more and more applications will be built by designers using Figma.

Congratulations to Dylan, Evan, and the whole Figma team.

It’s a true Silicon Valley story, and one we should all be rooting for.

Living a healthy financial life is far more difficult than most people believe. For most of us, our education in personal finance is relatively limited. We learn some from our parents and our friends, but for the most part, we are left to educate ourselves. This is not primarily an issue of intelligence, ambition, or capability. You can have an IQ over 140 and multiple degrees from incredible institutions and still not really understand the difference between a bank account and a brokerage account, what actions lead to a good credit score, or how to think about decisions like whether to rent or buy a house. 

This is one of the reasons why for the past six years I have invested the time and effort to create and teach a new course at Stanford University class, “Personal Finance for Engineers.” And after teaching the class to more than 1,000 students, it has given me quite a bit of perspective on how different people approach financial issues in their lives.

But as difficult as personal finance is for individuals, it is far simpler than the reality that most people face. 

Couples Are Not An Edge Case

The reason is simple: most of us are not alone. It turns out that ~62% of Americans between the ages of 25-54 are either married or cohabitating with a partner.

Financial planning is fundamentally different for couples. When my wife and I were married over 20 years ago, we received lots of marital advice, but very little guidance on how to merge our finances and plan our financial lives together. Over the past two decades, we have now seen a plethora of software applications and services developed to help people with a broad range of financial problems, and yet almost all of them are still designed primarily for individuals, not couples.

The financial lives of couples are becoming more complicated than ever. 80% of couples are now dual-career and dual-income. Making all of your accounts “joint” is no longer an effective solution, in fact, the most common way dual-income couples manage money is a through a “yours/mine/ours” method. 

Traditional financial advice has always been focused on families. Most financial planners insist on working with both partners in a relationship for the simple reason that their financial lives are intertwined. Their financial goals are planned together and both partners are required to make any financial plan successful. 

It’s not an accident that the highest tier of financial advisory firms refer to themselves as family offices.

Unfortunately, if you don’t have a liquid net worth of at least $1 million, it can be difficult or impossible to get a high quality financial advisor, and most couples do not have anywhere close to that amount when they are just starting their lives together.

This is why I am so excited to see Plenty launch today.

Plenty is building a home where families collaboratively manage their financial lives, beginning with the couple

The Next Wave of Fintech

The way forward will not be based on cloning the strategies that worked in the previous wave of fintech, but we can learn a lot from past technology transitions to see where fintech is headed. In particular, there are a lot of common attributes between how we navigated the transition between Web 1.0 and Web 2.0 after the internet bubble burst in 2000.

Three key trends will define the next wave of breakthrough products:

• Single Player → Multiplayer
• Millennial focus → Multigenerational
• Replicated products → Novel products & services

At Daffy, we have built our platform around these three ideas. Last fall, we became the first major donor-advised fund to offer native support for families (up to 24 people!)

With the launch of Plenty today, we will now see what a modern platform for financial planning could look like when it is designed to be multiplayer from day one. 

Congrats to team at Plenty on their launch, and proud to be an early investor.

This blog post was also published on Daffy.org

Steve Jobs famously talked about connecting the dots of your life in his now well-known commencement speech in 2005. There’s something incredibly insightful and at the same time humbling about that framing as a founder when you look at the differences between the product you set out to build, and where the journey takes you once you launch.

Daffy was based on a number of fairly simple, but powerful, inspirations:

• The idea that we teach our children to put money aside for charity, but that as adults we rarely follow that lesson.
• The idea that donor-advised funds are a great financial product, but are largely unknown to most people because the incumbents cater almost exclusively to the wealthy.
• The idea that the same behavioral finance insights that led us to build better systems to help people to save and invest could also be used to help people give.
• The idea that a simple app, like Acorns, could over ten years help a customer base of almost five million paying users with their financial health.

When Alejandro & I raised our $4.8M seed round in 2020 to help build what is now known as Daffy, the Donor-Advised Fund for You, it was very much based on the idea that we would build the Acorns for Charity. That’s what we pitched.

A little over one year ago, on September 30, 2021, we launched the service. Launching a new product is always both a triumphant and humbling process. It’s so powerful to see people using and enjoying something new that you and your team brought into the world. At the same time, the initial launch is almost always the beginning of the learning process, because real customers have a way of showing you the truth about where they see value in your creation.

So, not surprisingly, it quickly became obvious that we had missed something fundamental in our initial concept of the product.

Giving is not like saving on one very important dimension. Unlike saving, giving is fundamentally better with other people. We discover new causes and charities through other people. We are inspired to give by other people. Most importantly, we support the causes and charities we care deeply about with other people.

The more we learn from our members, the more we’ve come to realize that Daffy is meant to be more than just the best donor-advised fund on the market.

We set out to build the Acorns of Charity, but the future of Daffy may look much more like LinkedIn.

Giving is Better Together

The best software product clues tend to come from the organic actions of customers, and this has definitely been true with Daffy. In this case, our first clue came from people sharing their inspiration around giving with others. 

Every DAF allows their members to include a note to the charity with their donation, and when we designed Daffy, we included this feature. However, with every Daffy donation, the member is given the option to add a public note about why they give. For an optional feature, we weren’t expecting heavy adoption, but in our first year, over 36% of our donations had a public note.

These notes are not like typical internet posts. In many cases, they reflect emotional and deeply personal motivations for supporting causes and organizations.

It might be hard to believe, but in the early days of LinkedIn, there was a lot of public debate about what identity online would look like. Would people have a single profile that represented them on the web, or would we have multiple, reflecting the different slices of our lives? Mark Zuckerberg argued for the former, while Reid Hoffman argued for the latter.

What we believe we have discovered at Daffy is that there is another identity that is meaningful to people, and yet does not seem to have a home online: our charitable identity.

Our Charitable Identity

Even at LinkedIn, it was clear that there were going to be more than just social and professional profiles. Our identities and relationships are often compartmentalized based on context: think about what you ask someone you just meet at a party vs. a conference vs. a school event. At a little league game, I’m not even sure that I have a name — I’m just Julia’s Dad! These identities flourish and wane over the course of our lives, sometimes merging, sometimes fading.

Over the past few decades, it has become clear that there is a resurgence in how people think about themselves philanthropically. The causes you believe in, the organizations you support, the people you work with to make a difference — all of these matter increasingly to people. Perhaps it is a reflection of the times we live in, or perhaps it is an aspect of maturing generations. Whatever the cause, however, it is clear that people are eager to share this part of themselves with friends and colleagues, and also seek this information about others. We are proud of the roles and responsibilities we take on with charitable organizations and the people who work for these organizations.

Discovery. Inspiration. Support.

These seem to be some of the major emotional drivers behind the activity we see from our early Daffy members, and yet this seems to get lost on existing platforms. It’s so hard to compete with dating, news, shopping, and careers.

Fulfilling Our Series A Vision

2022 has not been a kind year for technology companies in general and has definitely been a tough fundraising environment for venture-backed startups. However, when Alejandro & I realized what we needed to do, we also knew we needed to raise our Series A sooner rather than later.

We know that building out this platform will take years, and we are grateful to Ribbit Capital and XYZ Ventures for supporting this vision, and we are especially grateful to the dozens of leaders and luminaries who have individually invested in our efforts.

Today, on Giving Tuesday, we are starting to roll out our first features that will help bring this vision to life. A place where people can not only share the causes and charities they personally support, but also spotlight a charity they are working to support right now. A way to learn who our friends and colleagues give to, and the opportunity to be inspired by their generosity and support their efforts. 

All of these features are layered over our ground-breaking, modern donor-advised fund platform, built from the ground up to help people be more generous by setting their own personal giving goals and then helping them achieve them.

All throughout November, our #BeMoreGenerous campaign gathered 30 notable leaders including Reid Hoffman (co-founder of LinkedIn), Charles Best (Founder of DonorsChoose), and Amy Chang (Board of Directors at the Walt Disney Co.) to use our new “Charity Spotlight” feature to share the charities they support this holiday season — and inspire others to give.

As of today, that feature is now available to every Daffy member.

Together, we believe that we can increase giving by over $1.2 Trillion dollars over the next decade in the United States alone, with an even larger opportunity globally.

If you are one of the 60-70 million households in the United States who give to charity every year, go to daffy.org now and set up an account. It’s completely free for members just starting out with a balance of under $100.

Connect with your trusted friends and colleagues. Share the causes and organizations you believe in. Inspire others to give, and more importantly, connect more people to organizations that desperately need more support. Include your family, and foster real discussions about the causes and organizations you support.

Daffy launched just a little over a year ago, and we are grateful to the thousands of people who have already signed up for the service. But our aspirations are audacious.

Our vision is a world where everyone puts something aside regularly for those less fortunate than themselves. A community of millions, not thousands.

Come join us.

One of the reasons that I am so passionate about entrepreneurship is because of my belief that companies can be highly effective agents of change.

This isn’t just a feature of technology companies built in Silicon Valley. Vanguard is an inspiring example, headquartered in Malvern, PA. They are immensely successful — now responsible for over $8 trillion in assets, and yet their impact is far broader than assets alone might suggest. Vanguard makes just a fraction of the revenue ($6.9B) of Fidelity Investments ($24B), but this is because Vanguard focuses more on making money for their customers rather than themselves. And while Vanguard has millions of happy customers, there are tens of millions of investors who are not customers of Vanguard who pay lower fees and have more money in retirement because Vanguard exists. They have forced an entire industry to offer higher quality financial products at lower prices.

Two years ago, Alejandro & I set out to build a category-defining company in a space that has been ignored for far too long. Each step of the way, I shared pieces of our story:

• My original intention to start a company
• Our initial seed round funding
• Our audacious goal to help unlock an additional $1.2 trillion for charity
• The future of fintech (2025)

Today’s release of Daffy for Families is a major milestone in our journey to fulfill that vision.

The Next Generation of Fintech

2022 has been a very difficult year for the economy, and it has been particularly hard on the venture-based startup ecosystem. We feel very fortunate to have raised our $17.1M Series A in February, giving us ample time to invest in our platform.

The way forward will not be based on cloning the strategies that worked in the previous wave of fintech, but we can learn a lot from past technology transitions to see where fintech is headed. In particular, there are a lot of common attributes between how we navigated the transition between Web 1.0 and Web 2.0 after the internet bubble burst in 2000.

Three key trends will define the next wave of breakthrough products:

1. Single Player → Multiplayer
2. Millennial focus → Multigenerational
3. Replicated products → Novel products & services

Daffy for Families is the first feature that we’ve shipped that illustrates all three.

Giving Together is Better Than Giving Alone

Unlike most financial products and services, giving is fundamentally better when done with others. We learn from each other, we challenge each other, and we inspire each other.

But why does every donor-advised fund have to look like a retirement account?

Why can’t grandparents engage with their children and grandchildren around the causes and organizations they support? Why can’t children learn from their parents about how and why they give?

Alejandro & I are both parents, and as a parent, you learn a few hard-earned lessons. One of those lessons is the simple fact that actions speak louder than words. It’s one thing to tell your children that reading is important, but it’s a very different thing for your children to see you read.

The move from Web 1.0 to Web 2.0 was based on fundamental insights like these, and it’s the reason why LinkedIn does not look like Monster.com.

Over the past decade, I have been floored by how many intelligent and passionate people work to support charitable organizations, and yet it has become increasingly clear that they are frustrated. Frustrated by the slow pace of technology. Frustrated by the inability to help people give. Frustrated by an industry driven by a business model that focuses too much on dollars and not enough on people.

They are looking for something new — an agent of change, a new platform, a new model that can unlock the way people connect with the causes and organizations they support.

We think Daffy could be that platform.

Leadership Through Product

With Daffy for Families, we are asking the industry a simple question: Why don’t you let families give together?

Almost every major consumer platform has family sharing, and yet Fidelity, Schwab, and yes, even Vanguard haven’t invested in this basic capability.

Why?

My best guess is that their business model, which is based on charging a fee based on a percentage of assets, makes features like this look expensive. After all, having more people on a fund to help inspire each other to give will likely lead to more money going to charity and less money sitting in funds earning fee revenue.

Daffy was built to be different. We have a simple mission: help people be more generous, more often. We are also quite proud to have a business model that rewards having more people involved with giving rather than more dollars sitting in accounts.

It has been just one year since we launched Daffy, and yet already we are already shipping features that may take the industry years to copy.

We can’t do it alone. Every member who joins our platform helps force the industry to change. Together, we believe that we can unlock the generosity of millions, and in the process, free up trillions of dollars for worthy causes and organizations.

Check out Daffy for Families. Set up a fund. Invite your loved ones.

Join us.

On June 25, 2013, Dylan Field, one of my favorite interns from LinkedIn dropped by Wealthfront headquarters in Palo Alto to catch up and get some advice about his new startup, Figma.

At the time, I was up to ears with work as the new CEO, trying to sell the crazy idea that someday millions of people would let computers, rather than humans, manage their money.

But I always take time for people, particularly students just coming out of college and embarking on a career in Silicon Valley. So I met with Dylan for an hour, and we walked around the City Center in Palo Alto talking about his new company. The next day, I sent him a note asking if there was any more room in his seed round, offering to help him with product, growth, and recruiting.

Yesterday, that company (Figma) was acquired by Adobe for $20 Billion.

From Intern to Founder

In 2010, Dylan was an intern at LinkedIn, on the data science team overseen by my friend DJ Patil. However, search & data science were closely intertwined at LinkedIn, and since search was an area that I was responsible for, I spent a lot of time with team brainstorming new ideas and working through product problems. For some reason, I distinctly remember that Dylan was the first intern to ever make me feel old, based on one offhand comment about how he was too young to see the Star Wars prequels when they came out.

Regardless, Dylan was brilliant and delight to talk to about almost any topic, and we kept in touch loosely through social media when he went back to school. He ended up interning at Flipboard, a company that happened to be founded by an engineer from Apple who co-taught CS 196P at Stanford with me, their first class on iPhone development. Dylan stayed close to the data science team at LinkedIn, and so we ended up with more than a few reasons to stay connected. I had left LinkedIn to take an EIR role at Greylock, so was just starting to become an active angel investor.

All of this led to that one walk around Palo Alto.

The Figma Pitch

There was no deck involved, and the meeting was not about fund raising. As it turned out, Dylan had already largely raised his seed round. In fact, a TechCrunch article came out about it that day. Going into the meeting, I had absolutely no idea what Dylan was working on, and knowing Dylan, it literally could have been anything and it wouldn’t have surprised me.

Instead, Dylan & I talked about the transition from Desktop to Web 2.0, and whether now was the right time to bring graphic design to the cloud. John Lilly & I had discussed a hypothesis about this while I was at Greylock, and it was one where I had come to have conviction. The basic premise was that the combination of Web 2.0, Social, and Mobile had finally created the possibility of building truly useful and user-friendly collaborative software in the cloud that was an order of magnitude better than desktop software and would finally drive the migration of professionals to web applications. More importantly, we believed that the history of desktop software contained clues to which types of software would be converted first: productivity applications (late 70s/early 80s), then enterprise applications, graphic design & desktop publishing, and finally personal finance. In fact, this theory is part of the reason I spent 2012 exploring the idea of bringing financial software to the cloud, eventually leading me to the sector now called “fintech” and my role at Wealthfront.

As we talked about this theory, Dylan then shared with me one of those simple insights that seems so obvious in hindsight, but was anything but obvious at the time. He told me that with WebGL in the browser, he thought now was the time to move graphic design to the cloud. As someone who had spent significant time in grad school on computer graphics, my initial reaction was very negative. In my mind, graphic design was incredibly compute intensive, to the point where professionals used highly optimized $10K workstations, multiple GPUs, and optimized data storage to get the local performance they desired.

Dylan was not deterred. He explained that the heavy compute was the exact reason why moving to the cloud made sense. By providing high powered machines in the cloud, anyone could get access to an almost arbitrary amount of power without spending $10K, and latency & bandwidth had progressed to the point where shipping the UI bits to the client was a solved problem.

He was right.

It was a simple moment, but I had to admit that multiplayer gaming had already solved problems of low latency, collaborative UI, and that it might be possible to extend that to the web now. Graphic design wasn’t just going to move to the web – eventually it was going to be better, faster, and cheaper online. On top of that, collaboration would be the killer feature that desktop couldn’t match.

The initial product idea, a photo editor in the cloud, turned out to not be the right way to ride this wave. But in the end, Dylan & team were intelligent and flexible enough to clearly iterate to a product that not only is riding that wave, but is also defining it.

Silicon Valley is about People

When I graduated from business school, my first job was as an Associate at a venture capital firm in Menlo Park. 2001 was a rough time to start in venture capital, but I was excited because I loved the idea of investing capital with founders when everyone else had pulled back. Our office, however, was too large, built out for a boom that had been cut short in 2000. As a result, they gave me a choice of offices.

I picked the one no one wanted, adjacent to the reception area. People thought it was too noisy, but I always left the door open. The reason was quite simple: when founders came in, I wanted to overhear how they treated our receptionist. You can learn a lot about a person based on how they treat people with less power when no one else is around.

Success in Silicon Valley is a dizzying combination of skill and luck, execution, and timing. But first and foremost, it is about people. One of the reasons that the most successful software cultures struggle to avoid hierarchy, is that the rapid change in platform capabilities means that the half-life of experience is brutal. The best solution for a problem five years ago may not be the the best solution today, and it very likely won’t be the best solution five years from now. As a result, young engineers approaching problems for the first time can sometimes see opportunities that the most experienced can’t. Other times, a “new” problem can actually just be a rehash of a problem that was common decades ago. The key is always to work the problem, and always work to avoid the destructive HiPPO anti-pattern. (HiPPO = the highest paid person’s opinion)

These days, online discussion is filled with debates about impressing your boss, impressing your CEO, impressing the company. To me, this misses the real opportunity. For most people, their best opportunities are likely ahead of them, and the connection to that opportunity will mostly come from a co-worker, a “weak connection,” and likely someone who isn’t above you in power and hierarchy.

Dylan was an intern, and not even an intern on my team. There was no obvious reason for me to spend time with him, other than that he is an amazing human being. Very intelligent, and also very kind. A long term, first principles thinker, but also someone who gets his hands dirty building. Ambitious, not to be a billionaire, but ambitious to make a difference and have an impact.

As an angel investor, I tend to look for a strong, authentic connection between a founder and the product they are building. For me to invest, I have to believe the founder is not only tackling a problem big enough to generate venture returns, but also is someone who is intelligent, trustworthy, and ambitious.

Dylan might have been an intern, but even as a teenager, he was all three.

A True Silicon Valley Story

Our careers are built based on the overlay of networks that we build. Every school, every job, every company is an opportunity to connect with people. It will only be obvious with hindsight which connections will generate the most value in your career, but try to remember that everyone may have something you can learn from.

There were quite a few executives at LinkedIn, and more than a few interns. There was no way to predict this type of outcome. Nine years ago, I became an investor in Figma, and two years ago Dylan became an investor in my new startup, Daffy. Roles change fairly quickly, but relationships with good people last decades.

Congratulations to Dylan, Evan, and the whole Figma team. This acquisition is just one more step in the fulfillment of a broad vision to elevate design in every organization.

It’s a true Silicon Valley story, and one we should all be rooting for.

Like many people, for most of my career, I never set an explicit goal for giving to charity. While I was raised to believe that everyone should put something aside for those less fortunate than themselves, in practice, I mostly gave only when I was asked. Sometimes it was a friend running a marathon for a worthy cause they had a deep connection to. Other times it was a fundraiser for one of the schools that my children attended. But overall, it was reactive, not proactive.

This all changed for me in 2011.

I first learned about donor-advised funds when LinkedIn went public in 2011. All of a sudden, private wealth managers became ubiquitous on campus. Part their sales process, as it turns out, was to promote the tax-deductible benefits of giving to charity through donor-advised funds.

The concept of a donor-advised fund appealed to me, but it raised an important question: how much should you contribute to a donor-advised fund? I had no idea.

Fortunately, at the time, my accountant recommended a fairly simple approach: take whatever amount you plan to give to charity every year, multiply it by ten, and contribute that to a donor-advised fund. The best part? By investing the money upfront in a donor-advised fund, I could potentially fund years eleven or twelve with the proceeds.

For the first time, I was forced to answer what should have been a very simple question: how much did I want to give to charity every year?

At the time, I chose $20,000, which was 10% of my base salary at LinkedIn.

More importantly, I now had a giving goal. And it changed everything about the way I give.

The Two Hard Problems With Giving

It turns out that there are two hard problems inherent in giving money to charity:

1. How much can you afford to give?
2. Who should you give the money to?

Until I had a donor-advised fund, I never realized how much the first problem influenced my generosity. But every time I was asked for a donation, there was friction as I tried to figure out what I could afford. However, once I had a giving goal, the first problem largely went away. As a result, I found it easier to give when I found an organization or cause that I believed in.

More importantly, the goal made me more generous. While the donor-advised fund did not change the amount that I thought I should give to charity, it did change the amount that I actually gave to charity. Looking back at my records before 2011, it is clear that having a goal increased my actual giving by more than 100%.

This shouldn’t be surprising. Behavioral economists have known for a long time that pre-commitment can dramatically increase the amount that people save for retirement. Why couldn’t it also work for giving?

This is the reason Alejandro & I started Daffy.

Set Your Giving Goal Today

Our research shows that when asked, most people intend to give a larger amount to charity than they actually end up giving in practice. At Daffy, we call this difference the Generosity Gap. It may sound like a small thing, but we believe that if everyone set a giving goal, it could increase the money given to charity by more than one trillion dollars over the next ten years.

Every year, we set goals for ourselves. Financial goals. Fitness goals. Diet goals.

Until 2011, I didn’t know what a donor-advised fund was, and I didn’t have a giving goal. But in 2022, you can sign up for Daffy in minutes, set a giving goal for the year, and have an app at your fingertips anytime you find the desire to give.

This year, consider setting a goal for your giving and be the generous person that you want to be.

Join us.

In 2020, I set off to build a new company. At the time, I never would have imagined that we’d end up building one during the largest pandemic in a century.

Lao Tzu said that a journey of a thousand miles begins with a single step, and I count myself fortunate to have made the best first step possible in finding a truly world-class co-founder. Alejandro is one of those rare talents that makes Silicon Valley special, a true builder and an inspiration. Together we set off on a journey to turn an audacious mission and vision into a reality.

We have been very fortunate. Despite building this company during the COVID-19 pandemic, we have been joined by an incredibly talented team. Each member of our founding team has taken a leap of faith that together we’ll be able to build something out of nothing. So many investors have also been willing to take that leap with us and fund our early efforts.

Today is the day. Not an ending, but a beginning. We’re coming out of stealth, and we’re ready to start building in public. It’s hard to explain how exciting and terrifying this moment is.

Introducing Daffy

Daffy is a community and platform built around people willing to make a simple commitment to regularly put money aside for those less fortunate than themselves. At its heart beats a fintech core: a new modern donor-advised fund built from the ground up for this purpose.

Daffy is the Donor Advised Fund for You.

Unlike most financial products, giving is inherently social, and we see immense opportunity to bring people together around the causes and organizations that they support.

You can read more about Daffy here, learn more about our team here, and get a quick walkthrough of the product here.

Who Taught You To Be Good?

Alejandro & I are big believers in talking to customers, and so we spent a lot of time talking to people about how they think about giving to charity. Through the course of that research, we came to two important insights:

1. Moral Compass. Almost everyone has a person in their life — a parent, a relative, a teacher, a priest — who instilled in them a strong sense of what it means to be a good person. Some people even say that they can still hear that person’s voice when they decide to do the right thing. Invariably, that person taught them the importance of giving to those less fortunate than themselves.
   
2. Guilt. Almost everyone has an idea of what they believe they should be giving to charity every year. Interestingly, there is very little agreement on what that amount is, but for almost every person we spoke to, there is a number. Unfortunately, very few people live up to that ideal. Our lives are too busy, and giving often falls off people’s immediate to-do lists. The can gets kicked down the road. As a result, people are not able to be the type of person they want to be. The person that their moral compass would be proud of.

Technology Can Help

We believe that technology has a role to play in solving this problem. Why can’t we use the same techniques that we have used to help people shop and save to help people give?

By automating giving, we believe that technology can help people be more generous, more often. We can help people be the good people that they want to be.

In some ways, it is not surprising that a company born during the pandemic would focus its efforts on one of the biggest problems caused by the pandemic. There are millions of people struggling, and we believe that there are millions of people who want to do something to help. We believe that there are millions of people who want to take action, who want to support the causes and organizations that will help build a better world.

We believe that there are millions of people who are willing to make a commitment to give.

Come join us.

A little less than four years ago, I wrote a post about home prices in Silicon Valley and how they relate to stock prices and Bitcoin. It was one of the most popular posts on my blog from 2017.

The original compared housing prices in Palo Alto to a few of the largest technology companies in Silicon Valley, with Bitcoin added just for fun. Given the incredible rise in technology stock prices and Bitcoin in the past few years, it seemed worthwhile to update the data in the original post.

Talking about home prices in Silicon Valley is always a sensitive topic, because the lack of affordable housing continues to be a both difficult and heavily political topic. As someone who grew up here, it seems painfully obvious that the primary problem is the overwhelming resistance of local city councils to approve housing unit construction that meets ever increasing demand.

This post isn’t about that issue.

Instead, this is an attempt to look at the housing market through another lens. Most financial estimates of housing cost tend to compare the price of housing to incomes, which makes sense since for most people in most places, the affordability of a home is directly related to the size of the mortgage that they can obtain for that home. In general, houses are purchased based on income, not assets.

In Silicon Valley, of course, income looks a bit different since many people in Silicon Valley work for technology companies, and most technology companies compensate their employees with equity.

Palo Alto Home Prices

I chose Palo Alto as a proxy for Silicon Valley home prices because it is historically “ground zero” for Silicon Valley tech companies, and it has relatively close proximity to all of the massive tech giants (Apple, Google, Facebook).

The original post started the data sets in June 2012, since this was roughly when Facebook became a public company. For this post, I’ve extended the data sets all the way to March 2021.

All housing prices have been sourced from Zillow. All stock prices have been sourced from Yahoo Finance, and reflect the price adjusted for dividends. All Bitcoin prices have been sourced from Investing.com.

This is what Zillow looks like today for Palo Alto:

As you can see, in June 2012, the average Palo Alto home cost $1.44M. Roughly five years later, in June 2017, that average price was up 84.6% to $2.55M. Now, in March 2021, that price has risen a total of 117.9% to $3.15M.

That’s certainly a much faster increase than any normal measure of inflation, whether looking at changes in prices or wages. But what happens if we look at those increases in comparison to the stocks of some of the largest technology employers in Silicon Valley?

Apple ($AAPL)

Apple is the most valuable public company in the world right now, measured by market capitalization ($2.023 Trillion as of March 18, 2021), and second most profitable ($55.256B in 2020). Thanks to their exceptional financial performance, Apple stock ($AAPL) has increased significantly since June 2012, rising (split-adjusted) from $18.79 per share to $124.76 in March 2021. That’s a gain of over 565.8%.

Wow.

Let’s look at Palo Alto home prices as measured in dollars, and then let’s look at them in comparison priced in shares of $AAPL.

This chart tells a very different story than the one from 2017.

In the five years from June 2012 to June 2017, Apple stock was volatile, but over the entire time period almost exactly matched the growth in Palo Alto home prices. However, the run up since 2017 has been incredible.

Split-adjusted, it took 76,839 shares of $AAPL to purchase the average home in Palo Alto. By March of 2021, that number had dropped to only 25,216 shares.

This isn’t surprising, since Palo Alto home prices are only up 117.9% over that time period, and Apple shares are up 564%. But what this means from a practical viewpoint is that for people converting one asset (Apple stock) into another (Palo Alto housing), it has become easier, not harder, to purchase the average home.

Google ($GOOGL)

Google tells a similar story to Apple in 2021, even though that wasn’t the case in the original post. Since 2017, Apple stock has clearly outperformed Google, leaving them with almost identical price increases from June 2012. (By itself, that’s somewhat of an amazing fact given the relative ages of the two companies).

As of March 2021, Google has a market capitalization of $1.37 Trillion, significant less than Apple’s. However, they have seen price appreciation of 557.3% since June 2012, rising from a split-adjusted $316.80 per share to an amazing $2,082.22 per share in March 2021.

Let’s look at Palo Alto home prices as measured in dollars, and then let’s look at them in comparison priced in shares of $GOOGL.

If you compare this chart to the one for Apple, it tells a different story but has a similar ending. Google shares are clearly more volatile than Palo Alto housing, but they have fairly consistently appreciated over the past decade.

In June of 2012, it would have taken 4,557 shares of Google stock to purchase the average home in Palo Alto. By March 2021, that number had dropped to only 1,511 shares.

So while Palo Alto home price appreciation has been tremendous by any historical measure, Palo Alto housing has become cheaper in the past decade for people holding Google stock, and more expensive for people holding dollars.

Facebook ($FB)

Facebook, the youngest of the massive tech giants, already has one of the largest market capitalizations in the world. As of today, Facebook is valued at $793.4 Billion. Facebook stock has risen an incredible 1208.2% since June of 2012, from a price of $21.71 per share to a price of $284.01 in March 2021.

At this point, you know how this story goes. With growth of over 1200%, Facebook stock goes a lot further in 2021 than it did in 2012, even against daunting Palo Alto housing prices.

In June of 2012, it would have taken 66,500 share of Facebook to purchase the average home in Palo Alto. By March of 2021, that number was down to just 11,077 shares. Quite incredible.

Bitcoin ($BTC)

While I realize that Bitcoin isn’t a large employer in Silicon Valley, nor is it a stock, the original idea for this post came from a joke I made on Twitter back in 2017.

Most of you likely already know the story here. Bitcoin price appreciation in the past 12 months has been unbelievably high, so looking back to June 2012 is going to be somewhat jarring.

In June of 2012, the price of Bitcoin was about $9.40. By March of 2021, it had risen to $57,326.20. That’s a gain of over 609,753%.

The growth rate in Bitcoin prices, as measured in US dollars, has been so incredible, this chart is almost impossible to read in recent years.

For context, in June of 2012, it took about 153,586.2 Bitcoin to purchase the average home in Palo Alto. By March of 2021, that number had dropped to just 54.9 Bitcoin.

This, of course, has a number of dramatic implications. As measured in US dollars, or in real assets like Palo Alto real estate, the wealth of Bitcoin holders has increased dramatically. As measured in US dollars, the average price of a house in Palo Alto has increased by 117.9% in less than 10 years. However, as measured in Bitcoin, the average price of a house in Palo Alto has decreased by 99.96%.

There aren’t many people who invested in Bitcoin back in 2012, but a disproportionate number of them were in Silicon Valley. However, even based on recent numbers, the story is similar.

In March of 2019, you could have purchased the average house in Palo Alto for 702.0 Bitcoin. Just two years later, in March 2021, the average house in Palo sold for 54.9 Bitcoin. That means the average home in Palo Alto, as measured in Bitcoin, has decrease by 92.2% in just the past two years alone.

Silicon Valley Is Seeing Significant Asset Inflation

These charts are not meant to imply direct causality, but in many ways they confirm several economic facts about Silicon Valley that may not be obvious when looking at nationwide statistics.

Because technology employers in Silicon Valley compensate most employees with equity, it is very likely that asset inflation in stock (and crypto) markets has some impact on the housing market. This is likely exacerbated by the lack of new housing construction in Silicon Valley.

The fact is, if you are fortunate enough to have equity in one of the tech giants, or if you have been an investor in Bitcoin, houses might actually look cheaper in 2021 than they did in 2012, or even in 2020.

What is most surprising about the data refresh is the apparent detachment of equity and crypto prices from the prices of Palo Alto real estate. There are a number of potential reasons why this might have happened. One theory is that real estate markets move relatively slowly compared to equities and crypto, and so the rapid price increases of 2020 have not yet worked their way into the market. A second theory is that large technology company compensation has been shifting away from stock options to RSUs, leading employees to hold less stock as they convert their shares to cash on vesting. A third theory is that we’re seeing complicated effects from COVID, as windfall money from equity and crypto markets may be flowing into other places rather than local real estate.

(Before the San Francisco crowd gets too rowdy, there is absolutely no evidence yet that more money is flowing into San Francisco real estate instead of Palo Alto this cycle.)

In any case, whatever the reasons may be, it is always worth checking the actual data to see whether it confirms or contradicts our intuition.

Let’s check back in another four years.

“The journey of a thousand miles begins with a single step” — Lao Tzu

As the year draws to a close, I wanted to share some good news: Alejandro Crosa & I have started a new company, and we’ve raised an initial round of funding led by Ribbit Capital.

This was one of my goals for 2020, and I couldn’t be more delighted to be setting off on this adventure with Alejandro.

Alejandro is one of those rare talents that makes Silicon Valley special. When we first met, he was a contract engineer from Argentina, referred by Google to LinkedIn as we prepared for the Open Social launch back in 2007. But Alejandro had an unstoppable desire to learn, moving from platform to search to mobile. Together, we collaborated on a number of innovative prototypes, including a search engine for Twitter based on LinkedIn data (I still miss this one…)

His passion for new technologies, design, and great products is inspiring. 

Even after we both left LinkedIn, we kept in touch, and talked often about starting a company together. This is that company.

Alejandro & I believe that there is still a lot more to do in consumer fintech, and that through software we can help bring purpose to the way people approach their financial lives. 

Micky & Nick have built one of the pre-eminent firms in fintech; they risked their own money and believed in the category long before most venture firms were willing to invest. We couldn’t be more excited to partner with Ribbit on this new adventure.

I also want to thank Ross Fubini at XYZ Venture Capital for his support, as well as a humbling list of friends & angels for backing this new idea. So thank you to Gina Bianchini, Amy Chang, Walter Cruttenden, Dylan Field, Todd Goldberg, Minnie Ingersoll, Aaron Levie, John Lilly, Gokul Rajaram, Mike Schroepfer, Leonard Speiser, James Tamplin, Rahul Vohra, Liza Wang, and the rest of our investors for supporting us. 

Most importantly, we are hiring! If you are a talented engineer or designer excited about consumer fintech, and want to take a shot at building a platform that just might change the world for the better, come join us!

We’re just getting started.

When I first joined Greylock at the end of 2011, Fintech wasn’t even a word that was commonly used in the venture capital community. Less than a decade later, however, Fintech has become almost ubiquitous. The category has not only proven that it can generate real revenues and scale, but also that it can create a large number of multi-billion dollar companies.

Unfortunately, when you are looking at seed stage opportunities, you have to think clearly about markets where there is the potential to build new multi-billion dollar product & companies.

When the bubble burst in 2000-2, there was a lot of thought put into what had worked and what hadn’t worked with Web 1.0, and those insights formed the basis of the next wave of software companies (Web 2.0 / Social). Some of those same issues have plagued Fintech 1.0, and may instruct how to think about Fintech 2.0.

As 2019 drew to a close, I took the opportunity to spend some time thinking about exciting new opportunities in consumer fintech. These continue to be areas that I’m investing against both as an angel and as a founder.

Beyond Millennials

For the last decade, a vast majority of consumer fintech startups have focused on millennial customers. This really isn’t surprising because the traditional financial services industry is so heavily invested in their older customers. By the numbers, households tend to build income and assets as they age, and the incumbents have spent decades servicing this customer base.

Young people, on the other hand, were the perfect market for new, unproven products and services. Young people are less tied to existing brands and services, more likely to be technophilic, and have simpler financial needs.

As we enter the next decade, however, consumer acceptance of new financial products & services will continue to grow, leaving new demographics open to new products & services. This would have been true regardless, but it seems clear that the COVID-19 pandemic has accelerated this opportunity.

These customer segments will be more competitive, but also potentially more valuable, as they collectively are much larger than the millennial market.

Single Player to Multiplayer

Traditional financial products & services are single player, which makes sense since people tend to expect a high degree of privacy around their finances, and products built for individuals are much simpler to design, market, and activate.

However, many new fintech services are built around a subscription-model, where three numbers tend to dominate: acquisition costs, average revenue per user, and churn rate. The last, of course, is a heavy determinate of lifetime value.

Multiplayer products & services have a number of advantages. Multiplayer products are inherently viral, pulling more people into the system and lowering average acquisition costs. More importantly, multiplayer products are fundamentally stickier, leading to lower churn rates and higher lifetime values.

One of the big shifts from Web 1.0 to Web 2.0 was designing products & services to be intrinsically multiplayer. This was one of the fundamental differences between the design of LinkedIn (Web 2.0) and Monster.com (Web 1.0).

Novel Products & Services

When web development began in earnest in the 1990s, most initial product concepts were just moving existing products & services online. Mail order catalogs already existed, but we put them online. Yellow pages already existed, but we put them online. There were a few novel products (eBay), but for the most part, we collectively just moved a lot of products into the cloud, with all the advantages that global reach & distribution brought.

Fintech 1.0 has also mostly replicated existing products, put them on modern technology platforms, and made them broadly available to customers (like young adults) who have been mostly underserved.

However, one of the great opportunities in Fintech long-term is leveraging technology platforms and distribution to create products & services that were not viable, or even possible, in the physical world. With Web 2.0, we saw a large number of products & services that just couldn’t have existed offline.

2020 Examples

Not surprisingly, ambitious founders have already started building products & services along these new dimensions.

Carefull is a novel service that connects Millennial & Gen X adults with the finances of their aging parents. Once connected, it provides peace of mind for customers that if anything unexpected happens with their parents’ or grandparents’ finances, they will be alerted.

PaceIt, led by Prof. Shlomo Benartzi, is working to tackle the problem of retirement income directly by building a service designed with retirees (or near retirees) in mind. This is one of the most challenging and potentially valuable financial services, and PaceIt believes they can deliver a highly differentiated service based on sound insights from behavioral economics.

Braid is a novel debit card designed from the ground-up for households and small groups (e.g. roommates), providing a standard way to transparently share expenses between groups of people.

Pillar Life is a digital platform that helps people protect and care for their aging loved ones. Pillar replaces outdated & messy physical files with a secure online vault where you can easily store, organize, and share all your family’s most important information like financial accounts, legal documents, medical records, and more.

2020 may have been a terrible year on most dimensions, but as an angel investor for over nine years, it turned out to be my most active one yet. Hopefully, this bodes well for the future of Fintech, and for the financial products & services we’ll all be able to enjoy in the coming years.

In 1991, when I turned 16, I had my first used car buying experience. My father took me to several different lots where we looked at the almost random assortment of cars in our price range. As it turns out, my father is a surprisingly good negotiator and had no trouble walking away from a bad deal. Unfortunately, that meant we walked off each and every lot we visited that day empty handed.

Fortunately for me, my uncle saved us from having to do another day of traditional used car shopping, and I drove his used Toyota pick-up all through college and grad school. But for millions of people, buying & selling a used car is still too painful, expensive, and complicated.

A Better Way to Buy & Sell Used Cars

When George Arison & Minnie Ingersoll came to visit me to talk about the new company they had started, I was immediately impressed with their excitement for a truly mobile-first approach to buying & selling used cars. Over the years, I’ve been phenomenally impressed with the way the team iterated and expanded on their original vision. In 2017, I had the opportunity to sell a used car on the platform, and it was transformationally better than my previous experiences trading in cars to dealerships or selling the car directly through classified ads.

As a product leader & angel investor, I try to focus on products & companies that are working to reinvent a key customer experience. In 2014, I invested in just six companies; they included Gusto, OpenDoor, and Shift.

For many people, buying and selling a car is one of the largest transactions they make in their financial lives. The system has long been littered with opaque practices, overblown loans, and sleazy sales tactics. Taking the high road, Shift has made transparency their hallmark, listing out any fees, doing away with haggling, and making financing more user-friendly and easier to understand. They even built out a loan term predictor so customers can know for certain what they can afford before they even start shopping. 

The company is now slated to go public in the coming weeks, and has grown considerably on the West Coast, aided by its  first-class operations and Silicon Valley culture. Customers finally have a way to buy or sell a car for a fair price without leaving their driveway.

Joining the Board of Directors at Shift

I’ve spent my professional life working to build products that truly improve the lives of ordinary people: whether a working mom who uses eBay to earn a little extra income on the side, a young college grad beginning to build their professional reputation, or the up-and-coming eager to start saving & investing.

I felt fortunate to have been one of the original angel investors in Shift. I was delighted when we sold our car through the service. I’m now grateful for the opportunity to join George, Toby, and their team as they make the transition to being a public company.

• Press Release
• Company Blog

If you are looking to buy or sell a used car, please get Shift a try. Reach out, and let me know about your experience. We’re excited about the road ahead.

Some personal news to share today.  After a great tour of duty at Dropbox, I’ve decided to take the leap into something new.

Having a January birthday has always added a little weight to my New Year’s resolutions, and as it turns out, 2020 was a big one for me. 45 might not be the biggest milestone birthday, but combined with the weight of a new decade, it had me thinking deeply over the holidays. Fortunately, I was able to spend a good deal of time with friends & family, and by New Year’s Eve I felt comfortable with a simple, but important, decision.

2020 will be different. This will be the year that I go off on my own.

The hardest part of this process was telling my team at Dropbox. I feel so very fortunate to have had the opportunity to lead such an amazing group of professionals. And as proud as I am of what we accomplished in 2018 & 2019, I’m even more excited about what this team will deliver for their customers in 2020 & beyond. 

For me, I’ll be spending the next few months preparing for the long road ahead founding a company. As one of the growing number of “operator-angels,” I’ll continue to advise and support the talented teams at the companies where I’ve invested over the past 8 years. Primarily, though, I’ll be spending time on a couple of specific fintech ideas that I think have the potential to be great companies. 

I have spent over 20 years learning to build & design great products and great companies, but somehow never my own. As an angel investor, I’ve now helped fund and advise over fifty amazing founding teams, and have had a front row seat to their struggles and successes. It’s time to take the plunge.

And who knows? I hear 45 is the best time to start.

On October 8, 2019, I was asked to give my talk, “Be A Great Product Leader” to a huge audience at Amplify 2019, the product management conference organized by Amplitude.*

The talk is named after possibly my most famous blog post on the topic of product leadership from 2011, Be A Great Product Leader.

For those of you who have seen earlier renditions of this talk, this version was cut down to thirty minutes, and as a result has a subset of topics. All of the lessons in this talk started as blog posts:

1. The Secret to Product Prioritization. Three Buckets
2. Find the Heat. Don’t Be Afraid to Talk About Emotion.
3. Einstein’s Razor. Make Things As Simple As Possible, But Not Simpler.
4. Obsess About Your Non-Users. Growth Comes from Them.
5. Solve the Product Maze Backwards. Think Back from the Future.
6. Know Your Superpower. Product. Design. Engineering.

Over the past ten years, I’ve given versions of this talk at over twenty different companies and conferences, but there has never been shareable video of it. Fortunately, Amplitude captured the video and  posted full video of all of their talks, including mine.

Product leadership continues to be a hot topic in the industry, and I hope that these lessons will help inspire more people to become great product leaders.

* Special thank you to Melinda Byerley for making the introduction!

Source: Deseret News, Jan 24, 2020

On January 23, 2020, Clayton Christensen passed away at the age of 67.

I found out about his passing during my commute home from work on Friday, and it left me reflecting deeply on my experiences with Clay. I enrolled in his class back in 2000 at HBS, and was fortunate enough to have him agree to be an advisor to me on an independent project on the topic of disruption. Over the years, when I would visit HBS for recruiting or for a case study, I would always try to stop by to see him. Ever gracious and thoughtful, he may have been the most influential professor in my life.

There have been some wonderful pieces written about Clay in the past couple of days, mostly reflecting on his impact on management theory or his lifelong dedication to his family and his church. The list of his accomplishments is appropriately long. However, there are a few personal details I’d like to add to the story.

First Meeting

Many people are familiar with Clay’s work on innovation and disruption, made famous by his 1997 book, The Innovators Dilemma. It’s always shocking to me when I meet people in Silicon Valley who haven’t read it – that’s how fundamental it has been in shaping my thinking about business & strategy.

However, the professor I met at Harvard twenty years ago didn’t talk about innovation, disruption or how to build a successful business. He talked about the morality of business, the ethics of leadership and about his own personal journey.

Clay was a warm and friendly person, but when I first saw in him walk into our class, it was hard to ignore just how tall he was. At Harvard, the third row of seating is known as the “Power Deck” because when seated you are eye-level with the professor. I used to joke that in Clay’s class, it was the fourth row that was the Power Deck.

In some ways, Clay’s height made his approachability and humility even more surprising and authentic.

Clay’s class was supposed to be about strategy, but he opened his first lecture with a discussion of people. He spoke about how we spend most of the hours of our adult lives  at work, and how impactful those hours are on the emotional wellbeing of people even outside of work. He asked us to think about great managers we’d had in the past who supported us and gave us energy, and terrible managers who had drained us of it.

And that’s when he told us that he believed that being a great manager was one of great moral responsibility, because your leadership would either make the people who worked for you miserable, or they could bring those people joy & accomplishment.

When Clay talked about leadership, he talked about it with a clarity and conviction that is rare. To this day, when I take on a new leadership position, I talk to my teams about the responsibility I feel to them based on Clay’s words.

Professional Journey

Clay’s professional journey also resonated with me. Most people don’t know that Clay himself was a founder, starting a company focused on advanced ceramics back in the 1980s material science boom. It’s a bit of personal trivia, but my first love at Stanford  wasn’t Computer Science. It was the Introduction to Material Science that made me decide to major in Engineering.

But after that experience, Clay had decided to go back to school. It is unusual for an MBA to go back to get a PhD, but he went back because he wanted to study management and teach. His passion for a more rigorous framework on how managers make decisions led him to the insights that became The Innovator’s Dilemma, and the career that we all know him for. His fundamental belief that managers were intelligent and capable led him to frame an incredible problem: how do large companies continue to fail when they have access to so many smart people and almost unlimited strategic resources?

However, his choice wasn’t purely motivated by academic or professional interest. He talked openly about his family, his wife and his children, and the life he wanted to create for them. He talked about his faith, and how he wanted to be judged in the end.

Not everyone who is religious leads an exemplary life, but for Clay, his faith seemed to amplify and enforce his ethical rigor. In his later work, he would argue that it was easier to hold the line ethically 100% of the time than 98% of the time, because one compromise leads to another, then another.

How Will You Measure Your Life?

Over the years, when I would visit Clay at HBS, he was always warm and encouraging. We would discuss each career move I made: eBay, LinkedIn, Greylock, Wealthfront. The clarity of his strategic thinking was always a gift, and his willingness to engage and debate when we disagreed was always a bit surprising to me. But Clay loved to sharpen his thinking, and had seemingly no ego tied to defending ideas or business strategies. He just loved finding more insight; a twinkle in his eye in the pursuit of a clearer glimpse of the truth. I always left of our conversations feeling amplified by both his support and his energy.

In 2010, Clay published a piece based on these ideas that became a book by the same name, How Will You Measure Your Life.  It is worth reading, and even re-reading.

I have a pretty clear idea of how my ideas have generated enormous revenue for companies that have used my research; I know I’ve had a substantial impact. But as I’ve confronted this disease, it’s been interesting to see how unimportant that impact is to me now. I’ve concluded that the metric by which God will assess my life isn’t dollars but the individual people whose lives I’ve touched.

I think that’s the way it will work for us all. Don’t worry about the level of individual prominence you have achieved; worry about the individuals you have helped become better people. This is my final recommendation: Think about the metric by which your life will be judged, and make a resolution to live every day so that in the end, your life will be judged a success.

Rest in Peace, Clay.

One of the fond memories I have of my first two years at LinkedIn was coming into the office almost every Sunday to spend a couple of hours with Reid Hoffman.

Our conversations covered a wide range of topics, but the time ensured that we were fully aligned on the strategy of the company and the priorities we were pursuing.

One of the topics that I was most fond of discussing was the nature of risk, and how to best lead teams when facing the various types of risk that are commonplace at hypergrowth startups.

Here, Reid never varied, and I quickly adopted his framework as my own. In the end, most of our productive discussion involved deciding which of three types of risk a particular decision involved.

Three Types of Risk

Categorizing the type of risk you face is incredibly useful in helping teams understand how much effort and consideration to spending on making various types of decision in the face of uncertainty.

For hypergrowth startups, risk can be categorized as one of the following types:

1. Fatal Risk
2. Painful Risk
3. Embarrassment Risk

Fatal risks are true bet-the-company issues. They are not that common, but they deserve clarity and focus. If you get the answer wrong here, the company is dead. These risks are unavoidable in early-stage startups, but as companies grow they become more and more uncommon. In fact, most large companies lose the ability or even recognition of these type of risks as they age.

Painful risks involve decisions that have significant repercussions if they go the wrong way. You might miss a key goal, or lose key people. They are recoverable, but there are real ramifications to getting the answer wrong.

Embarrassment risks have no significant impact if they are missed. All that is necessary is to acknowledge the mistake, change course, and move on.

Embarrassment risks are particularly difficult for smart & ambitious people, largely due to insecurity and ego. People want to be perceived as intelligent and successful, and they incorrectly map that to always being correct.

Unfortunately, most people at hypergrowth startups spend far too much time debating embarrassment risk, and they don’t take enough painful risks.

What About Type 1 & Type 2 Decisions?

Jeff Bezos has more recently popularized a different framework, based on two types of decision. This framework is often described in the context of the decision to move forward with Amazon Prime, which at the time was mostly a judgment call versus a data-driven decision.

In his framework:

• Type 1 decisions are irreversible. Spend time on them.
• Type 2 decisions are reversible, like walking through a door. Make them quickly and move on.

Overall, this framework is helpful. Thinking through the reversibility of decisions helps prioritize speed vs. perfection. When it comes to execution, the perfect truly can be the enemy of the good enough.

The problem is that almost every decision at a company is reversible, so it tends to not provide that much insight into why some risks feel harder to take than others.

Lessons in Execution

In some ways, you could describe painful risk & embarrassment risk as two sub-categories of Type 2 decisions. The speed of execution depends on taking these type 2 decisions quickly and aggressively, framing them as risk, and clearly articulating what the team will do if it doesn’t play out as expected.

Leaders need to embody this type of decision making, to give permission to newer employees to take risks and communicate their decision making effectively.

Otherwise, a spiral of low expectations and low-risk options will quickly put you in a vice when faced with more aggressive competitors. Worse, you won’t be taking enough shots on goal to learn fast enough to have high odds of success.

Large companies trend towards this problem because decisions become increasingly about the personal positioning of individuals for their own advancement, rather than optimizing for the best results for the company or their customers.

Ironically, taking painful risks may be the only way to set yourself up for exceptional outcomes.

The next time you see your team facing a decision in the face of uncertainty, try to quickly agree on what type of risk you are facing and what type of decision you are making. In most cases, you’ll be able to make decisions more quickly and save your time for the rare, but very real, risks that you have to navigate with your product and your business.

Four years ago, I wrote about the transition technology CEOs needed to make from economics to politics. Coming back from this year’s gathering, there  is no question in my mind that this insight turned out to be true. Responsibility was a significant theme this year. As the technology industry continues to grow and mature,  more and more people are looking to investors and technology leaders to think ahead about potential issues that will happen when their creations become ubiquitous.

It got me thinking about drones.

The Problem with Drones

The FAA projects that the number of drones will reach 7 million in just the US alone by 2020. The growth rates for both consumer and commercial drones continue to grow at a rapid rate. The FAA estimates that there will be over 3.5 million hobbyist drones in the US by 2012.

Over the past few years, I’ve made a few investments in startups in the drone space. But until last year, I hadn’t given significant consideration to all of the safety issues around drones, particularly as they fly over large crowds or critical infrastructure.

The problem is fairly simple. Large venues, like sports stadiums, and critical infrastructure are largely defenseless against drones. Whether it’s a music festival, a weekend football game or anything of that sort, most people don’t realize that event managers really have no solution to protect a crowd. Whether accidental or intentional, there is a real risk that a malfunction or crash could harm people.

The Need for Active Measures

Long term, of course, we can imagine a world where drones can be programmed to avoid these spaces, (Airmap is a great example of a company making this happen). However, We can’t just assume or depend on this to be universally true – that risks the mistake of being overly idealistic. There needs to be an active solution to protect critical areas.

There are a number of companies working on solutions that involve intercepting and disabling drones that enter space that needs to be protected. In fact, there are solutions like drone on drone capture (with nets) , projectile solutions (shoot it down) , even flamethrowers! 

Unfortunately, these kinetic measures make little sense in cases where the drones are flying over areas that need protection. If the concern is a drone crashing into a crowd or important infrastructure, these solutions run significant additional risk of the drone or pieces of the drone causing damage on impact. While there is definitely a market for kinetic solutions in the military and related markets, but it seems like a bad fit for the majority of the simple but real threats out there.

A Software-Based Solution for Drone Protection

Last year, as the co-chairman of ICON, I had the good fortune to meet Gilad Sahar, the co-founder and CEO of Convexum. With the unique insight that comes from military experience with both the costs & benefits of active solutions, they have developed a non-violent, software-based active measure to help automate perimeter protection from drones.

The concept is fairly simple.

Convexum has developed a device that allows companies & governments to detect when a drone is entering a restricted space, take control of the drone, and land it safely. A cloud-based service ensures that all Convexum devices have up-to-date signatures for known drones.

Initially, they are seeing significant demand for this solution around critical infrastructure, like energy development, and sporting venues. Long term, I can easily imagine a future where a non-violent solution for drone protection would be highly desirable anywhere we don’t want to bear the safety risk (like schools).

Working with Government

Europe has already provided a clear path for companies and government entities to receive the permits & exemptions needed to deploy this type of solution. (In fact, Enel has already deployed a solution to protect power plants.) Congress & Senate debating this now in the US, but seems to be one of the few remaining areas of true bi-partisan alignment.

I’ve personally been so impressed with Gilad & Convexum, I’ve decided to help them by becoming an advisor to the company.

Let’s hope this is part of an increasing pattern of entrepreneurs and investors thinking ahead about safety and regulation, and supporting technologies early that can help solve these eventual problems.

Over the course of my career, I’ve been fortunate enough to work in a variety of different functions.  No matter whether it is engineering, design, product, or service, every role has its own unique set of requirements and challenges.

Maybe that’s why I have always believed strongly that software is a team sport. If you want to build exceptional products, you have to find a way to harness the unique and diverse viewpoints of a team of professionals across a wide variety of functions.

Unfortunately, even at great companies, there is a repeated pattern where people in some functions feel disempowered. This doesn’t need to be the case.

Every function has a superpower. Make sure you know what yours is.

Every Function Has Value

Hypergrowth software companies are relentless in their pursuit of efficiency. Everyone who joins a new company dreams of building something new, something better than the companies that came before it. As a result, startups are always questioning the breakdown of functions in older, more established companies. In addition, resources are always tight, as companies stretch to make every dollar of funding count.

Unfortunately, this also means that many startups repeat the same mistakes over and over again when it comes to recognizing the value of different functions in a modern software company. This can be compounded by having a founding team or early employees who have never worked in those functions before.

You don’t really know a function until you know someone who is exceptional at it.

Inevitably, most startups, even when they have grown to hundreds of people, have gaps in their understanding and appreciation of some functions.

Avoiding Decision By Committee

Besides the lumpy build-out of different functions at fast-growing companies, the need for fast decision making also tends to bias the product process.

Great companies tend to be opinionated in their decision-making process around product, and those processes can vary significantly. Some companies may overweight decisions from engineering, others might look to a strong product function. There are companies that are largely sales-driven, and others that rely on general managers. There are companies where decision-making is hierarchical, deferring to the CEO or founder for key product calls, and others where decision-making is distributed broadly to the teams.

This isn’t surprising, however, because there is a direct tension at companies between the speed of execution and the exhaustiveness of a process. As a result, almost every product-centric company seeks to avoid “decision by committee” by assigning decision responsibility to a function or a hierarchy.

No matter what system exists, there are always people and functions that feel disempowered by the process.

Know Your Superpower

While you may not be the one to make the final product decision, it is a mistake to feel disempowered. Your function has unique value, and you can dramatically shape any product decision through your efforts.

The key is to know your superpower.

Every function has one. Here are just a few examples:

• Engineering. Every engineer has the ability to take what is and isn’t possible off the table. I’ve seen product strategy discussions completely changed in a single weekend by engineers building something that no one else had even considered. The power to create is an awesome one, and the best engineers use this power to open the eyes of their teammates to what can be accomplished.
• Design. Most people can’t visualize the different options that are possible around a given feature or product, and design has the power to reshape discussions completely based on visualization. Design can eliminate theoretical options, define the choices available, and most importantly trigger a deep, emotional response to certain choices in decision makers.
• Product. At some companies, product managers have procedural power to make decisions. However, the most effective product managers use their power to frame the discussion with strategy and metrics to help drive decisions. The power to define the framework for a decision often is the power to control the decision.
• Client Service. If you spend your day talking to real customers about real problems every day, you have amazing power to bring issues to the fore. Sometimes a decision is swayed by the scale of the problem, other times by the severity. Never underestimate the power of narrative, driven by real customer stories, to shape decisions on product and prioritization.

Every function has a superpower and everyone has the ability to do the extra work necessary to tap the unique capabilities and resources of their function to use that power to shape decisions. It requires work, but no matter what your function or role is, you can heavily influence critical decisions.

You just need to find your superpower.

— Steve Jobs, Stanford University, June 2005

In 2012, I was seriously considering becoming a full time investor.

I’ve always loved startups and venture capital, and I had been fortunate enough after leaving LinkedIn to have a chance to work for Greylock Partners, one of the most successful firms in the industry.

In May of 2012, my daughter was born. While on parental leave, I remember receiving a note about a Greylock company that was looking to add to its executive team. I had visited that company just the month before, to help advise on strategies for organizing and executing on viral growth.

The role itself wasn’t the right fit, but for some reason that company stuck in my head. Did I really want to become a full time investor? Or did I want to go help build a company?

As it turns out, the company that I couldn’t get out of my head was Dropbox.

First moments after the birth of my daughter, May 2012.

Opportunity at Scale

Over my career, I’ve had the good fortune to work at three companies that grew to reach over 100 million users. After spending the past six years focused on building new companies, I’m excited about jumping back into the challenges of designing and shipping features for the more than 500 million people who use Dropbox to get things done.

With the proliferation of devices and ubiquitous connectivity of the modern workplace, I think there is a unique opportunity, right now, to help teams unleash their creative energy and find more enlightened ways of working together.

Drew has done a great job of sharing the high level vision for Dropbox, and I’m excited to dive into a space that has so much product potential.  The era of walled gardens is over, and there has been an explosion of new applications and content types in the past few years. The challenge is to design an open ecosystem that helps bring all of those capabilities together in a way that doesn’t sacrifice simplicity in design.

Connecting the Dots

For now, I just want to say thank you John Lilly for reconnecting me to the Dropbox team, and thank you to Quentin, Drew, and the entire Dropbox team for this opportunity. It is truly amazing how life connects the dots.

On March 8th, Dick Weil, co-CEO of London-based Janus Henderson Investors,wrote an op-ed in the Wall Street Journal arguing that the SEC should prevent index-funds from voting on shareholder proxies. In it, he argues that index funds “have no interest in the performance of particular companies” and that index funds “lack a strong incentive to cast informed votes.”

Unfortunately, Mr. Weil misses some of the most important incentives that drive long-term equity holders, including index funds. In fact, index funds are likely to be superior to active funds for effecting good long-term corporate governance.

Index Funds Are Long-Term Owners

In October 2017, Jack Bogle gave an interview with Morningstar that addressed this exact issue. His argument, as usual, was clear and compelling:

Benz: How about on the governance front. I know you and I have talked about this over the years, about whether passive products are more limited than active managers from the standpoint of influencing corporate governance of the companies they own. What do you say to that assertion that passive products because they can’t walk away from some of these companies altogether don’t have that ultimate weapon that active managers do have?

Bogle: I’d say traditional index funds are the last, best hope for corporate governance.

Benz: And why is that?

Bogle: That’s because they’re the only true, long-term investors. Corporate governance should be based on long-term factors affecting the corporation, not a bunch of traders who want you to report higher earnings, gonna try and get on your board for a minute, and in a moment … I don’t know how they’re this smart to do it, but realign the entire company and then all will be well. It just doesn’t happen. In fact, the reverse is more likely to happen.

So, I don’t see … The old Wall Street rule was if you don’t like the management, sell the stock. The new index fund rule is if you don’t like the management, fix the management because you can’t sell the stock.

The critique of index funds and corporate governance comes from the mistaken idea that it is only by buying and/or selling a security that you can influence management and the allocation of capital. While there is no doubt that individual actions in the secondary market affect the price of a security, and the price of a security can affect capital allocation decisions, it is a relatively indirect link. Activist shareholders typically use these actions, but as a means to more direct control, either influence or direct membership on the board of directors.

Unfortunately, because discretionary investors have the power to walk away and sell a security, there is a weakness in their commitment to fixing a company. While some of the best activist private equity funds might spend years working to improve the returns of a company, most active investors show no such patience.

Index funds effectively operate as permanent owners of the business, so their incentive is to work to improve the performance of each and every company in proportion to their market capitalization.

Patient Capital Has Value

Perhaps one of the most compelling aspects of index funds as investors is their reliability as a patient source of capital. There is no doubt that the short-term focus of current capital markets is a problem for public companies looking to optimize their performance for the long term. Very often, significant changes in corporate strategy take years to implement, and can often result in negative short-term performance in exchange for the potential for significant long-term upside. Unfortunately, if most investors hold securities for short periods of time, management can be pushed for making decisions that are optimized for long-term value creation.

In fact, this problem is the focus of Eric Ries’ new startup, the Long-Term Stock Exchange.

For example, as of 2013, the average active mutual fund had a turnover of over 85% (according to Morningstar). This means their average holding period for a stock was barely over one year! They are not long-term investors, and their financial interest is incredibly biased towards short-term performance. They are not going to support any solution to a corporate problem that might hurt short-term performance.

This is not just a problem for active mutual funds. Private equity buyout funds, based on their structure, predominantly look for returns often within a relatively short number of years. Because they often use debt to leverage their buying power and maximize return on capital, their playbook also includes damaging short-term actions like the payoff of significant one-time dividends that can starve a business of long-term capital.

Index funds provide long-term, patient capital that is well aligned with the desire to see companies optimize their corporate governance for maximum shareholder value. The time frames of active investors are just too short to align with management changes and strategic choices that may not pay off for years, if not decades.

This Applies to Crypto, Too

One of the most exciting developments in cryptocurrencies has been credible initiatives around index investing. Bitwise Investments (currently available) and Coinbase (available soon) have both announced crypto index products and platforms. (disclosure: I am a private investor in both.)

Over the past few years, more and more investors are convinced there is an incredible opportunity for blockchain-based products and platforms. Though cryptocurrencies have the same liquidity as public companies, they are based on far younger organizations and will take time to develop. Index funds can act as a stabilizing force amidst the volatility, especially if index funds see continued net-positive inflows like their brethren in equity and debt assets.

Amidst all of the volatility, index funds will likely also have a role to play as aggregators of long-term holders of cryptocurrency. Index funds, given their incredibly long time implicit frames, are aligned to advocate for governance and development that will maximize the long-term value of the ecosystem.

Index funds may not control the marginal price of these assets, but they can provide a structure for a large pool of investors to have a long-term influence on the direction of these platforms. Whether the future belongs to proof-of-work systems, proof-of-stake, or other alternatives, my guess is that we’ll find that, over time, that access to long-term, patient capital is a huge benefit to products and platforms in crypto.

Long-Term Ownership Will Improve Governance

While there is no question that active investors can have a positive impact on the governance of corporations, it would be foolish not to see the additional advantages that index funds bring to the financial ecosystem.

Index funds may actually be the missing form of long-term, patient capital that we’ve needed in corporate governance to better align companies with the creation of long-term value for all of their stakeholders.

Over the last twenty years, I’ve been asked by hundreds of students for advice on how to think about their careers post-graduation. Inevitably, I’ve always responded with a simple framework to help structure their thinking around picking a profession:

1. What are you exceptional at?
2. What do you love to do?
3. What does the world value?

As it turns out, there is a Japanese concept for this framework. Ikigai.

The Reason You Get Up in the Morning

Dan Buettner gave a TED Talk called, “How to Live to Be 100+.” He focuses quite a bit of his lecture on the island of Okinawa and their extraordinary number of centenarians. He identifies several diet and lifestyle habits that seem to correlate with a long and healthy life. Ikigai is one of those concepts. He recently gave an interview in the Telegraph:

He talked of a 102-year-old karate master who still practised, a 100-year-old fisherman who loved to bring the catch to his family, and a 102-year-old who, asked what her ikigai was, said that holding her great-great-great-granddaughter, a century her junior, felt like “leaping into heaven.”

What Are You Optimizing For?

When I was in college, my mother constantly reflected on the bad advice she felt students were given as they attempted to pick a career. “Everyone tells students to follow their passion. It’s not that simple. There is a big difference between a hobby and a career.”

My father tended to be more direct. “The world doesn’t owe you a living,” he would often say, “Find something that people value.”

Our popular culture has become saturated with the idea that if you just find your passion, something you love doing, then your career will magically present itself. If only success were so simple. Finding something you love to do is critical, and if you are fortunate, you’ll find several. As it turns out, that’s just one piece of the puzzle.

The fact is, you may love something that the world doesn’t value highly. The world may value things that you aren’t very good at. And of course, you may be good at something that you don’t want to do.

The benefit of Ikigai is that it helps separate out the dimensions you can optimize your professional efforts around, in attempt to help you find a combination that will result in professional success and fulfillment.

Four simple questions.

1. What do you love? Find something that you really enjoy doing. It’s simple to say that the journey is the reward, but when you love to do something, work can be something you look forward to.
2. What are you good at? We all have different talents and aptitudes. With practice and determination, you can develop mastery in a wide variety of areas. However, if you have a natural (or hard-earned) talent in an area, that’s worth identifying.\
3. What can you be paid for? Just because you can do something, doesn’t mean that the other humans around you will value it. Looking for something that the market will reward financially is a critical piece of this puzzle if for no other reason than to set expectations realistically.
4. What does the world need? Being the unabashed capitalist, I originally assumed that anything the world needed would also be something the world would pay for. Stepping away from the theoretical argument, there is significant value in transparency from separating out this requirement.

Imperfect Combinations of Three

One of the most insightful aspects of Ikigai is the imperfect combinations of three of the four dimensions that are represented in the chart by different colors.

If you find work that you are good at, that you can be paid for, and that the world needs, you may find yourself feeling comfortable but unfulfilled. In this case, you aren’t working on something you love, but likely being compensated for your work and seeing its valuable impact on others.

If you find work that you love, you are good at, and that you are being paid for, you may find yourself feeling satisfied but useless. In this case, you aren’t working on something the world needs, but likely being compensated for your work and enjoying what you do.

If you find work that you love, you are good at, and that the world needs, you may find yourself feeling delighted but uncompensated. In this case, you aren’t working on something that world pays for, but you enjoy what you do and do it well. Fulfillment without wealth.

If you find work that you love, you can be paid for, and that the world needs, you may find yourself feeling excited but uncertain. In this case, you aren’t good at what you do, but you are being paid for something useful, and you love it. Purpose without proficiency.

It is not difficult to think of situations and phases in your life where you might not need to optimize for every dimension. For example, after a financially successful career, it is fairly easy to imagine why a person might optimize around work that ignores the need to be paid. For a retiree, the space between passion and mission might look ideal.

Finding Balance

Ikigai might sound like the right way to talk to students or young professionals in your life about their professional focus. But I would argue that no matter where you are in your career, you should take the time to be intentional about your professional choices and ask yourself these four questions.

Ikigai. It might be the key to a long & healthy life.

On September 26th, I had the great pleasure of officially kicking off a brand new course at Stanford University, “Personal Finance for Engineers“.  The course was offered through the Computer Science department (CS 007), but was also open to undergraduate & graduate students of any major.

How quickly the quarter went. On December 6th, I gave the 10th and final lecture of the seminar. Grades were submitted by December 18th, and course evaluations were summarized and provided to lecturers by December 20th.

In the interest of learning & transparency, I thought I’d post some of the feedback here, as well as summarize a few of my own reflections on the seminar.

Summary Results: Learning Goals

Out of the 93 students who took the course, it looks like 69% (64) left feedback on the course.  The following charts and material are provided anonymously by Stanford University.

The learning goals for the course were as follows:

1. Expose students to a wide range of personal finance topics.
2. Provide students with both practical & theoretical frameworks to make financial decisions.
3. Build confidence in students on how to approach real life financial decisions.
4. Provide students with content that will encourage discussions with family and / or friends.

Overall, the student feedback on these four areas were fairly consistent. A majority felt the course achieved these goals “extremely well” (highest ranking), with a large minority giving the course “very well” for these goals.The individual comments left by students seemed to confirm these results. A few samples:

Q: What skills or knowledge did you learn or improve?

“I literally knew nothing about personal finance, but just being exposed to this material helped me ask the right questions to myself and my parents.”

“Everything — I’m a financial manager on the row and a senior, but knew next to nothing about finances. This was super super helpful.”

“I improved on a great deal in this class. From understanding behavioral finance. to deciding whether or not to rent/buy, this class truly taught me about personal finance and more.”

Summary Results: Instruction & Organization

One of the elements I underestimated when proposing this class was the amount of time it would take to prepare an 80 minute lecture every week. Converting what previously had been a 60-minute talk into a 10 seminar course proved to be a significant time commitment (one of the reasons you haven’t seen any posts on this blog since the course started).

As a result, I was particularly concerned about what the feedback would be to the course material, since most of it was new. Fortunately, the results look positive.

Individual Feedback: Student Recommendations

One of the most telling results from teaching a course at Stanford are the individual recommendations that students are asked to give about a course to future students.

Yesterday, I had the great pleasure of officially kicking off a new course at Stanford University, “Personal Finance for Engineers“.  The course is offered through the Computer Science department (CS 007), but is open to undergraduate & graduate students of any major.

It was a packed room, and I was delighted. In fact, I was delighted for three reasons.

First, I love teaching. In an unexpected coincidence, the room my course was assigned, 200-034, is the same room that I taught CS 198 for the CS 106 Section Leaders over 20 years ago as a graduate student. It was the home of CS 198 for many years. To see it filled with students again was wonderful.

Second, the level of student engagement has been outstanding. Originally set for a maximum of 50 students, I expanded the enrollment to 75, and with waitlist interest the total number of students easily went over 100. For a new course without a track record on campus, I was delighted to see so many students interested in the topic.

Third, the topic is incredibly important to me.  Those of you who have been following my efforts around personal finance education know that I care deeply about the topic. Over the past 7 years, I’ve given talks at dozens of companies like Facebook, LinkedIn, Twitter & Dropbox, hoping to better educate and inspire employees to learn more about personal finance and make better financial decisions.

I’m hoping this class can amplify those efforts even further.

Making Personal Finance Education Open

I feel grateful to Stanford University and the Computer Science Department for supporting this effort, and I hope that by making the material public, we can help get higher quality education about personal finance to as many students as possible.

My hope is that by circulating this material, more people will engage to give feedback on the content, make suggestions for improvement and continue to improve the material and the class.

After every class, I’ll be posting the slides for the session up on Slideshare. The materials from the first class, “Introduction,” are now available.

As the introductory session, I focused the seminar on three topics:

1. Why the topic of Personal Finance is worth studying?
2. Real data from a survey of students enrolled in the class.
3. Full syllabus for the topics that will be covered during the course.

Student Survey Data

The second topic is based on 10 questions I asked every student in the class to complete before the start of the first session. It is hardly a scientifically representative student survey, but I wanted to ground some of the initial discussion of financial topics with data about their own experiences & expectations.

73 students completed the survey. It’s worth sharing the results of the 10 questions here:

A few data points worth sharing:

Question 1: A little over 50% of the class are either graduating seniors or graduate students. Only 14% are freshman or sophomores.

Question 2: Approximately 3/4 of the class (76%) had a “magic number” in mind when asked about how much wealth would define success for them. While the most common answer fell between $10M-$100M, the range spread from $20,000 to $15B. It was truly a blank field in the survey, so students typed in whatever number came to mind, and it started the process of open & honest discussion on why students picked the number they did.

Question 3: 92% of the students reported that they had either “some” or “quite a bit” of knowledge about the finances of their parents or guardians. Given the selection bias inherent in who signed up for this course (or even what type of students end up at Stanford), it’s hard to assign deep meaning to this result, but this was a class of students who clearly had received some meaningful exposure to financial decisions at home.

Question 6: 92% of students in the class do not expect to be responsible for any student loans after graduation. This was the most surprising result to me, based on both overall market data and my own personal experience .

I have two possible hypotheses to explain the result of Question 6. (1) The selection bias for enrollment in the class might explain part of the result. It is possible that the type of students who are most willing to sign up for a class on personal finance are not burdened by student loans.  (2) It is possible that the financial aid policies of the premier schools, like Stanford, have been highly effective in lowering the number of students requiring loans dramatically. For families with household income below $125,000, tuition is waived, and 71% of families with up to $245,000 receive scholarship assistance. (In fact, 34% of families making over $245,000 also get scholarship assistance.)

Since the syllabus was not shared in advance, Question 10 gave me a clear read of the expectations and hopes students had coming into the class. Not surprisingly, the students were, for the most part, very pragmatic. They are looking for information about compensation & job offers, the stock market, real estate and how to maximize their earning power during their careers.

Feedback

Throughout the next few months, I’ll be posting the course material in the hopes of receiving both corrections and ideas for improvement. If there are topics or material out there worth formalizing into the curriculum, I want to know about them.

Best way to reach me about the course will be through twitter @adamnash

Thank you in advance for your help.

As the father of young children, I can tell you that there is a special place in my heart for restaurants that provide puzzles and crayons for small children to pass the time.

On a recent trip out to The Counter in Mountain View, Jordan (who is 8)  was really struggling with a large maze puzzle on one of these activity sheets. It was a fairly large maze, and he was frustrated by his inability to see the dead ends ahead, forcing him to retrace his somewhat tortured crayon path.

I told him to try to solve the maze backwards.

As you can probably guess, he began at the end, and was able  to find a path back to the beginning in just a few seconds . He was delighted, and a bit surprised, to see how simple the puzzle looked like from a different perspective.

Surprisingly, I find that both entrepreneurs & product leaders miss this important lesson when evaluating ideas for either their company or their products.

Three Questions in Product Prioritization

In my experience, there are three common questions that often come up when product features are being debated:

1. Should we build this?
2. When should we build this?
3. How should should we build this?

Unfortunately, even highly talented teams can become  get bogged down in debate and uncertainty when all of these questions become entangled. As engineers & designers are professionally trained to answer the question of “How,” the worst debates tend to happen around the questions of  “Should” and “When.”

Too often, when debating what feature to work on next, debates around timing quickly devolve into debates about whether the feature is needed at all.

Solving the maze backwards does a fantastic job of disentangling these two questions. Simply asking the question of “If we are successful, will we have this feature in 3 years?” tends to illuminate whether the debate is about “Should” or “When.”

If the answer is yes, you will have that feature, then the question is simple. You are just debating priority.

Avoid the Local Maximum

One of the well known issues with iterative processes for delivering product features is the “local maximum” problem.

The assumption is that where ever you start with your product, your team keeps working on improvements. Each improvement is measured to ensure it is “better” than the product before the change. However, you can reach a point where every change you make hurts the metrics that you measure. The fear is that there is a better version of your product (the absolute maximum), but it requires a change bigger than you can get to from the current design.

It’s called a local maximum problem because of the similarity to the concept in mathematics when you are traveling along the curve. From the local maximum, every move is down, even though the curve ends up higher eventually.

Solving the maze backwards can help.

By asking the simple question about whether or not your product in the far future has a given capability, it can unblock your thinking about what leaps and changes will be necessary. Whether the limitations are in technical architecture or product design, clarity on your long term vision can help your team visualize a future not trapped by their current constraints.

Too often, the real limitation is not related to either technical or design constraints, but rather a lack of clarity and imagination about what might be possible. Just like a maze, it is easy to get lost in the middle. Thinking backwards from the end goal can help the team escape a Zeno’s paradox of minor feature improvements.

Founders Can Solve the Maze Backwards, Too

It may seem hard to believe, but in early 2009 when I took over LinkedIn’s mobile efforts, there was still active debate within the company about whether to dedicate significant effort to mobile. Why? Well, back in 2009, the Blackberry was still hitting record sales, the  app store was a year old, and from a web metrics point of view, mobile views represented less than 1% of LinkedIn’s traffic. Like every hypergrowth startup, LinkedIn had a huge number of initiatives it wanted to pursue around growth, engagement & revenue, and it wasn’t obvious that mobile would move any of these needles for the company in the next few years.

Solving the maze backwards helped.

What was fairly obvious in 2009 was that the growth rate of mobile engagement was compounding at a phenomenal rate. LinkedIn, as a professional use case, might have been slightly behind social use cases for mobile adoption, but it was fairly clear that within 5 years (by 2014), mobile should represent a majority (over 50%) of all visits to LinkedIn.

Thinking backwards helped give us the confidence to invest in both talent and technology that had little short term payoff, but would become essential to engagement over the next five years as those predictions came true.

Fast forward to 2017. I was recently meeting with a founder who was debating whether they should hire a Vice President of Marketing. As he walked me through his thinking, the argument wandered, and became more focused on whether or not the company “needed” marketing.

I asked him if there was any way, if the company hit their numbers over the next three years, that the company would not need marketing, or an experienced marketing leader?

The CEO quickly responded that marketing would be essential to hit the numbers they were looking for in three years. All of a sudden, the conversation changed. The question wasn’t whether or not to invest in marketing, but more a question of when they need to.  Was this a 2017 or a 2018 problem? Is this something they would need to hit the milestones to raise their next round of funding, or something that they would invest in during the next cycle?

It was now a question of when.

Questions of “Should” vs. Questions of “When”

“The essence of strategy is choosing what not to do.” — Michael Porter

Being clear about what your product will and won’t do is a critical element of product strategy. However, because it is so important, even well-meaning teams can turn almost any feature into an existential debate.

Thinking backwards can help differentiate questions of “should” from questions of “when,” and that can be incredibly productive in moving the discussion to prioritization.

This is not intended to be dismissive of questions of prioritization. Phasing decisions are some of the most important decisions start ups make. Financing for startups is phased. Small teams can only work on a few projects at a time. Customers can only absorb so many new features at once. As a result, prioritization decisions are incredibly difficult to make.

Greedy algorithms are very good, but can be traps if you are working against competitors and an ecosystem that is willing to make bets that lie across the gap from your product’s current local maximum. Thinking backwards can help illuminate long term goals that are across the gap.

When you are building a product roadmap, and get stuck on debates about a short term feature that doesn’t move the numbers, I encourage founders to take a moment and try to solve the maze backwards.

It worked for Jordan, right?

“Every day stuff happens to us. Jobs arise in our lives that we need to get done. Some are little jobs, some are big ones. Some jobs surface unpredictably. Other times we know they’re coming. When we realize we have a job to do, we reach out and pull something into our lives to get the job done.” — Clay Christensen

In the summer of 1993, after declaring computer science as my major, I got my first high paying software development internship. Over that summer Hewlett-Packard paid me over $5,000, which seemed like an unbelievable amount at the time.

Unfortunately, like a lot of people, I was so excited by receiving this windfall that I promptly spent it. By Thanksgiving, I was shocked to find that my bank account was nearly empty. All that money, gone. It literally sickened me.

That was the moment when I decided to learn as much as I could about personal finance and I got religious about saving.

The Theory of Jobs to Be Done

For a lot of people, there is a moment they can recall when they consciously decided that they wanted to start saving.

When I attended Harvard Business School at the end of the dot-com era, I was incredibly fortunate to spend time with Clay Christensen, who at the time had just recently published the now famous book, The Innovator’s Dilemma. In his class, we studied his new theory of disruption, and how industrial giants filled with smart people would make seemingly smart decisions that would lead to their downfall.

One aspect of his theory, which later went into his book, Competing Against Luck, is the Theory of Jobs to Be Done. Quite simply, Clay believes that companies can go astray by focusing too much on the data about their customers and the features of their product. Instead, he argues they should focus on the end-to-end experience of the job that their product is being hired to do.

In the past few years, I’ve come to believe that saving is a job that a huge number of people want a product to help them do and help them do it well.

Saving Itself is a Goal

Our lives are filled with a large number of small financial decisions and problems, but there are only a few very large financial moments that warrant the creation of an entire companies to support. Spending, borrowing, investing and financial advice all certainly fit that description. I believe that saving belongs on that list as well.

Americans are in a terrible state when it comes to saving. 6 in 10 Americans don’t have $500 in savings. An estimated 66% of households have zero dollars saved. If you are cynical about small, one-off surveys, The Federal Reserve itself estimated in 2015 that 47% of households didn’t have the means to cover a $400 emergency expense.

Saving is a huge problem, so it isn’t really surprising that tens of millions of Americans seem to be looking for something to help them save. Enter Acorns.

Hiring Acorns

Over the past two years, it has been astounding to watch Acorns grow. An elegantly simple product, designed from the ground up for a mobile generation, Acorns has grown to over 2 million accounts in less than three years. In the first half of 2017 alone, Acorns added over 600,000 new customers. Their overall mission is to look after the financial best interest of the up-and-coming, something I personally care deeply about.

It isn’t really surprising to see why so many Americans have decided to use Acorns to help them save. 75% of Americans have a household income under $100K. Acorns simple features like Round Ups automate the process of making sure that as you spend, you save. Acorns has now performed over 637 million round-up transactions for their customers – each one an action designed to help people save more. I believe that on any given day, thousands of people decide to hire a product to help them save, and increasingly they are hiring Acorns.

When I met the founders of Acorns two years ago, we immediately connected over the common ground between their culture and Wealthfront’s (the company I was running at the time.) They are very different services, focused on different problems and audiences, but with a shared belief in the power of automation. This is a company worth supporting, and I feel fortunate to serve on their Board of Directors.

At a time when people continue to grow more and more frustrated with the solutions offered by incumbent banks and brokerages, I continue to be excited about the opportunities for new products that are built around automation and world-class software design.  As an industry, we can and should radically improve the financial solutions that are available to everyone. Acorns is proving that saving is a job worth doing.

I’m writing this post with a bit of trepidation, because talking about Silicon Valley home prices these days is a bit dicey. The surge of the last five years has been shocking, and almost no one I know feels good about how difficult it is for people to buy a new home in Silicon Valley in 2017. Some houses are pretty bad but others arae actually at a reasonable price, because they come with furniture and some even come with shutters from plantation shutters installation Sydney. They are actually really good quality.

So if you need a trigger warning, this is it. Stop reading now.

The truth is, as shocking as the rise in Silicon Valley home prices has been, there has also been an asset boom in other dimensions as well. Total compensation for engineers is up considerably and stock prices at the big tech companies continue to rise.

To visualize this, I thought I’d put together a few charts based on real market data. As a proxy for Silicon Valley, I pulled the last 5 years of home prices from Zillow, and monthly stock price data from Yahoo.

Palo Alto Home Prices

Two days ago, the Mercury News reported that a home in Palo Alto sold for $30 million.  A quick check on Zillow seems to confirm this.

I chose Palo Alto as a proxy for Silicon Valley home prices because it is historically “ground zero” for Silicon Valley tech companies, and it has relatively close proximity to all of the massive tech giants (Apple, Google, Facebook).

I picked June 2012 – June 2017, not only because it is roughly five years, but also it also happens to mirror the time that Facebook has spent as a public company. For many in the local real estate market or online sites as SafeguardProperty.com, correctly or incorrectly, the Facebook IPO still looms as a transformational event.

As you can see, in June 2012 the average Palo Alto home cost $1.38 million. Five years later, the estimate for June 2017 is up 84.6% to $2.55 million.

Apple (AAPL)

Apple is the most valuable company in the world, as measured either by market capitalization ($810B as of 6/7/2017) or by profitability ($45.7B in 2016).  Thanks in part to this exception financial performance, Apple stock (AAPL) has risen 84.5% in the last five years, from $83.43 per share to $153.93 per share.

84.5%? Where have I heard that number before?

That’s right, the increase in Apple stock over the last five years is almost exactly the same increase as the average home price in Palo Alto over the same time period.

In June 2012, it took 16,555 shares of Apple stock to purchase the average Palo Alto home. In June 2017, it took 16,566 shares. (Of course, with dividends, you’re actually doing a little better if you are a shareholder.)

If you look at the chart, the pink line shows clearly the large rise in price for the average Palo Alto home. The blue line is the number of AAPL shares it would take to by the average Palo Alto home in that month. As you can see, AAPL stock is volatile, but five years later, that ratio has ended up in almost the exact same place.

Alphabet / Google (GOOG)

Alphabet, the company formerly known as Google, may not be as large as Apple in market capitalization ($686B), but it has seen far more share appreciation in the past five years. Since June 2012, Alphabet has seen its stock price rise 240.4%, from $288.95 in June 2012 to $983.66 per share.

What does this mean? Well, it means that if you have been fortunate enough to hold Google equity, the rise in Palo Alto home prices doesn’t look as ominous. It took 4,780 shares of Google to purchase the average Palo Alto home in June 2012, but it only took 2,592 to purchase the average Palo Alto home in June 2017.

Facebook (FB)

Facebook, the youngest of the massive tech giants, already has one of the largest market capitalizations in the world. As of today, Facebook is valued at $443B. Facebook stock has risen 394% in the past five years, from $31.10 in June 2012 to $153.63 in June 2017.

To state the obvious, it has been a good five years for owners of Facebook stock. Not many assets could make owning Palo Alto real estate look slow, but 394% growth in five years is unbelievable. In June 2012, you would have needed 44,412 shares to buy the average Palo Alto home. In June 2017, that number had dropped significantly to just 16,598 shares.

Bitcoin (BTC)

While I realize that Bitcoin is not a stock, the original idea for this post came from a joke I made on Twitter recently given all of the buzz about Bitcoin, Ethereum and ICOs over the past few weeks.

I couldn’t resist running the numbers.

For the small number of readers of this blog that haven’t been following the price of Bitcoin, the increase in value over the past five years has been unbelievable.The total value of all Bitcoin outstanding is currently about $44.5B. Since June 2012, Bitcoin has risen approximately 4,257%, from $6.70 per Bitcoin to a current value of $2,858.90.

You can see why there has been so much buzz.

In June of 2012, it would have taken 260,149 Bitcoin to buy the average home in Palo Alto. In June of 2017, that number is now down to 892.

Needless to say, anyone who sold Bitcoin to buy a house in 2012 is likely not loving these numbers. But to people who have held Bitcoin for the past five years, Palo Alto is looking cheaper by the day.

Silicon Valley Is Seeing Significant Asset Inflation

To be clear, I’m not attempting to attribute causality to these charts. I believe the real driver of home prices in Silicon Valley is the lack of sufficient building of new supply at pace with the economy, combined with a significant increase in compensation for technology employees and historically low interest rates.

But the fact is, if you are fortunate enough to have equity in one of the tech giants (or in Bitcoin), houses might actually be looking cheaper now relatively than they did five years ago.

I always find it enlightening to look at real data and compare it to intuition. Hope you find this data and these charts as interesting as I did.

This is an unusual step for me, as it is the first time in my twenty-year career that I’ve decided to come back to a firm. Then again, Greylock is an unusual firm.

When I look around Greylock, I recall Warren Buffett’s famous advice* on what to look for in people:

“Somebody once said that in looking for people to hire, you look for three qualities: integrity, intelligence, and energy. And if you don’t have the first, the other two will kill you.”

Early in my time at LinkedIn, I remember Reid Hoffman modifying this a bit:

“You really want to look for people who are smart, trustworthy, and ambitious. Having just two of the three is a problem.”

Deciding who you want work with is one of the most important decisions that you make in your career. Not to embarrass John Lilly, but I think his advice from the New York Times is spot-on:

“…find your tribe. You should look around and figure out whose team you’re on and whose team you’re not on. And for the people whose team you want to be on, you need to invest in those relationships and treat them well and spend time with them.”

When I look around Greylock, I see nothing but people who are smart, ambitious, and trustworthy; people whose team I want to be on. I can’t think of a better environment for me as I explore and look for the next big thing.**

(*) If you are interested in the history of this flavor of advice, this post on Quote Investigator is fascinating. Goes back more than a hundred years to a German General named Kurt von Hammerstein-Equord.

(**) Might be time to re-read my Executive in Residence series from 2012…

]]> https://adamnash.blog/2017/05/17/back-at-greylock/feed/ 1 2888 adamnash https://adamnash.blog/2017/05/02/spend-time-thinking-about-the-people-who-dont-use-your-product/ https://adamnash.blog/2017/05/02/spend-time-thinking-about-the-people-who-dont-use-your-product/#comments Tue, 02 May 2017 21:42:15 +0000 http://blog.adamnash.com/?p=2763 Continue reading Spend Time Thinking About The People Who Don’t Use Your Product]]>

This is an extension to my original three post series on user acquisition.

Today, AirBnB announced that it had reached a settlement with the city of San Francisco on how to effectively register and monitor legal listings in the city. I am a huge fan of the company, and it seems like a positive outcome for both San Francisco and AirBnB.

For many, the issues around many of the sharing economy companies, including AirBnB, are examples of regulators trying to find a way to both control and incorporate rapid, disruptive innovation.  There is, of course, some truth to this point of view.

However, as a product leader, there is another important takeaway that seems to be too often forgotten. Most of us spend too little time thinking carefully about the people who don’t use our products. 

The people who don’t use your product often won’t show up in your core metrics. But if you don’t spend time understanding them, you will eventually feel the negative effects in your growth and your brand.

It’s Natural for Companies to Obsess About Their Users

When a startup launches a new product, it is natural to obsess with every user it touches. Every click, every tap, every piece of data is precious feedback about your features. The data is one of the most objective sources of information about what your users are doing with your product and when they are doing it. In the early days, before finding product/market fit, a huge amount of time tends to be spent on the people you touch but who don’t convert. In fact, that may be where most people at the company spend their time.

As consumer products find product/market fit and hit escape velocity, more and more engineers and designers spend a disproportionate amount of time on users. The people who work on growth & marketing will still often continue to look at the data on leads, trying to find ways of converting those non-users to users. However, as a percentage of the company, fewer and fewer engineers, designers & product managers will be looking at data from non-users.

This makes sense, of course, because as your product grows, almost all feature development is focused on your users. In 2008, when we established the Growth team at LinkedIn, we discovered that of the hundreds of features on linkedin.com, only three features reliably touched non-users. (For those of you who are curious, those features were the guest invitation (email), the public homepage (linkedin.com), and the public profile (in search.))

Customer obsession, of course, is generally a good thing. But as we learned at LinkedIn, if you want to grow a viral product, you have to spend a considerable amount of time thinking about the non-user, where they touch your brand and your service, and find ways to both reach them and convert them to users.

You Have More Non-Users Than Users

Few brands and products could ever claim that their conversion rate for everyone they touch is over 50%. It is even possible that Facebook, with nearly 2 billion users, still has more people in the world who have heard of the company than who use it.

In 2011, I remember talking to the great founders at CardMunch about a new email they were proposing to add to their service. CardMunch was a wonderful app that made it effortless to scan a business card and then have it automatically entered into your address book, with almost no errors. The proposal was to add an email so that the person whose business card you scanned (non-user) received an email from the CardMunch user with their business card in electronic form.

The team was ready to whip something together quickly and test the idea, and the concept was good in principle. But given some of the experience of Plaxo a decade before, it was prudent to ask the simple question: “How many people will see this new email?” Within a few minutes, we figured out that the number of people who would receive this email within the first three months would be 30 to 50 times the total user base of the application.

Some of you are probably thinking, “sounds like a great growth feature!” Others are likely venting about why we have so many emails cluttering our inboxes. Both reactions are fair.

The guidance I gave the team, however, was to consider the fact that, once they launch this feature, most people who have ever heard of CardMunch will have only heard of it through this email. The product and the brand. I asked them to spend a bit more time on the design on the email, in that context, to ensure that all of their hard work on a wonderful product wouldn’t be drowned in an avalanche of poor experience.

In the end, Sid Viswanathan & team did a great job brainstorming ways that they could show the value of a connected addressbook in the email, including LinkedIn features like people you know in common. Once framed properly, it was simple to think about what they wanted non-users to think about their brand and their product.

Non-Users Matter

Marketers, of course, have known this for decades. It is a brand marketing staple that it takes at least three touches of a brand before it will stick with a potential customer.

Somewhere along the way, software companies lost touch with the basic idea that every piece of content that contains their brand is a potential touch. It is not just the users of the core product that matter for long term growth.

Market research and customer development are often essential for discovering and understanding new potential users for your product. The case can be made that viral systems can, in fact, spread to these new pockets automatically. However, truly viral products are few and far between, and in most cases these new markets will not be in the data sets that your product & engineering teams are focused on.

Brand will also impact your company well beyond new user acquisition. With AirBnB, we now know the many ways in which their service and brand touch non-users. Neighbors, for example, have natural questions and concerns when a house or a unit near by is available on the platform.

Software companies, especially successful ones, tend to have passionate and talented designers and product leaders who are eager to find clever solutions to real user problems. Given the right data and focus, there is no question that these teams can also design and build features that address non-user concerns.

Tesla spends time thinking both about the feeling a driver has in the car, as well as the experience of a non-Tesla owner who is watching that car drive by.

Spend more time thinking about all of the people who touch your product & your brand, not just your users.

A few years ago, I wrote a few posts to outline the requirements for exceptional product leadership:

• In “Be a Great Product Leader,” I focused on three key responsibilities: strategy, prioritization & execution.
• In “Great Product Leaders Win Games,” I focused on deliverables in the first two weeks, two months, and two quarters when hiring a new product manager.
• In “Three Feature Buckets,” I focused on a bucket-based approach to product feature prioritization.

While I have been gratified that people continue to find utility and value in these posts, I’ve come to believe that product leadership, particularly the issue of prioritization and phasing of a product roadmap, remains daunting and challenging for most teams.

In particular, the need for organizational scalability and speed of innovation has driven the widespread popularity of small, independent teams building product and features. Unfortunately, the side effect of the explosion of small teams has also amplified user-experience fragmentation and the haphazard quality of many web-based and mobile software applications.

As a result, I’ve come to believe that there are two facets of  product leadership that have become increasingly important for delivering a high quality product experience: curation & editorial.

Curation Amplifies Your Product Experience

Around 2014, I remember first being struck by a product management job description at Pinterest which incorporated the concept of curation as a core responsibility of product management.

The dilemma of product prioritization is always simple to understand: most software teams, filled with talented people, have more ideas for great features that the capability to execute. As a result, there has to be some process for filtering down the ideas to answer the question of “what do we build next?”

Prioritization on metrics, customer requests and delight is not hard to operationalize, but it still leaves open critical questions:

• How does the product & experience come together for the user after we ship?
• How does the product communicate the changes to the customer in way they can easily understand and utilize?

I believe curation is the key to answering these questions.

Curation is an under-appreciated skill in software design. In the world of art, curation is a critical and valued function. A curator ensures that the pieces of art not only combine to amplify each other collectively, but also gives thought to the experience a viewer will have when engaging with the collection.

Users need some level of coherence in new versions of your product. With proper curation, features and changes amplify each other, and lead to a greater customer appreciation of your efforts through a product experience that is more coherent and easier to communicate.

Without curation, software feature prioritization tends to devolve purely into the line-item value of a given feature, rather than how it fits in general with the whole product, or the product release. Great curators won’t think twice about cutting a piece that doesn’t fit the theme of the show, even if it is exceptional.

Designers, not surprisingly, tend to intrinsically understand the value of curation, and valiantly attempt to connect features together into a coherent product experience. Unfortunately, they often are forced to incorporate together a hodge-podge of features that have been prioritized independently by different small teams.

This is not an argument against constant enhancement and iteration of code, or the constant shipping of bug fixes and small feature enhancements. But for user-facing features, teams need to be wiling to hear from product leadership that a great idea for a new feature is not enough to qualify it for immediate prioritization. Customers cannot endlessly absorb a haphazard array of changes and feature enhancements. The perceived quality of the product drops, and customers fail to perceive the value in the features that are shipped.

Every Creator Needs an Editor

Understanding the value of editorial comes easily to professionals who have worked in content & design.

In my experience, many otherwise talented engineers and product managers balk at receiving critical review of their work. Sure, most software engineers understand the value of pair programming and code reviews. But for some reason, when it comes to overall feature design, the sentiment almost always shifts to stubborn independence.

Unfortunately, just like in writing, having a great editor is essential for the overall quality  and consistency of the finished work.

Even the best writers benefit from having a great editor. J.K. Rowling may have written all seven Harry Potter books herself, but she had a team of editors ensuring everything from line level quality to the plot consistency of the overall series.

Why editors? In general, editors provide three levels of assistance to writers: proofreading (spelling, punctuation, grammar), copy-editing (phrasing, style), and developmental-editing (plot, character development, pacing, tone, and effectiveness.)

Most writers at first balk at the idea of an editor. They are professionals, after all, and incredibly skilled. Why do they need someone in between them and their readers?

The answer is two-fold: first, editors provide a more objective “second-pair of eyes” not affected by the sunk cost and confirmation bias inherent in any creative process, and second they are typically individuals who are exceptionally talented at finding errors and issues that will be perceived by the target audience.

The same applies to software products.

Even exceptionally talented engineers & designers become blind to their own work. While each function can have their own version of an editorial process, my experience has been that if product leadership doesn’t actively engage in the editorial process, the quality and the coherence of the product suffers.

Product Leaders as Curators & Editors

Most software companies have moved to a bottoms-up, distributed organization process for their engineering, design & product teams. Amazon, of course, is famous for their two-pizza team concept. As a result, the need for curation and editorial to keep the product experience coherent has become critical.

If you look critically at organizations that have a distributed culture, but still ship high quality product experiences, you’ll find that there is an accepted culture of curation & editorial in their product process, connecting all the way to the CEO.

If you are a product leader, think carefully about how you can incorporate curation & editorial into your process as you scale.

In 2016, voice-based interfaces exploded into the imagination of the startup community as a potential new consumer platform. Amazon deserves much of the credit for this radical shift, as the Amazon Echo seemed to jump the chasm from early adopters to a more mainstream market. Of course, voice has been a hot topic now for years, as Apple & Google both leveraged their ubiquitous mobile platforms to launch Siri & Google Now, and Microsoft & Amazon have demonstrated incredible technical progress with Cortana & Alexa.

Unfortunately, as the excitement around voice shifts into practical execution, there is an uncomfortable consensus growing that there is something amiss with these new conversational platforms. The issue? The engagement numbers just aren’t as strong as expected, or even as strong as engagement numbers for traditional web or app-based interactions. One of the biggest issues? Retention.

I believe the issue is real, and will be a persistent problem for developers and designers looking to create the next generation of conversational interfaces. But if I had to give one piece of advice to those creative professionals, it would be this:

Deliver trampoline moments.

Lessons from PullString

Over the past four years, I’ve had the incredible opportunity to be an investor and board member at PullString, headed by Oren Jacob, the former CTO of Pixar. This company set out with the audacious goal of reimagining conversational interfaces designed for entertainment, rather than for utility. With a bit of that unique Pixar magic, this incredible team believed in two things that even to this day seem quite at odds with the conventional wisdom of Silicon Valley:

1. Conversation is a fundamentally new medium for creative content, and would expand beyond the pure utility of a search engine interface to a platform for engagement & entertainment.
2. A platform to deliver truly engaging entertainment through conversation would require the combination of both technical and creative contributors to the content creation process.

Over the past few years, Pullstring has delivered a wide range of industry-firsts for voice-based engagement for a wide variety of audiences, ranging from young children to adults. Large brands, like Activision’s Call of Duty, Disney’s Marvel and Mattel’s Barbie trust Pullstring’s platform because of its unparalleled scalability and its unique ability to integrate content from creative professionals with expertise in sound, voice, character and dialogue. Even Amazon counts on Pullstring when they want to deliver high quality conversational content.

However, one of the key insights about conversational engagement came early on, during one of their rigorous rounds of user testing & prototyping. After session after session with children, who would use, but not deeply engage with a conversational application, they found it. A trampoline moment.  

Child: Hey

Pullstring: Quick! Name three things you like that are outside.

Child: I think please I’m Chris taxes and jumping on trampolines

Pullstring: W-w-w-w-w-w-wait…you mean like, a real trampoline?

Child: Yeah

Pullstring: Do you think I could go on it sometime? I’ve been using your bed up until now and I think the springs are worn out…

Child: Are you really able to

Pullstring: My oh my, what a day I’ve had…It was so strenuous I can barely remember what I did…Ellington? What have we got in the log?

Pullstring: Right. We sat on the bed. Ellington needed a little rest time from our usual forays.

A couple things you’ll note here:

1. Speech recognition for children’s speech was very imprecise at the time. The text is not actually what the child said, but the text fed back from the best speech recognition engine of that time.
2. The child’s willingness to “believe” in Winston (the virtual character, with his friend Ellington) changes dramatically when he demonstrates active listening around one of her favorite things, the trampoline.

This session went on not just for a minute, not just ten minutes, but over 30 minutes. The child had clearly decided to engage, and continued to engage, despite a huge number of imperfections in the interaction.

Why? The trampoline moment.

Turing Test or Trampoline Moment?

For decades, the high bar in artificial intelligence has been the Turing Test, invented by Alan Turing in 1950. The test was fairly simple: an evaluator (human) would have a conversation with two entities, one human and one artificial. If the evaluator could not reliably tell the human from the computer, the machine would “pass” the test.

While there are a number of criticisms of the Turing Test, there is no question that it has profoundly affected the way many evaluate machine-generated conversation.

The insight from the trampoline moment was different, and takes more of its heritage from the world of fiction. The question can be reframed not whether or not the consumer believes the character is human, but instead are they willing to suspend their disbelief long enough to immerse themselves in the experience.

Most people don’t believe that Iron Man is real, or that they are witnessing an accurate portrayal of Alexander Hamilton. They know that the actors in their favorite romantic comedy aren’t really in love, and they forgive plot holes and shallow character development. Even highly critical audiences of science fiction often can and will forgive obvious scientific flaws in the technology presented. (Well, not all of them)

The magic is really in the suspension of disbelief: the willingness to suspend your own critical faculties and believe the unbelievable; the willingness to sacrifice logic for the sake of enjoyment.

Is it really surprising that a critical insight to human engagement might stem from the arts, where creative geniuses have spent thousands of years attempting to engage and entertain notoriously fickle humans?

Focus on Trampoline Moments, not Intelligence

The progress in artificial intelligence, voice recognition and conversational interfaces has been astounding in the past few years. There is no question that these technologies will reshape almost every facet of our economy and daily lives in the coming decade.

That being said, in Silicon Valley, it is sometimes too easy to focus on the hardest technical problem, rather than the one that will bring the consumer the most delight.

The reason Pullstring spends time talking about finding “trampoline moments” is likely the same reason talented product leaders talk about finding “magic moments” in their product experience. If you can connect with your customer emotionally, you will inevitably find that engagement and retention increase.

Trigger their suspension of disbelief. Find your trampoline moments.