In the Northern Hemisphere, it’s that time of the year. First day of school pictures, backpacks full of books versus hiking and beach gear, and a flurry of back-to-school sales. Fall of 2023 is also the first year we have a bit of an organized response to the availability of generative AI -- AI trained on massive datasets of prior work and information that then can create new work when we “prompt” it. While you might get away with last year’s outfits this Fall, you cannot ignore how AI is changing education.

Spring 2023: Students 1, Teachers ??

As schools let out last spring, many students had more AI expertise than their teachers. Not surprising as one of the easiest things to do with generative AIs like ChatGPT, Bing, or Claude 2 is to generate text in response to prompts. Much homework in the past was a prompt (to a student) to generate text. Easy 1:1 swap of effort from person to AI. 

Schools and teachers hadn’t had time to prepare new assignments. Teachers and parents had little time to think about updating expectations and values around what is and isn’t cheating. None of us, even today, have had much time to consider the huge shift in what work is most valuable and important for people to do versus outsourcing to tools. (I argue for “owning” your own tools.)

Some of these questions were first asked as Wikipedia… or take a step back, calculators, came on the scene. But this year, it’s different. Generative AI can do much of our (and our students’) work.

What We Need to Think About - And Where to Take Action

Teachers open class this Fall after a summer of whirlwind catch-up. How do we support students' development in a world filled with an exploding number of AI tools? I’ve never heard a teacher asking for spell-checking to be turned off, but whole school districts have banned (tried to ban?) AI. 

High-Level Evaluations

AI in education is a global topic. I’ve scanned a variety of reports (UNESCO’s report is 418 pages, scanning is the best I can do) and will share a few insights here. The May 2023 US Office of Education’s Artificial Intelligence and the Future of Teaching and Learning: Insights and Recommendations offers much to cherry-pick:

Some headings:

• A Duality: Learning With and About AI

• A Challenge: Systems Thinking About AI in Education

• Preparing and Supporting Teachers in Planning and Reflecting

These resonate with me, given my focus on Thinking in 5T as we build any kind of human, social, or technological system.

Specifics

The report also suggests possible benefits from leveraging AI in education: “Personalized learning, project-based learning, learning from visualizations, simulations, and virtual reality, as well as learning across school, community, and familial settings.” These are generally approaches we know are valuable, but given limited resources, hard to do. AI may change some of this calculus.

When asked how my courses are changing, I highlight that I can ask the students (all working professionals) to do more as they apply our course concepts to their work settings. I can also expect higher quality. I describe the value of AI as offering them an intern. Yes, having an intern has costs and benefits, but you both get an extra set of “hands” and a chance to be in a teaching role. Both are great opportunities for performance and deeper learning.

The 2023 US Department of Education report draws on their 2017 report (AI mentioned once then) to offer learning goals and considerations on how technology can be supportive. They say:

1. Enabling Enhanced Question Types: to give students more ways to show what they know and can do.

2. Measurement of Complex Competencies: to better elicit growth in important skills that go beyond typical subject matter standards, for example, in measuring practices, social skills like teamwork, self-regulation, and work-relevant skills (e.g., making presentations or leading teams).

3. Providing Real-Time Feedback: to maintain and increase student engagement and to support effective learning, providing timely and helpful responses and suggestions to each learner.

4. Increasing Accessibility: to include neurodiverse learners and to engage learners’ best communication capabilities as they share what they know and can do.

5. Adapting to Learner Ability and Knowledge: to make assessments more precise and efficient.

6. Embedded Assessment in the Learning Process: to emphasize an assessment’s role in improving teaching and learning

7. Assess for Ongoing Learning: to reveal progress over time and not just predetermined milestones.”

2023-2024: Our First Year of Experimentation

Governments and non-governmental organizations took until the summer to get us to their assessment and recommendations. We should see this year as one of experimentation. AI offers us new tools and questions in a way that changes -- and will keep changing -- daily. 

How to Help

If you’re reading this, you are in one of my top two categories -- I’m not worried about you:

1. People who spent the summer trying out new tools and thinking about how to get value from them

2. People who were listening when others talked about their AI experiments

3. People who think they can ignore the latest batch of AI like they did blockchain and TikTok -- these are the folks we all need to be supporting

It’s a Process

As with any change, we need to stop-look-listen, and mix together a version of education and work where our talent, technology, and technique fit our targets and our times (Think in 5T). Then we need to share the results with others. As you see helpful ideas and examples, share them with your network. That’s the easy one. Include people with more and less technology experience and understanding. 

Talk with kids, teachers, and school administrators, but most importantly, figure out how to use AI in your own work. AI is too important a change to get behind. Share your understanding and ideas with your children, family, friends, and colleagues. 

If You Need Help to Get Started

Follow Professor Ethan Mollick:

• The Homework Apocalypse

• Assigning AI: Seven Ways of Using AI in Class

• Using AI to Implement Effective Teaching Strategies in Classrooms: Five Strategies, Including Prompts

Tryout Some of My Strategies

• Show and share your work process. See an example here.

• Use one coffee break a week to look back over the available tools. They change daily. Did you know you can use Microsoft’s Bing bot in Chrome? I didn’t until today.

1984-2024

Welcome to a school year to remember. I know personal computers were available before the 1984 Apple Mac Commerical, but that’s the date I use to think about computers being in wide public use. Here we are 40 years later. How will we look back on this year? 

For example, I went through IBM’s Augmented work for an automated, AI-driven world report today. The authors, Jill Goldstein, Bill Lobig, Cathy Fillare, and Christopher Nowak note, “A recent IBM Institute for Business Value (IBM IBV) survey found that 4 in 5 executives say generative AI will change employee roles and skills. But only 28% of CEOs in our 2023 CEO Study have assessed the potential impact of generative AI on their current workforce” [emphasis added].

In March, a colleague asked me if AI would be another case of the rich getting richer. I came to see her point, but now I’m equally worried that it’s a situation where not being early in adoption with AI is a bigger risk than with other new technologies. People who have been successful as late adopters may not fare as well with a wait-and-see strategy regarding AI and their jobs or AI and their business models. 

As an educator, it’s my job to help people decide what to pay attention to. You may also be inclined to help others make these assessments.

Two Calls to Action

1. As you see helpful ideas and examples, share them with your network. That’s the easy one. Your ecosystem is likely already sharing and using one another as backboards for your thinking. 

2. More importantly: Share with at least one person you believe is a step behind your own thinking. This could be a friend, a relative with a small business, or someone with a successful middle or executive management role. You may have heard them acknowledge AI but say they haven’t had time to try. Or maybe they tried a tool like ChatGPT in the new year but didn’t see the connection to their work. Have a stop-look-listen AI moment with this friend, relative, or colleague. 

Resources for Your Lucky Friend and You

Overview

While the IBM report I mentioned earlier is primarily survey-based, the breadth and depth give us much to consider. (I’m always searching for assessments with objective processes and performance data -- thank you for sharing examples in the comments below.) The authors highlight three priorities for augmenting work:

– Transform traditional processes, job roles, and organizational structures to boost productivity and enable new business and operating models.

– Build human-machine partnerships that enhance value creation and employee engagement.

– Invest in technology that lets people focus on higher value tasks and drives revenue growth.

Broad-ranging reports like this IBM one can be great motivators. Then we need action. More from the IBM report:

The human-machine partnerships that will drive advantage tomorrow are being developed today. That means workers need to be willing to experiment with new approaches to understand what works—and tech-savvy enough to troubleshoot along the way.

Work Crafting

My colleagues and I have done some deep dives on how we can leverage AI as we craft/recraft our work. The quote above points to experimentation. IBM and recent books by Prof. Amy Edmondson, and Profs. Michael Luca and Max Bazerman highlight that experiments don’t always work -- failure is part of the learning. Manage the process with lightweight experiments such that the risks are appropriate for the gains. What’s important is that we look for new approaches to our work, given the pace of change across our tools and environments.

The Stop-Look-Listen Process 

Drawing from my 2012 book, The Plugged-In Manager:

• Stop to see how things are going.

• Look to see what opportunities you have. Span the 5Ts of Talent, Technology, Technique, aligned to your Target and Times. Track sites and newsletters highlighting and reviewing new tools and approaches appropriate for your work. Make a change, and…

• Listen to the result both in your area of influence and beyond. Return to the first step, Stop. 

Depending on your goals, the pace of change in your organization, and the pace of technological evolution in your work, this process could be something you do every Tuesday or every second Tuesday (for example). Given the pace of AI today, I feel like I need to do a stop-look-listen every morning.

A Bridge to Opportunities

Whether you’re championing your own projects, extending a hand to a friend, colleague, or relative, or steering your entire organization through these tumultuous times, embrace adaptability. Think of it as building bridges to keep your paths open and be willing to reinforce and reconstruct your bridges as conditions change.

Friends of mine have recently formed a new consulting venture, Pontem Advisors. They chose “Pontem” (Latin for bridge) because they assist organizations in "bridging the gap between company business understanding, goals, and behaviors….” I see the significance of their methodology across organizations at every phase of digital transformation.

We must stop-look-listen at each step and cross bridges to new opportunities. Help yourself, and a colleague, take the time to test a new direction with AI and their work.

Resources to Help You Leverage AI In Your Work

• Futurepedia: “The Largest AI Tools Directory, Updated Daily”

• FutureTools: "FutureTools Collects & Organizes All The Best AI Tools So YOU Too Can Become Superhuman!"

• One Useful Thing: Prof. Ethan Mollick’s Substack

• Dr. Alexandra Samuel’s work across LinkedIn, the Wall Street Journal, and more

• Discussions (human-to-human or online) within your organization about what your colleagues find useful.

• Suggestions from the AI — either across or focused on the specific platform. For example:

  • Asking ChatGPT: “What's a good prompt to use for MidJourney if I need an image of AI code wrapping around the world?” As I write, ChatGPT has internet access blocked, so it’s not aware of MidJourney — but it still writes a good prompt. Give it a try!

  • General searches for capabilities and finding articles offering options. For example, Discord AI Art Generator: 7 Best Servers to Use by Mercie Mwikali

Ode to a Beautiful Search Tool

Click on the image below to look at our now “old school” (but beautiful) AI search tool. Mobile users may have a better experience here. Spring 2023 was our last update, as the search engines and AI now do a better job. Our human efforts will focus on finding new ways to craft our work with these tools.

Taking a Step Back to Build a Foundation

Does having access to all these tools seem like putting the cart in front of the horse? Take a look at this earlier discussion that Utpal Mangla (IBM) and I put together. We talk about how organization leadership can bring in top-down automation, but how all of us can address bottom-up automation in our work (and lives). Much of that conversation started through our work with ISSIP (The International Society of Service Innovation Professionals). We are honored to be the current (Utpal) and past (me) presidents of that organization. Join us — for the ISSIP upcoming Discovery Summit on Tech for Good.

Automation is part of our work. The question is whether we are finding the tools to augment our abilities or waiting for our organizations to decide what to automate and who to replace. Research finds that people who craft their work are more productive and employable. In this earlier post with Brett Li of Tonkean, we talk about that research and the steps you can take to craft your work. But what tools can help us?

Bottom-Up Automation Tools

Here is the Spring 2023 quarterly update of our database of personal automation tools! Nitish Gupta and I collect tools that leverage artificial intelligence (broadly defined) to support work. You likely use some of these tools already (e.g., GMail’s autocomplete). We hope you also find many valuable new tools within our mix. There are thousands of news tools given the generative AI explosion. Here are 200+ of our curated selections. Our criteria include these tools are:

• for work (again, broadly defined) - generally, not lifestyle. That said, many will help across your work and leisure.

• that individuals or teams can integrate into their work without organizational support. (Many powerful tools for automation would connect directly into an organization’s systems - these are better taken on as top-down and bottom-up efforts.

• leveraging automation either internally (e.g., machine learning or other artificial intelligence) or as part of a process connecting to AI tools (e.g., IFTTT).

Click on the image below to have a look. Mobile users may have a better experience here.

This Quarter

We added over 20 new tools this quarter. New/split categories include: Creative Suite, Research Support, and Code Generator.

What’s Next?

We update the list quarterly. Ironically, for now, this is a hand-crafted process. As we looked at earlier lists of automations for personal use, we found many were out of date. Tools may come and go, change names, are rolled into other services, and the like. We will use automation to check our links each quarter and add new tools as we find them — or as you suggest them in the comments ⇓ below ⇓.

Realities are barging in on my euphoria about Microsoft 365 Copilot. After a day of sharing shorter and longer versions of the Microsoft announcement, I’m starting to track my questions and those I hear from others.

Business Chat works across the LLM, the Microsoft 365 apps, and your data—your calendar, emails, chats, documents, meetings, and contacts—to do things you’ve never been able to do before. You can give it natural language prompts like “tell my team how we updated the product strategy” and it will generate a status update based on the morning’s meetings, emails, and chat threads.

I have no doubt (and even have placed bets) that our work will transform in the months and years after its release. (Still months away if you’re not in their preview group of 20 companies). Already I’m dealing with frustrations as I can’t bring myself to work on a Powerpoint deck without the flashy support of Copilot.

Deeper Considerations

My colleague, Prof. Mila Lazarova, wondered if this would be another case of the rich getting richer. I waved off her concerns by saying Copilot was part of 365. Another colleague, Prof. Matt Beane had just tweeted that 345 million people use Microsoft 365. That’s a broad base. However, a text from author Phil Simon about premium features sent me back to the announcement document.

Pricing reared its ugly head.

I hope that Copilot won’t be an upcharge beyond the basic 365 pricing. Given all the enterprise language in the announcement document, I also hope that personal and family accounts get the magic too. For years, I’ve asked for my personal “graph” to be leveraged to improve my work (albeit generally in the context of Google).

My Copilot euphoria is based on the AI ability to leverage the work we’ve already done (our graph) to support the work we need to do.

The power I’m seeing in the Microsoft demos would put knowledge workers without Copilot capabilities at a severe disadvantage. Mila would be right. Already I’m frustrated that only 20 organizations have access. I also expect my organization won’t be first in line for the next wave.

Another fear is that the work history that powers these benefits will be locked within organizational walls. Remember when you couldn’t share collaborative documents or discussions outside your organization’s domain? Yes, security and provisioning will be of huge import - but perhaps a virtuous circle of AI will make it easier to build the walls and bridges we need.

We need to own our own tools.

My biggest fear is about my personal work. Will it be locked inside my organization’s account?

The better our “graph,” the better our work. Own your own tools.

Learn more here: Microsoft 365 Copilot Site

2008

[Appologies for broken links. No copilot to track them down....] Three times in the last week I’ve heard/read about employees owning their own computers – rather than having the company provide them. This harkens back to a world where the identity of a craftsperson was partially determined by his/her tools.

First time was a friend who was switching jobs and going through the start-up costs of a new computer. Decision was finally just to turn in the company-provided laptop and use a personal one. My friend is a world-traveling consultant who needs his personal applications on the road. (Even when companies will allow you to put personal applications on a company machine, problems are created when tech support re-images the drive to do updates and fixes.  You then get to spend hours reinstalling your personal applications.)  Carrying two laptops isn’t an option.  Agreement is that the company will support its applications, owner will support his own.

Second time was on the TWIT podcast (about 54 minutes in) where the panel noted that it’s common for people to have preferences about their tools – e.g., Windows versus Mac, and/or particular applications.  John C. Dvorak noted that when he was a kid working in factories, the master mechanics owned their own tools.  The benefit the TWIT panel ascribed to the firm is that the employer doesn’t have to take on the burden of computer “refreshes” etc., and the employee gets the benefit of controlling their own applications and methods of work.  The conversation then hit on the main reason big enterprise isn’t excited about this: security.  Quick transition to the variety of technology approaches available for solving the security problem.  It can be solved.  Issue is creating safe “virtual machines” that connect to the company network.

Third time was an email summary of the week’s tech/work news from a professional group I belong to.  They linked to Rasha Madkour’s article “B.Y.O.C. (computer) to work - wave of future?”  Citrix (the company highlighted in the article) even provides a $2100 stipend to help employees buy a laptop and support package.  Key to note is that Citrix sells one of the tools that handles the virtualization issues (VMware  also provides a desktop virtualization product). 

Is the third time the charm?  Have we circled back to an age where we will again own the means of our production?

Other organizations that seem to be getting on the bandwagon:

• Microsoft & British Petrolium (see Ina Fied’s Beyond Binary CNET blog)
• Arizona State University (see article by Jennifer Mears of Network World)

How does this change our relationship with our employers?  Do we then become more valuable the better our technology? Do we become more effective given greater control over our tools? Tool ownership might tip the balance for some regarding employee versus contractor status.  (See some checklists here and here.) Note that the desktop isn’t the only tool in the box.  Access to organizational resources stored either on company servers or on company portions of the “cloud” may be where the real work gets done.

Show Your Work

Sharing the provenance of our work adds value at the moment and as you return later to leverage the ideas or make them better. However, we know from Sidney Harris’ famous cartoon of scientists working on a blackboard (“then a miracle occurs”) to math assignments worldwide, showing your work is complicated. 

Hyperlinks give us the ability to share our sources without much distraction. Various in-line academic referencing techniques (APA, MLA, etc.) offer value to insiders as we can translate “DeSanctis & Poole (1994)” in our heads and place the related material in context with decades of research. Footnotes are slightly less distracting, and endnotes push the connections out of sight. 

Yet, even traditional citations don’t tell us how we made the connections. Formal research writing is such that you should be able to replicate the work. Even so, we are in the midst of a replication crisis. Some of that is due to sketchy research. “Lucky” results are another issue. But some of the crisis must be due to limited documentation of the process. When we run an experiment, we don’t always fully describe the room setup, the software versions, or the particular timing -- we used to be better at this.

Space Constraints (Really, Attention Constraints)

I end my January piece in The Conversation: Why using AI tools like ChatGPT in my MBA innovation course is expected and not cheating with "I like an approach some photographers use: share your tools and critical settings." Susannah Schmidt, my editor on that piece, suggested I take the idea further and fully document the approach I used to create the article.

Sharing the process even just as bullet points turned out to be about one-third again the length of the article. No-go, given the word count limit for The Conversation, but here I have all the space in the world. I also respect your time, so I haven’t gone completely overboard in the notes below.

Show Your Work To Add Value

Generative AI and other AI-enabled tools can be of great help. We are all experimenting in these early days of publicly available AI. AI learn, change, and our practices continue to evolve. I expect many of us to reinvent our wheels. 

Yet, learning how to use these tools is difficult without watching someone work through the process. Observable innovations have a greater chance of adding value, but knowledge workers work on their screens, not in public. We must make our experiments visible to learn from our new workflows. How to share the process helpfully for our audiences needs examination. 

A 5T Analysis

When I talk about Thinking in 5T, I think of the interplay across Talent, Technology, and Technique as we work toward a Target and stay aligned with our Times. 

Talent

In the case of AI use for knowledge workers, talent can start with the person experimenting with AI in their work and wanting to share that workflow with others. The first step is to acknowledge that humans are easily distracted. Tracking our process takes us out of our flow. Find a way to document your work automatically so you can lean toward “freewriting.” If you’re a coder, you may have already found a way to have AI create comments in your work (I hesitate to add a link as the best tools will change -- search for something like: “ai adding comments to code.” You likely automated your reference management years back if you are a researcher. Google, Microsoft 365, etc. automate our version control, but not yet in a way we can learn from. (Am I more productive when I outline first? Maybe Microsoft Viva Insights will someday help me know.)

For the talent trying to learn a new workflow, is a video screen capture the way, or is a textual recipe better? I’ll append my recipe for this piece below.

Technology: When an AI Generates the Work

Unfortunately, the major style-guides haven’t caught up to the AI. Some institutions offer stop-gap advice -- Thank you, Seneca and Guelph-Humber. 

The tricky part is that what the AI tells me, it may not tell you… and it may not tell me the same thing twice. Style-guide-wise, this is a bit like referencing personal communications where we can’t explicitly show you our data as it’s private or ethereal. 

Technique: Current Recipe for My Written Work:

• Throwing ideas and references/links into a Google Doc with a draft title

• Both Google autocomplete and paid Grammarly run in the background (just now, I hit the tab key and back turned into background). 

• When the idea gels, rough out the outline. Outlining is iterative as I self-edit (I’m not very good at freewriting), reminding myself about the goal of the post. Create other idea files to save trimmed ideas.

• When stuck on finding the right word, cut the paragraph and paste it into ChatGPT, YouChat, or the paid version of WriteSonic. My attempts at just putting an idea into WriteSonic or Tome have yet to pay off with a good draft. Given its access to all my background work, I expect Microsoft's Copilot will do a better job. Please let the months before my access to Copilot pass quickly….

• I wait until I have a full draft before clicking the Grammarly icon and doing the full proofing pass. (Small concession to the ideas of freewriting.

• Old world -- at the end, I add in full references via Zotero or Paper.li. In the new world, I’m hoping my copilot will suggest the best references as I type… and then, ultimately, write the review section and keep it up-to-date.

• Depending on the final publication venue, I’ll cut and paste the material into its new home. For example, this post went from Google Docs into Squarespace — where Grammarly offered still more (and sometimes, different) suggestions.

The Mix

Each of the talent, technology, and technique dimensions is in flux as I do my work. My understanding of each, and the target and the times, shifts as I go. How we reference our AI support (at least until we have “prompt history”) remains a question. For a recent short article, I happily added a sentence from ChatGPT-4’s review of my draft. Going back to T is for Talent, I wouldn’t cite an editor given today’s norms. I didn’t cite that sentence. I would like “version control” to track and help me improve my work through analytics. Microsoft Viva Insights -- are you listening? Or maybe I should say, Copilot?

[I know I can do a better job on the above paragraph, but I have to move on to another task. Enter ChatGPT-4 (though, why does it so love to say, “In conclusion”?) My prompt: Rewrite this paragraph as a powerful ending to a professional blog post. Other than “In conclusion,” and the florid “the ever-changing landscape,” not bad]:

In conclusion, the ever-changing landscape of talent, technology, and technique continues to reshape the way we approach our work. As our understanding evolves, so does our approach to leveraging AI assistance in our creative process. The implementation of "prompt history" could provide valuable insight and streamline our work with AI like ChatGPT-4. Drawing from the lessons in "T is for Talent," we recognize the importance of adapting to modern norms and finding ways to incorporate AI-generated content seamlessly. The future of work could greatly benefit from enhanced "version control" systems that monitor and improve our output. Microsoft Viva Insights and Copilot, the call is clear – we are ready to embrace the evolution and revolutionize our professional landscape.

Same original paragraph, explicit request for first-person active voice:

As I navigate the dynamic realms of talent, technology, and technique in my work, I continually adapt my understanding to keep pace with ever-changing targets and circumstances. The integration of AI support, such as ChatGPT-4, into our workflow poses intriguing questions about referencing and acknowledgment. Reflecting on "T is for Talent," I realize that today's norms may not always align with traditional citation practices. I eagerly embrace the potential for advanced "version control" systems to monitor and enhance my work. Microsoft Viva Insights and Copilot, I implore you to join me in this quest for progress as we strive to revolutionize the professional world together.

Not sure I’ve ever “eagerly embraced,” nor “implored,” but again, not bad.

The talent around us benefits our work. Publication style guides call for us to cite articles, books, and personal communications, but not our editors. What does this convention cost us? Will new technologies like blockchain enable us to gain the value of better citing all our sources?

T Is for Talent -- Often Hidden

Susannah Schmidt, the editor for my recent piece in The Conversation: Why using AI tools like ChatGPT in my MBA innovation course is expected and not cheating is an excellent example of uncredited value. Beyond her knowledge of the audience and style of The Conversation, Susannah offered insights and ideas for improvement. There is irony in this given that one of my main points in the article is that using technology isn't cheating, but not citing your sources is.

I’ve had many fantastic editors over the years. We sometimes footnote an idea or analysis suggested by these collaborators, but not often. When we don't fully source our writing, we limit the provenance of our work.

Knowledge Management

I motivate my students to use citations by making connections to the value of knowledge management. A 2017 ICD survey found people spend 19% of data activities time searching for the data. How can you validate your claims and check your results if you can't recall the source of your inspiration, data, or workflow?

Counterpoint

The publication style guides may be right. Publications credit the editors in the introductory material. This acknowledgment solves the ethical issue of editorial contribution. Editors edit, enough said. 

Limiting our references may better support the creativity of those who follow. Kane and Ransbotham find that contributors to Wikipedia articles fall off as the topic matures. If a more substantial network of references makes it appear that all the good ideas are already on the table, what happens to future insights? Are we more likely to contribute if we can stand on the shoulders of giants? Or are we less likely as attention, funding, and willingness to take risks fall off in the face of more established findings? (Thanks to colleague Ian McCarthy for a tweet sending me down this path).

The Future

I had the chance for a sit-down with Phil Simon this week. He's working on a new book, The Nine: The Tectonic Forces Reshaping the Workplace. One of his forces is the application of blockchain technologiess -- global distributed ledgers that store and track digital assets and information. Just as hyperlinks can simplify how we connect to our sources, I hope we use blockchains to map the full provenance of the ideas without reducing the article's readability.

As always, I don’t expect a singular solution. We must consider a mix of talent, technology, and technique. What’s essential in this time of dramatic technological change is that we mindfully adjust our workflows with these new technologies.

Next Up

A good editor stays in your head. In this case, I hear decades of editors coaching me to stay focused. I'll save another of Susannah’s suggestions for a follow-up post on writing methodology in the age of generative AI: T is for Technology and Technique. Please let me know your thoughts and critiques in the comments below -- a direct way to document the contribution of your ideas!

ChatGPT launched on wednesday. today it crossed 1 million users!

Every good blog post needs a hook. For today, I wanted to leverage the continued growth of ChatGPT registered users. Given it hit 1 million in 5 days, where must it be now? Likely some big, juicy number that would be great for this post. I asked Chatsonic “where can I verify the number of registered users chatgpt has today?”, but it told me yet another in a long line of fibs:

“You can verify the number of registered users on ChatGPT's website. On the homepage, you can find the "Users" section, which shows the total number of registered users on the platform. You can also find the total number of active users in this section.” […there is no Users section on either the OpenAI or ChatGPT sites.]

Is it Me?

Maybe I just don’t know how to ask the right question… but I’m likely better than many. I’m known in the family as the Queen of Search (thank you, Google Advanced Search course!) and much of my research involves me crafting search requests across a variety of platforms. It may also help that searches early in my schooling cost actual money and I had to make an appointment with the university librarian to submit my request (1980s Dialog searches for academic articles).

We’re All (including the AIs) Learning as We Go

The requests I’m running these days cross ChatGPT, ChatSonic, MidJourney, DALL-E 2, and more. Each of these platforms has a slightly different set of parameters you can use. How about this one for MidJourney: “a seamless tileable jade tree pattern, spiral carvings, octane renderer, trending on CGsociety --ar 1:1 --q 2”. Not a phrase I would have come up with, but the result is lovely. There is also the complexity of integrating some of these capabilities into our standard tools (e.g., ChatSonic extension for Chrome).

Thank you to those who have gone before and their willingness to write instruction guides -- see my short list below. Thank you too, to the platforms for offering up backgrounders to help us learn the nuances and see more opportunities. I’ll list some of those below as well.

What is the Expertise We Need?

Queen of Search may be a great title, but I wonder if we will find it on many LinkedIn or Indeed job posts. Prompt Engineer is an actual job title, but I’d like to see it fade away. Two reasons: First, I’d like all my engineers to be prompt, and second, given we are unlikely ever fully to understand the AI black boxes, is it engineering? 

How About AI Wrangler?

AI Wrangler builds on the short history of Robot Wranglers. It also reminds me of the skills needed to herd literal or figurative cats. Until, if ever, we know what it means to be fluent in the language of AI, wrangling is more in line with the reality of this work than engineering. 

Learning from Others

Prof. Ethan Mollick offers examples that show me that I have much to learn as I work with these new tools:

write an essay with the following points. use an academic tone. use at least one clear example. make it concise. write for a well-informed audience. use a style like the New Yorker. make it at least 7 paragraphs. vary the language in each one. end with an ominous note. -Humans are prone to error -Most errors are not that important -In complex systems, some errors are catastrophic -Catastrophes cannot be avoided….

Sometimes the memory is useful, you can (and should) ask it to revise previous work: change the third paragraph to be more professional or use a different example in the middle and it will provide a revised version. However, sometimes it forgets what you were working on, and you have to remind it. You may, for example, want to tell it revise the third paragraph on the essay on catastrophes so it doesn’t lose track.

And It’s Not Just the AI - We Need to Work Collaboratively

Yet, focusing on prompts seems limiting. If my goal is to race with the machine, I want to see the process become more of a collaboration. Alexa and Google Home sometimes offer options after answering questions, but usually these are more of an annoyance than a help. One more thing to say “no” or “stop” to. Coaching from the new AI would help me. Live-action versions of the backgrounders would be nice. Humans learn best actively -- when we’re in the middle of a task is the best teachable moment. ChatGPT seems the closest of the tools I’ve used in that it asks for feedback on the quality of the response. Sometimes, it also gives a hint. In this screenshot, it coaches me on how to find what I’m looking for.

My Attempt to Be Proactive

I asked ChatGPT and ChatSonic to give me hashtags for my last post. “Act as a coach, how can I more effectively ask you for help in creating good hashtags for this post?”

ChatGPT’s response:

1. Be specific: Provide as much context as possible about the post, including the topic, audience, and goals.

2. Provide an idea of what you're looking for: Are you looking for hashtags that are popular, unique, or specific to a certain community?

3. Be open to feedback: Be prepared to receive suggestions and be willing to make revisions based on my feedback.

4. Give a good example of the post, if possible. Tell me if you have any specific guidelines that you need to follow, such as the number of hashtags, length, etc.

5. And finally, be clear and concise in your question. For example, "Can you help me create 5 hashtags for a post about vegan food targeting a health-conscious audience?"

Learning Together

We are writing thousands of articles in hundreds of languages about using these new tools. (WriteSonic even offers example prompts for AI-related posts in its menu bar.) I’m reading and experimenting with as much of this as I can. I hope my colleagues and students are as well. Every time I write, stumble at getting the AI to do what I want, or comment on a colleague’s related post, I’m hoping this work is training the various AI as well as giving me a chance to practice. I’m willing to put the work in now for better tools in the future. 

Take your AI wrangling on as a challenge. If you spend much time interacting with voice assistants like Alexa and Siri, or maybe your smart oven, you know that (at least today) you must adjust your language. You may adjust your pace, tone, and vocabulary to get the desired result. Working with the new batch of generative AI is the same. …and these are the same skills you may have had to develop if you’ve programmed in anything from COBOL to Python: We start with a “Hello, World” program and move on from there (…and have no worries, ChatGPT can write those “Hello, World” programs for you and explain the work -- just ask).

The good news is that, like with programming in different computer languages, once you learn one, the next is easier. Consider other life skills that you can draw on as you learn these AI languages. In a constructive Medium post, Shubham Saboo says, “In a way, prompt design is like playing a game of charades!” Unfortunately, if I’ve played charades, it’s less than three times. Good thing I have COBOL to fall back on.

Thank you for letting me share my learning journey.

Resources

Each of the following is a support document I’ve found helpful. Thank you for sharing others you find (or that you had the AI find for you) in the comments section below.

• ChatGPT:

  • https://github.com/f/awesome-chatgpt-prompts

  • https://fka.gumroad.com/l/art-of-chatgpt-prompting

• MidJourney: https://midjourney.gitbook.io/docs/resource-links/guide-to-prompting

• More Image Examples: https://mpost.io/top-50-text-to-image-prompts-for-ai-art-generators-midjourney-and-dall-e/

• History of AI Art: https://www.stevemurch.com/engines-of-wow-ai-art-comes-of-age/2022/12

• WriteSonic: https://docs.writesonic.com/docs

I finished my Fall MBA teaching before the explosion of ChatGPT - a chatbot that can write, code, and answer questions. The next time I teach this material will be in a different world. ChatGPT reached 1 million registered users in 5 days and continues to grow. 

My innovation course for our Management of Technology MBA is writing intensive. True, even this Fall, AIs were available that could paraphrase (e.g., Quillbot), but they hadn't made the mainstream in my community. Even Grammarly, a proofreading tool I pay for and encourage my students to use, wasn't common knowledge. 

Past students don't have second thoughts about using Google Autocomplete. However, when it comes to Grammarly's increasingly powerful rephrasing capabilities, some wonder whether using such tools is cheating. My syllabus has an extensive academic integrity section, and I spend much time on how to quote and cite in business writing correctly. I also let the students know I use Turnitin.com to check for citation mistakes. (I'm happy to say I haven't encountered full-blown plagiarism at my current university.) My students' concern makes sense. 

My Answer So Far

My answer has been that no, the use of an editor, whether human or machine, just makes sense -- it's not cheating. The final words must belong to the listed authors, but good business practice supports using discussion and editing tools to get you to that final stage.

Generative AI

I will teach my next course in a world of ChatGPT, WriteSonic, and the multitude of generative writing AI that are not just editors. Examples from homepages of some of the commercial tools:

• WriteSonic: "Best AI Writer for Creating" [and then an animation lists LinkedIn posts, SEO Content, Product Descriptions, etc.] for bloggers, freelancers, etc.

• Copy.ai: "Say 'goodbye' to the blank page for good."

• Sudowrite: "Sudowrite is the non-judgmental, always-there-to-read-one-more-draft, never-runs-out-of-ideas-even-at-3am, AI writing partner you always wanted."

• Notion AI: "Leverage the limitless power of AI in any Notion page. Write faster, think bigger, and augment your creativity. Like magic!"
  
  

I expect each tool to do an adequate job (low "B") with my assignments. Leveraging multiple tools to get the design, text, and references in line seems realistic. My final individual assignment is to create facilitator-focused playbooks related to three of the course concepts. I've offered a baseline quality example to the students for the last couple of years. Before the next course, I'll redo that example using a set of generative AI.

But is using an AI in such a way cheating?

Recall the bruhaha of Fall 2022 when an AI-generated image won at the Colorado State Fair. My reply to the discussion on Twitter:

Is the prize for the art, the best human art, art by someone living in that country, art by a child, or art by an elephant (or the best monkey selfie)? We've always made distinctions, now we just need to build a norm for attribution. Share the tools and who/what submitted.

— Terri Griffith (@terrigriffith) September 21, 2022

Chatsonic seems to agree with me. I asked it, "what is the biggest concern faculty have about generative ai?" Chatsonic's reply:

The biggest concern faculty have about generative AI is its potential for creating automated plagiarism and copyright infringement. Generative AI can generate content that could easily be plagiarized without proper attribution, and its models can reshape existing material into something new and unrecognizable. Therefore, it is important to ensure that any use of generative AI is properly attributed and that the content generated is unique and non-plagiarized.

Chatsonic differs from ChatGPT in access to current web search results. To verify my understanding, I asked Chatsonic, "can chatsonic use 2023 search results?" Its reply: "Yes, absolutely! I can use the latest online search results from the year 2023 to provide you with the most up-to-date information." (I've installed the Chatsonic chrome extension such that any searches I do from the Chrome toolbar that end in a ?-mark offer Chatsonic's reply and the Google search results.)

Using AI Is Not Cheating. But Not Citing Your Source Is

When I shared three of my favorite business books in my final 2022 post, I used ChatGPT to create an alternate review of Power and Prediction: The Disruptive Economics of Artificial Intelligence by Ajay Agrawal, Joshua Gans, and Avi Goldfarb. I said, "I hope knowledge workers [people using generative AI] will share their tools just like photographers often caption their images with a description of their camera and setup." Where I used ChatGPT's work, I used the quote format (as I've done here). 

I also specified the prompt I used. However, I wouldn't expect that same prompt to give me or anyone else the same answer each time. Some image-generating AI (e.g., MidJourney) let you define a seed so that you can "steady" the results. I have yet to find similar features for chatbots. If replication isn't possible, then references to AI-generated text are similar to how we reference personal communications or direct quotes from interviews -- situations where the author has access to the material, but others do not. 

We Need APA/MLA/Chicago Manual of Style Citation Guidance

I asked Chatsonic, "give me the URL showing how to reference material generated by an AI in the chicago manual of style format?" The response was, "Sure! Here is the URL to the Chicago Manual of Style guide on citing materials generated by AI: https://www.chicagomanualofstyle.org/citation-quick-guide/citation-quick-guide-3/ai-generated-material.html Hope this helps!" Following that link gave me the error noted in the image. Entering "ai generated work" into the Chicago Manual of Style search bar returned, "Your search 'ai generated work' did not match any documents.” [Spelling out artificial intelligence was also a bust.]

I'd love to know more about the underlying language model Chatsonic uses such that it seems to fake a URL. I'd be happier about paying for the service if it would at least check itself before offering up the link. ChatGPT took an honest pass:

I'm sorry, I'm not able to provide URLs. However, The Chicago Manual of Style does not have specific guidelines for citing material generated by AI. The best way to cite such material would be to consult with your instructor or editor for guidance. It may be helpful to include information about the specific AI model or program used to generate the material, as well as the date and any other relevant details. [ChatGPT shares that it's training data goes up to 2021.]

We're All Learning As We Go

I started blogging to allow myself to reflect before answering common and more detailed student and executive questions. Thank you for joining me on this journey as we all (and I include the AI) learn as we go. I'm very interested in differing perspectives. Feel free to comment below or reach out on other platforms.

Created using a combination of Grammarly (paid), Chatsonic (paid), ChatGPT, Google Autocomplete, DALL-E 2, and the Five template on Squarespace.

Happy holidays!

My comments are in the order I read the books. You can follow my Goodreads list here. So many fantastic books to read!

The No Club: Putting a Stop to Women's Dead-End Work by Linda Babcock, Brenda Peyser, Lise Vesterlund, and Laurie Weingart

The No Club was an easy purchase (and the book for which I've made the most 1:1 recommendations). Anytime I'm asked about women negotiating in the workplace, I cite Professor Linda Babcock and women and the workplace authority Sara Laschever's earlier book, Women Don't Ask: Negotiation and the Gender Divide. Here, Professors Linda Babcock, Brenda Peyser, Lise Vesterlund, and Laurie Weingart take a discussion about their workloads and turn it into a science-backed playbook for women in organizations (and life).

They start with identifying the critical issue that brought them together: Women do more non-promotable tasks than their male colleagues. "A non-promotable task matters to your organization but will not help you advance your career" (pp. 16-17). They build out strategies for assessing the situation, making effective decisions about what work to take on, and how to effectively say no.

The Basics

• Get the Information You Need to Understand the Task

• Consider Who Is Asking You

• Avoid the Traps that Lead to Yes -- don't underestimate the costs (something I do all the time)

• Use a "Yes, No, Yes" Strategy (p. 131-132). Here’s an example they share:

"Thank you for thinking of me, Joe. I have so much on my schedule the next two quarters with leading the new product launch that I won't be able to devote the time that organizing the meeting really requires, so I'm going to have to decline. But Don would be a great person to take on the task, and he could benefit from the opportunity to interact with others from across the company. I am confident he'd do a fantastic job." 

The Long Term

Having given us an individual playbook, they switch to an organizational focus:

...organizations need to fully embrace responsibility for correcting the current imbalance of [non-promotable tasks]. That is our primary lesson. This is not a fix-the-women problem (pp. 232-233).

Read, The No Club, then keep it close by. Follow the authors' advice to take your time before answering a request. Use that time to skim the book again. The No Club is a book for many women you know -- and for the men working alongside them.

(My tools: Google auto-complete and Grammarly, paid account)

Low-Code/No-Code: Citizen Developers and the Surprising Future of Business Applications by Phil Simon

Low-Code/No-Code is a fantastic book for all of us (this is a common theme in these summaries). We all need to do more to build our tools and craft our work. As leaders and managers, we need to make sure our organizations function by having the best talent and tools aligned with the times and toward our targets.

Contribution

Besides the engaging voice and dry humor I expect from Phil Simon’s work, Low-Code/No-Code also presents benefits for citizen developers and examples and implementation strategies for managers. Whether you take on low-code/no-code approaches as small bites or as an overarching organizational strategy, you will benefit from this book.

Aside

As these tools spread, I hope we move away from a language of “code.” I fear that thinking of this work as coding may be a barrier to some. The vocabulary train has likely left the station, but I’d rather have a language of apps.

Conclusion

Regardless of what we call these tools, if you can use a smartphone, you can be a citizen developer. Read Low-Code/No-Code to learn more.

(My tools: Google auto-complete and Grammarly, paid account)

Power and Prediction: The Disruptive Economics of Artificial Intelligence by Ajay Agrawal, Joshua Gans, and Avi Goldfarb

I enjoyed their previous book, Prediction Machines: The Simple Economics of Artificial Intelligence, but agree with the authors’ insight here -- we need more about how AI fits into our broader sociotechnical systems: the full design and outcomes of our organizations and work.

System Mindset

In Power and Prediction, Professors Ajay Agrawal, Joshua Gans, and Avi Goldfarb help us understand where AI fits into the broader picture. They show AI as a piece of an overall system and that:

"[t]he successful adoption of AI presents what we will term here the system mindset. It stands in contrast to a task mindset in that [the system mindset] sees the bigger potential of AI and recognizes that to generate real value, systems of decisions, including both machine prediction and humans, will need to be reconstituted and built" (p. 112).

Actionable Framework

They also offer an “AI Systems Discovery Canvas" (p. 241) to support leaders' thinking about AI's strategic and integrative roles in their organizations. 

My Vancouver Perspective

As happy as I am with the book's insights, I am a little sad (given I work in Vancouver) about their 2017 prediction cited in the preface: "Where do you expect to see Canada's first AI unicorn—the first AI startup to reach a billion-dollar valuation?" Our bet: "Montreal. Or maybe Toronto. Or possibly Edmonton" (p. 8). It turns out my wishes and their predictions were both off. Verafin, from St. John's, Newfoundland, hit 2.75B USD in its acquisition by Nasdaq in 2020…..

I look forward to Vancouver playing a strong role at least in the bottom-up applications of AI. My RA, Nitish Gupta, and I contribute to the basics by organizing a quarterly list of AI-enabled tools for personal automation.

Taking Action

I do my best in class and workshops to share a systems-level approach (Thinking in 5T) and will be adding the system mindset advice from Power and Prediction.

(My tools: Google auto-complete and Grammarly, paid account)

The Future of Work

Low-Code/No-Code and Power and Prediction need deeper dives than I offer here. I am not doing the significance nor the nuance justice in these short mentions. I look forward to other ways I can integrate more of these ideas into my teaching, workshops, and work. You will also find value in reading, discussing, and most importantly, applying the material.

What ChatGPT Has to Say about Power and Prediction:

I thought it only fitting that Power and Prediction be the focus of my ChatGPT test. I fed it this prompt:

Write a review of Power and Prediction: The Disruptive Economics of Artificial Intelligence by Ajay Agrawal, Joshua Gans, and Avi Goldfarb. Include page numbers for quotes. Include hyperlinks. Write in the active voice.

I have no clue what edition of the book ChatGPT is using -- the pages noted below do not match my Kindle version. Maybe it’s making them up (just like some humans I know).

In Power and Prediction: The Disruptive Economics of Artificial Intelligence, Ajay Agrawal, Joshua Gans, and Avi Goldfarb delve into the economic implications of artificial intelligence (AI). As experts in the field of AI and economics, they offer unique insights on how AI is transforming the way we do business and the way we live.

The authors introduce the concept of "prediction power," or the ability of an AI system to accurately predict the future, as a key factor in unlocking the economic value of AI (p. 3). They provide numerous examples of how companies use AI to gain a competitive edge, such as optimizing supply chains to reduce costs and improve efficiency (p. 25).

The book also discusses "creative destruction," or the disruption of existing industries and the creation of new opportunities by new technologies (p. 7). The authors examine how AI is driving creative destruction in industries such as transportation, healthcare, and finance, with a particular focus on how it is enabling doctors to make more accurate diagnoses and treatment recommendations (p. 87).

Overall, Power and Prediction offers a thorough and timely analysis of the economic impacts of AI. It is a must-read for those interested in the future of technology and its effects on society.

Links [NOTE: all of these are wrong, common problem with generative AI — use links above]:

Power and Prediction: The Disruptive Economics of Artificial Intelligence: https://www.amazon.com/Power-Prediction-Disruptive-Economics-Artificial/dp/0198805068

Ajay Agrawal: https://www.rotman.utoronto.ca/FacultyAndResearch/Faculty/FacultyBios/AjayAgrawal

Joshua Gans: https://www.rotman.utoronto.ca/FacultyAndResearch/Faculty/FacultyBios/JoshuaGans

Avi Goldfarb: https://www.rotman.utoronto.ca/FacultyAndResearch/Faculty/FacultyBios/AviGoldfarb

All in all, not a bad write up from ChatGPT, aside from the fake links. I will build and share a workflow leveraging ChatGPT for transactional writing. I also look forward to rethinking my homework assignments. More in the New Year!

Automation is part of our work. The question is whether we are finding the tools to augment our abilities or waiting for our organizations to decide what to automate and who to replace. Research finds that people who craft their work are more productive and employable. In this earlier post with Brett Li of Tonkean, we talk about that research and the steps you can take to craft your work. But what tools can help us?

Bottom-Up Automation Tools

Here is the December 2022 quarterly update of our database of personal automation tools! Nitish Gupta and I collect tools that leverage artificial intelligence (broadly defined) to support work. You likely use some of these tools already (e.g., GMail’s autocomplete). We hope you also find many valuable new tools within our mix (ChatGPT is new this quarter). Our criteria include these tools are:

• for work (again, broadly defined) - generally, not lifestyle. That said, many will help across your work and leisure.

• that individuals or teams can integrate into their work without organizational support. (Many powerful tools for automation would connect directly into an organization’s systems - these are better taken on as top-down and bottom-up efforts.

• leveraging automation either internally (e.g., machine learning or other artificial intelligence) or as part of a process connecting to AI tools (e.g., IFTTT).

Click on the image below to have a look. Mobile users may have a better experience here.

This Quarter

We added over 27 new tools this quarter. We split Photography given the size of the category and the number of new tools. Look for Image Enhancer and Image Generator. We also added a category for Chatbot. I remain surprised that all of our prior selections are still available.

What’s Next?

We update the list quarterly. Ironically, for now, this is a hand-crafted process. As we looked at earlier lists of automations for personal use, we found many were out of date. Tools may come and go, change names, are rolled into other services, and the like. We will use automation to check our links each quarter and add new tools as we find them — or as you suggest them in the comments ⇓ below ⇓.

Many organizations put new policies in place as we transitioned from COVID-19 shutdowns to our current work mode. The early shutdowns were a COF: Crisis Online Format. (Does anyone have a great name for what we’re doing now? Muddling along given the mismatch between remote opportunities and interest in remote jobs?) 

I like to ask individuals, managers, and organizational designers what they learned about their work practices during the shutdown. Most haven’t thought to track what went well and what was a challenge. People were, of necessity, acting quickly. However, now we have some time and data to help us think about what to do next. Don’t let the opportunity to learn from those difficult times go by.

Please let us know on the WSJ site or in the comments section here ⬇ about how the metrics we discuss play out in your own work:

1. Manager versus team time in the office

2. Time on video

3. Expanding work hours

4. Formal versus informal interactions

5. Pandemic nostalgia

6. Return to hardcopy practices

What amazing timing! Last night I had the pleasure of talking open and user innovation with my Management of Technology MBA students. We covered organizations that won’t accept ideas from their community (think Disney). But we also discussed great practices for engaging with your customers, clients, and broader community to innovate and meet customer needs.

Today, I received a marketing email from Fluevog -- I’m a happy subscriber to this avant-garde Vancouver-based shoe company’s notes. Today’s email was an invitation to Flummunity Fest 2022. Given I work 15 minutes from Fluevog HQ, I thought I should get a ticket and check out this energetic community. Clearly, the company was practicing a special kind of design.

Then it hit me. I didn’t own a pair of their shoes. I’ve happily window (and web) shopped but never closed the deal. I’d be deemed an interloper at Flummunity Fest without the right footwear. I took my daily walk toward Fluevog’s combination store, design studio, and headquarters.

Meeting John Fluevog

As I tried on the Domingos and the Nortons, I wandered around checking the fit. A stylish gentleman with amazing glasses asked me how it was going. It was John Fluevog (I had an inkling, but he thankfully introduced himself). The stars had aligned to find me cool shoes in the right size and the chance to talk to an iconic designer and entrepreneur.

I shared my role at SFU and that we’d just been talking about “user” communities and innovation in class. I told him that the email about Flummunity Fest was the trigger for my visit.

John shared a bit of the history and answered my community innovation questions. Flummunity Fest is the result of the community coming together on its own. He is both appreciative and careful to note their autonomy. That said, the connection seems tighter this year with the event in Vancouver. I’m looking forward to the talks, including one by Bernadette Croft, costume designer for Star Trek: Strange New Worlds™. 

User Innovation

Organizations can be fortunate and have a community gel, but they can also be proactive when it comes to engaging with their community for innovation. In the case of user innovation, Fluevog has a formal system. In this 2006 New York Times article by William C. Taylor, To Charge Up Customers, Put Customers in Charge, John says:

"Some of the ideas from customers are striking, but impossible to make," Mr. Fluevog said. What tends to work best, he explained, are intriguing twists on design themes that he and his colleagues are already exploring. "But even submissions we can't make add to the stimulation," he added. "Our customers get more involved, and we get insights into who they are and what they're doing. It's better for both of us."

Here’s the link to the current call for design ideas. This open source process is a great example for my students, given how clearly the Fluevog site spells out the process, including an answer to this question about selected styles:

 Will I be rich?

Quite possibly, but probably not from this. Nobody gets paid for Open Source Footwear designs because nobody owns them. Once you send us your design, it becomes public domain and freely available to all. We may use the whole thing, base a design of our own on it, or just use a part of it in one of John’s own designs.

What Am I Wearing to Flummunity Fest?

From this photo, you’ll know that I’m not a fashion stylist. But am excited to see these boots sparkle as I talk to people about their Fluevog stories. Thank you to John for checking in with this happy customer. Thank you to the patient staff who helped me find the right pair - taking extra time given my break for conversation. More after Flummunity Fest….

MOT Students

When we cover prototyping, we’ll be back to the Fluevog open source submission site. Stay tuned.

We Are All Experts

We all fit somewhere on a spectrum of programming knowledge. No matter where we are on that spectrum, we deserve respect. We each know our jobs better than anyone else. How do we help share the value of No-Code/Low-Code tools to everyone working with any kind of data? 

Scary Language?

My biggest fear is that even an accessible term like No-Code/Low-Code will scare people. The idea of “coding” may be outside most people’s experience, or worse, code of any form, something to be avoided. In the cases of collaboration tools and mobile devices, the explosion of adoption at work took place after people had experience with the tools in their personal lives. Maybe the same is true of No-Code/Low-Code?

Ninety-seven percent of Americans have a mobile phone. The number is 78% in Europe; 99.7% of Chinese internet users use a mobile phone for their access. How do we share the mental image that if you can use a mobile phone, you can use No-Code/Low-Code in your job?

Enticing Language

I see at least two positive ways this can go:

1. The terms Citizen Developer and No-Code/Low-Code gather steam. Maybe we can leverage the “Hot cause - Cool mobilization” dynamic that Hayagreeva Rao describes in his book, Market Rebels. The hot cause is that our work demands are increasing faster than our teams and our skills can manage. The cool mobilization is that No-Code/Low-Code becomes what the cool kids -- the Citizen Developers -- do to solve the problem.

2. We avoid language like No-Code/Low-Code and Citizen Developer. Both those phrases presume you know what coding and development are. For most people, do we even need that level of knowledge to take advantage of the tools? Collaboration tools don’t need people to know what a knowledge management system is. Internet devices don’t rely on more than the ability to install an app (or know someone who does). Sure, you can do more if you know more, but great value is coming to billions of people who don’t have advanced skills.

Bridges Rather Than Walls

I request we don’t build walls out of language. Perhaps mobile phone terms like apps, app store, and the like are more enticing. We need to build bridges from the technology knowledge people have and how they work now to how they can be gaining value from No-Code/Low-Code. I’m also okay with Citizen Developer superheroes — as long as we know we can all be one.

Thank you to Phil Simon for our conversation this week. His forthcoming book (available now for pre-order), Low-Code/No-Code: Citizen Developers and the Surprising Future of Business Applications will be a great resource as we think about the automation of our work.

I’m thrilled to be involved in an upcoming “Discovery Summit” on the Future of Expertise (June 29, 8-11am PDT -- join us!) I’m reading and contributing to the backgrounder ISSIP co-founder and board member, Dr. Jim Spohrer, is preparing. This pushes me to offer the following thoughts and hope you will comment below on areas you are most interested in seeing here and perhaps at the Discovery Summit. Know that this is the first of two Summits on the Future of Expertise; the second is scheduled for Sep 28, 2022. Some of the links below are to my colleagues’ and my prior work. Other links are to background research from other experts that I’m happy to have found.

Our Knowledge and Our Tools

In 2008, I took a look at BYOD (Bring-Your-Own-Device). This left me with a variety of questions. “How does this change our relationship with our employers?  Do we then become more valuable the better our technology?”

Video-Mediation of Expertise

In 2012 I wrote a piece wondering how we would value expertise shared from afar. It was triggered by a Polycom demo of new mobile video capabilities and an increased ability to partner across software and hardware. Use cases included medical experts being more accessible in smaller communities. 

Augmenting our Expertise with AI

My questions today focus on expertise either directly from artificial intelligence (AI) or as an augmentation of our human skills. Nitish Gupta and I track AI-supported tools for personal automation in an effort to help people with the bottom-up application of AI in their work. Utpal Mangla and I did a series of posts focused on gaining value from AI in our work.

Systems Savvy

My colleagues and I are preparing a deep review of the use, attitudes, and outcomes related to AI applications at the team level. An early observation is that systems savvy, “the capacity to see the interdependence of technological and social/organizational systems and to construct synergies between them,” is a critical human capability both for technology and work designers… so all of us. All of us need to be involved in the design of our work. We need to participate in work crafting.

Guilds

But where does the responsibility (and capability) lie for developing our expertise in our field of choice and, more specifically, expertise in how to design our work? As the precariousness of work (e.g., gig and contract work) gains attention, I often think about the value of a guild system. In 2015, Nathan Schneider wrote a New Yorker piece, The New Guilded Age. He describes guilds as, “associations of independent craftspeople, setting standards for their lines of work and cultivating lively subcultures around their labor.” He cites Wage Labor in Medieval Europe by Steven A. Epstein: “The members also swore an oath of loyalty to each other” - to include mutual protection and vengeance against non-payment.

Speaking of the gig economy, John Hagel (author of The Power of Pull and the forward to my book, The Plugged-In Manager) writes:

We’re going to begin to see impact groups forming and coming together into broader networks that will help them to learn even faster.

That’s where guilds come in. In Medieval times, guilds were a prominent way of organizing in urban areas to bring people together who were seeking to earn a living from a particular craft or trade. These guilds had many different roles, but a key one was to help their participants become better at their craft or trade. They were powerful learning organizations where participants learned through practice, rather than sitting in classrooms….

These guilds can play many different roles over time. One major role would be to provide the participants in their guilds with access to a variety of benefit programs like health care and life insurance that would be much more difficult to obtain as individuals. These guilds can also help to define and manage reputation systems that will help their participants to build a broader range of trust-based relationships. They can become rich environments for mutual aid among participants. [Perhaps including vengeance for non-payment?]

Tools

In some cases, apprentices would make their own tools as part of their education. This brings us back to human expertise and augmentation via automation/artificial intelligence. Are guilds a model in support of our learning to design our work and develop our tools? Are there generalizable skills (like systems savvy, though perhaps using my hopefully more catchy phrase, Thinking in 5T) that are better suited to general education? Is expertise a combination of our knowledge and our tools?

Some scholars think so. From Nicolini, D., Mørk, B. E., Masovic, J., & Hanseth, O. (2017): 

Human expertise always implies and presupposes some form of material or symbolic mediation (language being the mediatory tool par excellence). Through mediation, history, culture, institutions, and power are all concretely manifested in human action. Artifacts are thus not only integral in the accomplishment of expert activity, they are constitutive of expertise itself as they have the capacity to mediate onto the scene of action the history of achievements and learning, tracing and shaping their creation and refinement. In short, mediatory “tools” can be seen as accumulations of expertise that are then brought to bear on the activity that they help make possible.

Your Thoughts?

Thank you for pointing us in new directions and helping us focus on the topics above that are of most use to you. As Nicolini et al. (2017) say, “...we suggest that one would have good reasons for attributing expertise to the master and the center of excellence—as a collective entity.” I won’t claim to be a master in the study of expertise, but I know that collectively we’ll get further toward finding excellent applications in our work.

Post-Script: Guilds versus Unions

I’m early in my own thinking and I’m not a lawyer (nor do I play one on TV). So I’ll only offer a link to an interesting piece describing modern guilds and unions in the entertainment industry.

Automation is part of our work. The question is whether we are finding the tools to augment our abilities or waiting for our organizations to decide what to automate and who to replace. Research finds that people who craft their work are more productive and employable. In this earlier post with Brett Li of Tonkean, we talk about that research and the steps you can take to craft your work. But what tools can help us?

Bottom-Up Automation Tools

Here is the September 2022 quarterly update of our database of personal automation tools! Nitish Gupta and I collect tools that leverage artificial intelligence (broadly defined) to support work. You likely use some of these tools already (e.g., GMail’s autocomplete). We hope you also find many valuable new tools within our mix. Our criteria include that these be tools:

• for work (again, broadly defined) - generally, not lifestyle. That said, many will help across your work and leisure.

• that individuals or teams can integrate into their work without organizational support. (Many powerful tools for automation would connect directly into an organization’s systems - these are better taken on as top-down and bottom-up efforts.

• leveraging automation either internally (e.g., machine learning or other artificial intelligence) or as part of a process connecting to AI tools (e.g., IFTTT).

Click on the image below to have a look. Mobile users may have a better experience here.

This Quarter

We added over 20 new tools this quarter. We split collaboration and meeting support given the size of the category and the number of new tools. Similarly for art and graphic support. Surprisingly, all of our prior selections are still available.

What’s Next?

We update the list quarterly. Ironically, for now, this is a hand-crafted process. As we looked at earlier lists of automations for personal use, we found many were out of date. Tools may come and go, change names, are rolled into other services, and the like. We will use automation to check our links each quarter and add new tools as we find them — or as you suggest them in the comments ⇓ below ⇓.

Thanks to Utpal Mangla, VP and Senior Partner, IBM, for joining me in this post. Under Utpal's leadership, his team recently achieved its mission of making "Watson AI Impact 1 Billion Consumers." Utpal and I are officers within the ISSIP (International Society for Service Innovation Professionals) organization. 

Fintech Sales Agents

Luo and his colleagues examined data from two fintech organizations in Asia. In the first, sales agents are selling personal loans to current banking customers. In the second, sales agents call people who are delinquent on their peer-to-peer loans to collect overdue amounts. In both instances, and in all contact center work we are aware of, sales coaches listen to calls and give coaching. The focus here was whether and how AI could play a role.

In the first study, the comparison was AI versus human. Sales agents received an email each morning either from a human coach or from an AI system adopted by the company. The email included text excerpts from the prior day’s calls, called-out mistakes, and provided solutions to those mistakes. 

Overload versus Aversion

As compared to human coaching, the researchers expected that AI coaching, as represented by this particular system, would affect sales agents differently based on the sales agent’s expertise (as measured by past sales performance ranking). They expected bottom-ranked sales agents (generally new-hires or interns) to be overwhelmed by the more extensive feedback provided by the AI. The researchers expected top-ranked experts to have aversion to AI coaching given the experts’ existing skills and expectations.  Both overload and aversion were predicted to reduce the benefits of AI coaching. The three-bar chart maps the outcomes, supporting the researchers’ predictions about sales (their underlying predictions about learning over time were also supported).

In the loan collection context, Luo and colleagues dug deeper into how best to support agents. Bottom and top-ranked agents were coached in one of three conditions: face-to-face by a human coach, face-to-face by a human coach who received the AI’s feedback for the agent, or directly from the AI via email. (The host company declined to include the middle-ranked agents as they were satisfied with the results for middle-ranked agents in the prior study.)

Race With the Machine

Using this AI system and these coaches, the face-to-face human-supported with AI coaching is the winner. Leveraging the benefits of AI (ability to listen to all calls, identify more mistakes, suggest more improvements) coupled with human coaches’ interpersonal abilities is a chance to do as Brynjolfsson and McAfee suggest and race with the machine, not against it (book, TED talk).

More Traditional Coaching: Tennis

Shifting gears away from traditional customer environments, an excellent use case in the field of sports is how AI is helping professional tennis players improve their game. With the help of AI & analytics, coaches can deliver more effective advice to the players. IBM’s “Coach Advisor,” for example, leverages data from multiple sources such as players’ physical exertion, endurance, and outcomes to suggest strategies to enhance match performance.

Like all applications of technology, there is no silver bullet. How players and coaches gather and use the data varies wildly and there is no one right answer. The key is to align the talent, technology, techniques, for the times and target. While Sarina Williams and Novak Djokovic (he even has a data analytics advisor on his team) use the data in their preparation, not all the players do (yet?)

AI Coaching for the Rest of Us

Let us know where you’re looking forward to using AI coaching, or the outcomes you’ve had so far.

Welcome to Part 2 of how to leverage artificial intelligence (AI) in customer-facing settings. In Part 1, we offered customer fundamentals. Here we focus on linking data (e.g., questions, suggestions, complaints) documented by intelligent virtual assistants (IVA) to product and service development teams. Based on the following research and experience, we suggest building these three organizational structures into your IVA approach:

• Employee autonomy to interact with AI-sourced data - opportunities to dig into the data

• Incentives plans that motivate employees to interact with AI-sourced data - perhaps award programs that share success stories

• Communication practices that cross departments and hierarchical levels - customer issues are rarely bound by traditional organizational boundaries. Responses to customer queries are likely stronger to the extent that they weave together the organization’s talent, technology, and techniques rather than more limited approaches.

Thanks to Utpal Mangla, VP and Senior Partner, IBM, for joining me in this post. Under Utpal's leadership, his team recently achieved its mission of making "Watson AI Impact 1 Billion Consumers." Utpal and I are officers within the ISSIP (International Society for Service Innovation Professionals) organization. 

In our prior post, we said, “AI may usher in a golden age of customer contributions to product and service innovations. Customer service interactions offer opportunities both during the interaction and then, in a more macro sense, from the organization’s ability to glean insights from trends across interactions. However, there is never a silver bullet -- new technology tools must be introduced alongside training for customer service and product development talent and new techniques that keep the knowledge flowing from customers to people in design roles.” Starting from a classic study of 169 of Denmark’s largest firms, we bring the ideas into the 21st Century to offer a set of best practices to help managers leverage AI to create tighter ties between customers and organizational innovators.

In the Beginning

Value from individual interactions and trends may have been easy for an organization when it was small. In the beginning, company founders personally answer customer service calls - there’s no one else to answer the phone. Founders can learn from these one-on-one interactions where their products and services need improvement or may have additional opportunities along the development roadmap. As the company grows, customer service becomes its own area and may have less connection with product development. Unfortunately, bad news generally doesn’t flow up the hierarchy well. Even good news or suggestions from happy customers may have more trouble making it to the design team if those groups are separated. Sales representatives may be too busy selling to share customer requests. Even when people are sitting next to each other, they may not know what knowledge might help their colleague. Innovation scholar, Andrew Hargadon, quotes a Boeing manager:

There are cases where the person who has the knowledge can be sitting right next to you and it goes unnoticed and you plow a lot of ground that you didn't necessarily have to. There's still a lot of duplication of effort. There just isn't any way that I know of to really make that happen so that all knowledge that has ever been done on something is available to the person at the time in which they need it. It's all a matter of getting the right knowledge into the right hands at the right time.

From 2001 to 2021

In 2001, researchers Nicolai Foss, Keld Laursen, and Torben Pedersen sent surveys to Denmark’s 1000 largest firms. The results showed that customer interactions offer value to innovation to the extent that teams and individuals have autonomy, communication across departments and levels, and incentives for knowledge sharing.

In 2008, Motor [a pseudonym] was founded in the UK based on pricing auto insurance based on driving behaviors collected via a telematics device. Researchers Helen Perks, Thorsten Gruber, and Bo Edvardsson report that the founders didn't do traditional market research given the idea was so new. Instead, the founders wanted to have an on-going dialog with their customers. By 2011, Motor had 33,000 customers and 100 staff. Perks and her colleagues offer this example of how customer interactions played a role in the evolution of the service:

... the idea for the development of bimonthly payment terms... was initiated by a high level of calls to the service call center from customers asking when Motor would be introducing different payment terms. A series of activities from Motor, including enduring adaptations of its financing procedures, ensued. Similarly, the development of a new process for renewals, with new driving behavior-based discount features… was triggered by the lead firm reacting to multiple customer enquiries direct to the call center and on Facebook.

Foss and his colleagues identified three organizational techniques to support the translation of customer interactions into innovations: 

• Employee autonomy to create the opportunity to interact with customers 

• Incentives plans that motivate employees to share what they learn from customers

• Communication practices that cross departments and hierarchical levels

The critical mechanisms are collecting valuable information, learning from the information, and making sure the information makes it into the innovation process. 

Enter Artificial Intelligence

Intelligent virtual assistants (IVAs, including chatbots, digital assistants, virtual assistants) can offer productivity and cost reduction. IVAs can also learn as they go, and as we will describe in our next post (link TBA), can work alongside their human customer loyalty representatives to offer alternatives and additional products or services.

Three Steps Between Customer Interaction and Innovation

IVAs are tireless documenters of customer issues where IVAs serve as the first point of contact for a growing number of customers. As the customer loyalty team tunes an IVA, human support agents receive fewer simple customer issues. What happens when a customer makes a suggestion or a segment of customers report concerns with a product or service? Do companies like “Motor” still gain ideas for innovation from interacting with their customers when an IVA is the intermediary?

Respond, Improve, Innovate

Teams monitoring customer interactions have at least three steps as IVA data comes in and the team members notice an aggregation of issues that the current forms of the IVA cannot handle: respond, improve, innovate. Here is an example demonstrating how value is enhanced through every IVA conversation and interaction with customers as the respond, improve, innovate process plays out.

Vodacom (Vodafone, South Africa)

TOBi, the Vodacom chatbot, was brought to the customer service team and initially could help with a few sets of simple customer queries. As the IVA support & maintenance teams noticed the types of questions customers asked TOBi, the team added new features and functionalities. Their process included steps that improved TOBi, but also a step for taking ideas back to product development:  

• Initial Response: Create a static website to quickly respond to customer’s questions if many queries are similar. (Consider a broad example: a mortgage company hit with many COVID-related questions might promptly put up a COVID FAQ webpage.) If questions are customer-specific, deflect to a customer service representative

• Improve:

  • Add new responses to the IVA for the “intents” underlying customers’ queries. For example, with TOBi, customers may want more to buy additional products (add an intent: Buy Bundles) or learn how to swap the pre-paid SIM cards themselves (add an intent: Do a SIM SWAP). 

  • Adding additional channels is another example of improvement based on customer feedback gained via IVA. Companies tracking requests in many developing countries may find preferences to use WhatsApp, given different fee structures for mobile devices.

• Innovate: Sometimes the customers’ request doesn’t exist (example: Buy Bundles). Adding the offering and the matching response for the intent is a chance to innovate based on customer information — just as company founders did when they were personally taking customer calls.

Autonomy, Incentives, Communication: Gaining Innovation Insights From Customers Interacting with Intelligent Agents

The innovate response shows that an IVA can help in monetizing new revenue opportunities -- but only if the structures from the research noted above are in place. We can leverage Foss and his colleagues’ findings to strengthen the Response-Improve-Innovate process in organizations, especially as their results speak to the teams working with IVAs. Innovation comes to the teams tasked with monitoring customer interaction data (and employees more broadly) if the organization offers:

• Employee autonomy to interact with AI-sourced data - opportunities to dig into the data

• Incentives plans that motivate employees to interact with AI-sourced data - perhaps award programs that share success stories

• Communication practices that cross departments and hierarchical levels - customer issues are rarely bound by traditional organizational boundaries. Responses to customer queries are likely stronger to the extent that they weave together the organization’s talent, technology, and techniques rather than more limited approaches.

These three suggestions are based on research done before IVAs and other forms of artificial intelligence were common. What does your experience using IVAs today suggest we should add to this list to better leverage customer data for innovation? The comments box is open below.

We set the stage for a series of posts (#2 here) looking at the role of artificial intelligence (AI) and customer interactions as they relate to product and service innovation. In this first post, we offer some fundamentals for customer-facing intelligent virtual assistants. Next up, we'll link these digital assistants to product and service development teams. On the horizon, look forward to considering how human representatives engage with their digital assistants to augment their human capabilities.

Thanks to Utpal Mangla, VP and Senior Partner, IBM, for joining me in this post. Under Utpal's leadership, his team recently achieved its mission of making "Watson AI Impact 1 Billion Consumers." Utpal and I are officers within the ISSIP (International Society for Service Innovation Professionals) organization. 

Artificial intelligence may usher in a golden age of customer contributions to product and service innovations. Customer service interactions offer opportunities during the interaction itself and then, in a more macro sense, from the organization's ability to glean insights from trends across interactions. However, there is never a silver bullet -- we must introduce new technology tools alongside training for customer service and product development talent and new techniques that keep the knowledge flowing from customers to people in design roles. 

Some Opportunities Offered by Digital Assistants

Intelligent virtual assistants (also known as chatbots/virtual assistants/digital assistants) are tireless at documentation and remain calm under fire. In some cases, people are more willing to disclose information to a chatbot. These attributes signal wide-ranging opportunities, especially in customer-facing roles.

We've seen that combining human customer service representatives with intelligence virtual assistants can double productivity with a 50% reduction in cost. Additionally, while customer care employees are often bound by scripts in their interactions with customers, artificial intelligence systems are allowed to learn and change responses based on broad access to customer interactions and outcomes. 

Fundamentals for Customer-Facing Digital Assistants

The fundamentals of customer centricity remain unchanged while working with artificial intelligence. Performing customer segmentation to identify the target audience, understanding the customer needs, and tailoring responses to match those customer's needs are all critical for the success of digital assistants, and all of us.

Based on over two decades of experience working with customer interaction systems, seven years experience building AI virtual assistants, and continued work in the development of these intelligent digital applications, we offer a checklist of 'best practices' to maximize the success and productivity of digital assistants from your customers' perspective -- this is foundational to the digital assistant being a resource to your product/service development team (Part 2 of this topic, coming soon).

1. Ease of Use: Seamless usability is critical for success. Keep it simple. Successful digital assistants are easy to work with, have reduced clicks, use voice interaction, and are concise in communication with the customer. For an example, see Vodafone's TOBi.

2. Datasets & Training: Data is essential to developing a truly conversational digital assistant. Digital assistants, like all of us, learn and become intelligent over time. As we deploy an initial set of "intents," it's important to ensure that the intents have been fully tested across various data sets. A digital assistant is only as good as the data it is trained against. Here's an example from Stanford University's Open Virtual Assistant Lab so you can see the issues in context.

   What is an intent? An intent is defined as a particular activity or objective that the customer has in mind when interacting with chatbots. Examples of intent include: Paying a Bill; Check Balance in Checking account; Return Products

3. Land & Expand Strategy: Start small and scale over a period of time. Start with a limited set of intents. Follow a phased approach to adding more features & functionalities. A small set of robust intents functioning accurately is more effective than a large set of intents that don't solve customers' needs. You want the customer to start liking the digital assistant and asking for more of it. Mostly for fun.

4. Context-Based Workflows: As virtual assistants take customers to next steps, it is important that the workflow successfully completes the specific activity or answers all queries tied to that transaction. Workflow can be an "intent" or a "combination of intents." When customers start doing more complex transactions, it is a reflection that they like the digital assistant and want to take greater advantage of new features & functionalities. The Zappos Customer Loyalty Team is amazing. If you're building a customer-facing digital assistant, the Zappos approach may be the holy grail for the combination of your digital and human (augmented) customer team.

5. Omnichannel experience: Successful design strategies provide a seamless omnichannel experience (mobile, voice chat, phone, social media, etc.), regardless of which platform they use. Virtual assistants integrated with the channels can help solve this problem.

6. Measurements: Measuring effectiveness is critical to success. Measurement should be done from both customer and business angles since they are closely interrelated. Some of the commonly used key performance indicators include Net Promoter Score, Customer churn, Customer effort score, First call resolution, Average handling time, Reduced cost per transaction. Note that Zappos uses Net Promoter Score as well as some other metrics that will stretch your thinking of your digital assistant's goals.

Next Steps Toward Innovation

You may well be on your intelligent virtual assistant journey. "As of 2020, 54 percent of customers have daily AI-enabled interactions with organizations, including using technologies such as chatbots, digital assistants, facial recognition or biometric scanners." Hopefully, your organization is aligned with the fundamentals above. Our next step is to extend the value of these AI interactions to your product and service innovation teams. Check back soon!

Thanks to Utpal Mangla, VP and Senior Partner, IBM, for joining me in this post. Under Utpal's leadership, his team recently achieved its mission of making "Watson AI Impact 1 Billion Consumers." Utpal and I are officers within the ISSIP (International Society for Service Innovation Professionals) organization. 

Example from Dentsu

Tom Davenport, Babson College Professor and author of the book, The AI Advantage, had the chance to talk with Max Cheprasov, Chief Automation Officer at Dentsu about Dentsu's efforts to "elevate human potential through automation." Like many organizations, Dentsu set up an automation Center of Excellence (COE) with the idea that these experts could identify and automate repetitive tasks throughout the organization. In a Forbes article, Davenport writes:

The CoE team, however, found only a relatively small number of large-scale opportunities. They began work on those, which each required several months to develop. However, in its search across the company the team became aware of a much larger number of potential projects—" a long tail of microtasks"—done by individuals that would never be able to be addressed by the CoE. As Cheprasov put it, "We needed to figure out how do we bridge top down and bottom up automation opportunities."

Top-Down and Bottom-Up

Davenport's last quote especially stands out. Recall the introduction of personal computers. Before personal computers, computing was very much a top-down effort. Organizations used mainframes and minicomputers (which weren't) for major tasks. Most office workers might have typewriters, calculators, or word processors, but limited access to computing. Our application of computing exploded when many more people had access and could leverage computing in ways specific to their own work.

Productivity and Other Advances Come From More Than Technology Alone 

Repeat readers of this blog will know that: We see in 3D. We need to Think in 5T™. As we take on different targets, we need to leverage all of our talent, technology, and technique -- aligned for the times. Erik Brynjolfsson, Seth Benzell, and Daniel Rock note in their 2020 report for the MIT Work of the Future Task Force: 

For a transformative new technology like AI, it is not enough to simply 'pave the cow paths' by making existing systems better. Instead, productivity growth from new technologies depends on the invention and implementation of myriad complementary investments and adjustments. The result can be a productivity J-curve, where productivity initially falls, but then recovers as the gains from these intangible investments are harvested.

Before we gained the value of electricity, internal combustion engines, and other general purpose technologies, we had to innovate across organizational design, supporting infrastructures, and work practices.

The 2020 MIT report offers as part of its conclusion: 

...technological advances typically don't translate into improvements in productivity unless and until complementary innovations are developed. These include many intangible assets such as new business processes, business models, skills, techniques, and organizational cultures.

Many Hands Make Light Work

The MIT authors point to national-scale policy efforts in support of these changes, but we offer that many hands make light the work. 

As Dentsu found, there are opportunities to take on top-down and bottom-up efforts at the same time -- jumpstarting the expansion of new business processes, business models, skills, techniques, and organizational cultures. Jessica Berresse, a "citizen developer" at one of Dentsu's subsidiary companies, Carat, is quoted in the Forbes article, "Nobody wants to automate for the sake of automating; in some cases we might identify enough improvements that the team might not need a bot after all." Her colleague Erika Shand agreed: "We almost always do some process improvement before automating the process."

In our experience, having worked with organizations across multiple industries, one thing stands out. While top-down is critical for alignment, momentum, and having the entire organization rowing in the same direction, bottom-up is equally essential. People on the field have a much better view of whether day-to-day processes are critical or unimportant. People doing the work are best positioned to advise or take action on which steps from their daily functions can be optimized and automated. 

Role of Top-Down Activities

However, it is vital to create an overarching culture of trust. If employees worry that automation and new technologies will make their jobs redundant, few will participate in automation initiatives. That's where a top-down approach is critical. Leaders must offer crisp messaging and support to employees at all levels. Clear communication and actions showing that new technologies should complement employees and enable them to move up the productivity ladder will provide confidence at all levels. 

Experience shows that getting employee alignment is critical for long-term success. We have seen companies making investments and rolling out 'Achievement' and 'Bravo' awards to teams that proactively support this effort. Amplifying these successes creates a healthy culture of cooperation and collaboration.

Creation of CoEs or Centers of Competency (CoC), like those noted at Dentsu, are key mechanisms towards getting an organization to leverage the best of talent, technology, and technique -- working from the 5Ts. Successful centers have a combination of tools and functional competency. For example, a center focused on Robotics Process Automation (RPA) will have the subject matter expertise of technical skills required to perform a variety of automations. This center of competency will then work with subject matter experts from various business functions (finance, procurement, human resources, supply chain) to assist in automation at all levels.

The Value of Bottom-Up

The centers can encourage employees to share ideas for both large-scale (top-down managed) automations and those they take on themselves. 

For large-scale implementations, employee contributions are narrowed down to few to move from ideation to proof of concept stage. The center can support successful proof of concepts with full-blown projects leading to deployment. Centers can apply agile methods where every sprint has a clear set of “customer” metrics to define completion before moving to subsequent stages. Agile practices ensure that organizational automation goals stay in focus -- before work goes too far. 

When individuals build out their own tools, perhaps using "no-code" automation platforms offered from the top, centers should be following up to be sure these new resources are available to all. 

Showcasing successful engagements, big or small, in leadership and employee forums bring far more value than cost. These showcases are opportunities to share the specifics, trigger new ideas, and build on the culture we all need to improve our work through automation effectively. 

Let us celebrate with you: Please share your examples in the comments below.