So what’s the trick? If you’re having trouble identifying a scenario for training, stop focusing so much on the content. Shift your focus to the people who have to do something related to that content. Every rule, regulation, system, and process has to be implemented by actual human beings. Even if the regulations are boring, the people who have to apply and are affected by those policies aren’t boring. If you focus on the people and the decisions they need to make, then you’ll find it easier to write scenarios. Ultimately, this can help us create training that improves learner engagement and outcomes.

Worst case scenario

One strategy you can use for many types of training is the worst case scenario. Tell the story of what happens to someone who doesn’t follow the rules, showing the catastrophic consequences. Sometimes I use this at the beginning of training to “hook” learners’ attention. Then, you can back up and show how to prevent that problem.

For example, the ORI interactive video training The Lab begins with the words, “It was a bad day. It started with just one reporter…” This ethics training starts with news reports discussing research misconduct. In the training, you can pick a role in an “alternate reality” to attempt to prevent that misconduct from happening.

In that example, the focus of the problem isn’t on the research integrity, but on how that affected the people involved. One person lost his job; others had to deal with the effects of lost reputation. You watch the uncomfortable interviews about the fallout from these poor decisions. The training starts with that focus on people. Later, it asks more specific questions about research integrity, but only after learners have a reason to care about the training.

Compliance training: the boring way

Compliance training can be the bane of an instructional designer’s existence. But let’s face it—if it’s boring for us to create, it’s probably boring for the learners too, right? We have to find the people involved and tell their stories.

For example, say you need to create training on wage and hour laws. The boring way to create the training would be to cite the regulations. In the US, that’s the FLSA.

The federal overtime provisions are contained in the Fair Labor Standards Act (FLSA). Unless exempt, employees covered by the Act must receive overtime pay for hours worked over 40 in a workweek at a rate not less than time and one-half their regular rates of pay. There is no limit in the Act on the number of hours employees aged 16 and older may work in any workweek. The Act does not require overtime pay for work on Saturdays, Sundays, holidays, or regular days of rest, unless overtime is worked on such days.

The Act applies on a workweek basis. An employee’s workweek is a fixed and regularly recurring period of 168 hours — seven consecutive 24-hour periods. It need not coincide with the calendar week, but may begin on any day and at any hour of the day. Different workweeks may be established for different employees or groups of employees. Averaging of hours over two or more weeks is not permitted. Normally, overtime pay earned in a particular workweek must be paid on the regular pay day for the pay period in which the wages were earned.

Excerpted from the FLSA explanation of overtime pay

Compliance training scenario

In order to make this not-so-boring, you first need to identify the important people. Let’s say the audience is retail managers, so that’s the primary focus. Include the employees in the scenario because that helps provide realistic context.

Next, identify the specific problems. The SME tells you they’ve been having problems with managers not tracking and paying overtime correctly. You can ask the SME and stakeholders more questions to gather information to create the scenario.

Based on the information you gather, you might draft a scenario question like this:

Instead of an abstract question about overtime rules, this asks the learners to apply the rules to a specific scenario. Scenario questions like this require plausible distractors, but making people think makes the training less boring.

In that example, you could also include an option for “I’m not sure, let me check with HR.” That option could provide an explanation of the rules. Sometimes, you do need to list the actual policy in compliance training. However, if you can include that policy with a scenario, it gives people a reason to look up the information. Instead of pushing information to learners, you give them a reason to pull the content themselves.

How do you deal with large amounts of text?

In some training, you can’t get away from large blocks of text. Some job roles require working with text, so practicing important skills means having big blocks of text on the screen. While we should try to rephrase regulations into plain language where possible, what if the job itself requires reading and applying different regulations?

In that case, you need to practice that skill. You’ll include the regulation text, but you’ll put it into a realistic context where applying the regulation matters. A story where people experience consequences if you don’t follow the policies suddenly makes the content less boring.

Regulations example

One of my past projects involved training advisors on how to support international students. Part of their job is understanding regulations so they can explain and advise students. We used a series of case studies to give learners numerous practice opportunities with a wide range of problems.

In this example, the advisor was working with a student facing disciplinary action and possible loss of a visa. In the case study, they needed to determine the conditions of the regulations and potential consequences. Therefore, one of the activities was to review the regulation and identify the important text.

While I can’t share the full version of this with the proprietary content, you can get an idea of how the activity worked even with the text replaced. This is a practice activity for one step in a real-world skill.

Connect regulations to people

The regulations activity above was one piece of a larger scenario.

1. A story about the student’s actions and situation
2. Two advisors discuss how to help the student
3. Review the regulations
4. Two advisors discuss how to apply the regulations using a framework taught earlier in the course
5. Multiple choice questions about actions to take
6. Additional information about the student in the story
7. Decide whether to take additional action based on the new information

I didn’t show the regulations in isolation; I connected them to the people affected by them. The regulations on their own would be extremely dry and boring.

In the context of the case study, understanding the regulations meant determining if an international student could maintain her visa or not. That’s a story about the people. If you didn’t apply the regulations correctly, then the characters in the story were affected, including one of them potentially having to quit school and leave the country. That’s a consequence with some emotional resonance for advisors who work with students.

More on scenarios and compliance training

• Create Motivating Compliance Training
• Make Learners Care about Compliance Training
• Mini-Scenarios for Assessment
• Converting to Scenario-Based Questions
• Plausible Distractors for Compliance Training Mini Scenarios
• 7 Tips for Writing Realistic Wrong Answers in Branching Scenarios

Originally published 10/26/21. Updated 7/27/26.

The post Scenarios for Boring Training Topics appeared first on Experiencing Elearning.

You can try the scenario with the updated images now. This is more of a beta version than an alpha version, but there still may be some problems.

Reference images and planning

Reference images are key to getting consistent characters across multiple images. I started by generating images of each character looking at the camera; these are my clean reference images that I refer to later. These all look very posed because I prompted for a “studio photo,” but that’s fine since these are just reference images.

Since I was already working with Claude on the updated user interface, I prompted Claude for a list of the images and poses I needed. That saved me some time in my planning. I also generated an image of a conference room as the setting for the initial team meeting in the scenario. I named all of these reference images with the character names.

Generating scenes with multiple characters

Assembling scenes with multiple reference images is really easy in Flora. You just type your prompt and add @ before the name of the image. That’s why I named each reference image with the character names.

Style: Editorial photo
Subjects: @Samantha @Jake @Alex
Setting: @Small conference room, laptops on the table
Action: Having a meeting, discussing

In the screenshot of Flora below, you can see the thumbnails of the reference images for each character plus the setting.

Changing camera angles

To provide some variety in the scenario images, I changed the camera angle for some images. As you can see in these two images, they’re the same scene, but with the camera angle changed.

I used Flora’s image tool for changing the camera angle to accomplish this change. That uses a model called Qwen Image Edit that has special options for directing where the camera should be. As you can see below, you can set both horizontal and vertical angles plus a Zoom. That means I have a lot more control than just prompting Nano Banana to change the camera angle (which I never have much luck with).

Unfortunately, while Qwen does great overall at changing the camera angle and keeping objects pretty consistent from different angles, it didn’t do well at all at keeping the characters consistent. They look sort of like my characters, but they lost a lot of detail. The people have that very airbrushed AI image look that I’m trying to avoid. That meant I had to do another step to prompt Nano Banana to replace the people in this image with the characters from my reference images.

Time and cost for scenario image creation

I spent about 5.5 hours generating the images for this scenario. While I can batch image generation in Flora to speed up the process, that process didn’t work with this project. I needed to get the scenes right and then build from there, so each image built on the previous one. Once I got a few scenes right though, I maybe could have done some batches to get multiple poses of people talking and listening.

I could generate characters with transparent backgrounds and assemble them into scenes, the way we all did with cutout images in the past. Sometimes that might be faster, although I think it would have taken longer for this particular project.

My total time includes some time where I was task switching though. Image generation is usually fairly fast, but I still find myself switching to check email or my phone while waiting. Am I always switching right back to the image generation as soon as it’s done? Probably not. I don’t have a solution for that right now, but it’s something I observe in my work.

My cost for generating 100+ images was about $9. Combined with the cost of redesigning the UI with Claude, my cost is about $15 total.

Over 100 images generated

While there are only 22 images in the final product, I generated over 100 images in Flora. All of the edits and regeneration means I’m only keeping about 20% of the images I generate. I hear similar ratios of 20-40% from other people who use AI for media generation. Image generation is about your prompting and ideas at the beginning, but also about your judgment and refinement throughout the process. Don’t believe any hype about how AI is a magic button that you click once and get great results out of; there’s a ton of refinement, iteration, and sometimes manual editing involved.

Interactive video

I’ve thought about changing this to an interactive video scenario. There’s a fair amount of dialogue here that would lend itself to video. (Although as I’ve been rereading this scenario, I see a number of places I’d like to edit.) I might do that as a future update. I’m sure the time and cost will be quite a bit higher though; video generation is a lot more expensive and time consuming. It might be a good project to build my skills with AI video though.

What do you think? Would you like to see this scenario as a video? I could do some more of these working out loud posts to show my process.

Find any glitches?

If you find any glitches in the scenario, please let me know! Generating the images took a lot of time, so I haven’t spent as much time testing as I’d planned. I suspect there may still be some issues for me to resolve.

Looking for more?

I’ve published a number of articles on AI image generation, particularly around character images.

• Updating a Twine Branching Scenario with AI – Part 1 (My previous post about updating this scenario)
• Speed Up Character Image Creation with Flora
• Comparing AI Image Generation Tools
• Testing Freepik Spaces for Character Image Generation (Freepik is now Magnific, but the basics of this post are still accurate.)
• Nano Banana (Gemini) Character Image Experiments

You can also check out all of my posts about AI and instructional design as well as my growing collection of over 70 posts on scenarios and storytelling.

The post Updating Scenario Character Images with Flora appeared first on Experiencing Elearning.

The original scenario

You can try the original scenario to see where I started. Pay attention to the project status dashboard at the bottom and how it changes based on the decisions you make. If you want to see the branching structure and learn about my process for this first version, check out my previous post Project Management Simulation: Modeling Tradeoffs in a Scenario.

The updated scenario (a work in progress)

You can also try this updated version of the scenario. Note that this is a work in progress; most of the images are placeholders, and I haven’t fully tested everything in the new UI yet. Some elements may be broken or behave unpredictably. Consider this an alpha version.

Initial pass updating the UI in Claude

From Twine, you can export to Twee format. Without getting too far into the technical details, just know that Twee format can be saved as a .txt file just by changing the file extension. Claude can understand Twee format in a text file, so that’s typically how I work with Claude and Twine together.

Here’s my initial prompt:

This is a branching scenario I built in Twine for practicing decision-making for project managers, specifically about the trade offs between cost, quality, and time in projects. I'd like to refresh it with a more modern design. The attached file is the Twee format (saved as a .txt file).

What to keep:

    All the text of the dialogue and choices
    The elements of the project dashboard (elapsed days, cost, etc.)
    Overall color scheme

What to change:

    Make it responsive so it adjust for smaller screens. The current dashboard doesn't work on phones.
    Add placeholders for images (I'll generate some new ones--AI image generation has improved a ton since 2024).
    A way to add those images (maybe just put everything in a folder with the right file names? open to better ideas)
    Update the overall styling for buttons and UI to be more modern and clean

The final output should be HTML that I can upload for my blog and website.

Do you have any questions about the output and what I want before you get started? If not, you can build it and we'll iterate from there.

Iterations

As is always the case in working with AI, I did some iterations back and forth to make improvements. The initial layout Claude designed was a big improvement from my original, but the color contrast was really low in some areas. The buttons weren’t as obviously clickable as I wanted, and they had an odd hover effect that changed the size. The dashboard was responsive, but it also took up a lot of space on small screens.

So, I went back and forth. The good news is that you can do all of this vibe coding without necessarily knowing the technical code that needs to change. However, you need to be able to clearly describe what you want, even if it’s not in technical language. Vague directions aren ‘t as effective.

Then, although I started with my own improvements for the iterations, I also asked for ideas with this prompt: “What other suggestions do you have to make this better?”

Claude suggested several additional improvements:

• Better accessibility
• A running decision trail
• Animated metric changes
• A richer ending summary
• Progress or phase indicator
• Some other small polish items

I prioritized the accessibility improvements, decision trail, and progress indicator.

UI and structure improvements

Through those iterations, I got to the version you see now. I had Claude summarize all of the changes, but its summary was wordy. So, you’re getting my bullet points instead.

• Platform and structure: This is now a single self-contained HTML file with Javascript rather than using the Twine and Harlowe format.
• Responsive: On desktops, the project dashboard sits in a sticky sidebar. On phones, it collapses to s compact top bar. The dashboard metrics were reformatted as cards.
• Images: Claude replaced the images with placeholders; that’s the next part I’ll work on.
• Visual and brand styling: My overall original color scheme was retained, but the visual elements were modernized with a card-based design with rounded corners and subtle shadows.
• Accessibility: A “Skip to decisions” skip link was added, and the dashboard was given a labelled landmark. The meters have concise ARIA labels. The focus now moves to the top of each new passage on navigation. All interactive elements have visible focus rings for keyboard users.
• Your path and progress: A running log of your decisions appears below the decisions so you can see the cause and effect of your choices. At the bottom of the dashboard is a phase tracker to show progress without pretending the branching is linear or that all the paths are the same length.

Cost of using Claude

I used Claude through my Poe subscription. Poe gives me access to all the major LLMs plus a number of image, video, and audio tools for $200/year. My costs may not reflect what you’d pay working in Claude directly.

For the initial build and all of the iterations, the cost for my tokens was $5.75. I worked on this off and on while also working on another project, so I don’t have a great time estimate. It was probably about 60-90 minutes of work.

Next post: Images in Flora

This post is already over 1000 words, so I’m breaking it into a series. In my next post about this project, I’ll share how I used Flora to generate new images.

Check out my collections of posts on AI and Instructional Design and on Storytelling and Scenarios for more.

---

Upcoming events

Crafting Choices That Challenge: Designing Scenarios for Authentic Practice. July 15 at 12PM Pacific / 3PM Eastern. Register for this free webinar hosted by Training Mag Network.

Scenario-Based eLearning Design Certificate: Strategies to Engage, Motivate, and Transfer Skills. 3 online sessions starting August 5. Register now; only a few spots left!

Creating High-Quality AI Media: Prompting, Scripts, and Consistency. October 8. Register for the ATD AI Intensive.

DevLearn

Branch Smarter, Not Harder: Naming Conventions, Variables, and Bottlenecks in Storyline

• November 3, 2026 at 9:20 AM
• CE01: Storyline & Rise Pro Lab

Cohesive by Design: Generate Consistent AI Icons, Illustrations & Characters

• November 4, 2026 at 10:00 AM
• BYOD (Bring Your Own Device)

The post Updating a Twine Branching Scenario with AI – Part 1 appeared first on Experiencing Elearning.

Vibe coding and accessibility

The Vibe Coding Crisis: Why AI is Manufacturing Accessibility Debt

Jacob Wood shares examples of technical debt for accessibility caused by using the messy code that vibe coding generates. Yes, we can build activities and websites quickly, but how are we going to make it accessible? If we ignore accessibility and don’t plan for it from the start, we’re going to accumulate a lot of cleanup work later.

So here’s a quick tip: When vibe coding anything, remind your friendly neighborhood AI, “The first rule of ARIA is that no ARIA is better than bad ARIA.”

Learning friction

Why AI Needs Vygotsky: The Case for AI-Based Intentional Friction – Learning Guild

LLMs can give nearly instant answers with almost no effort–but effort is what helps us learn and grow. This article connects classic learning science of Vygotsky and the ZPD to how AI can cause harm through cognitive outsources and provides principles for designing for intentional friction.

The absence of “desirable difficulty” or friction in AI interactions is among the most serious concerns for learning and instructional design experts today. This concern is not due to tool speed, but rather because the lack of friction bypasses or eliminates essential stages of the learning process that strengthen human cognitive and neurological foundations. When machines respond effortlessly, the natural learning pathway described in Vygotsky’s ZPD and scaffolding is disrupted. While this may seem “efficient” in the short term, over time it can undermine higher-order cognitive skills such as problem-solving, critical thinking, and creativity.

—Atefeh Ferdosipour

AI trends and L&D teams

The Anatomy of a Modern L&D Team [2026 Edition]

Ross Stevenson shares research, trends, and outlook for how roles in L&D have shifted and are continuing to change. What do those roles look like moving forward? What skills should L&D professionals focus on?

Recover unpaid invoices

Recover Your Unpaid Invoices

I’ve had several conversations with other freelancers and consultants recently about clients not paying their invoices. It’s usually not enough money to justify hiring an attorney or sending them to collections, but it’s also painful when you work for yourself. This is an AI-supported tool to generate and send a certified letter and follow up until you get paid. Will it work? I don’t know. For $50, I’d probably try it myself if I had an unpaid bill. I might even pay the extra for an attorney to send the letter on their letterhead.

Medical imaging with Midjourney

A New Era of Midjourney

This is all very early and not in production yet, but Midjourney is working on using their expertise working with image data into developing a body scan machine to provide medical imaging. I think a heavy dose of skepticism is smart until it’s actually in use and we see results, but I like the idea of using AI to generate images that help doctors and patients make more informed decisions.

---

Upcoming events

Crafting Choices That Challenge: Designing Scenarios for Authentic Practice. July 15 at 12PM Pacific / 3PM Eastern. Register for this free webinar hosted by Training Mag Network.

Scenario-Based eLearning Design Certificate: Strategies to Engage, Motivate, and Transfer Skills. 3 online sessions starting August 5. Register now; only a few spots left!

Creating High-Quality AI Media: Prompting, Scripts, and Consistency. October 8. Register for the ATD AI Intensive.

DevLearn

Branch Smarter, Not Harder: Naming Conventions, Variables, and Bottlenecks in Storyline

• November 3, 2026 at 9:20 AM
• CE01: Storyline & Rise Pro Lab

Cohesive by Design: Generate Consistent AI Icons, Illustrations & Characters

• November 4, 2026 at 10:00 AM
• BYOD (Bring Your Own Device)

The post Vibe Coding, Learning Friction: ID Links 7/7/26 appeared first on Experiencing Elearning.

As a side note, I also just realized that Nano Banana (the image model in Gemini) can make mockups. Here’s the very simple prompt I used:

Make a photorealistic mockup of [the screenshot] on a laptop on a desk in a cozy home office with #adc3df walls. A cup of coffee is on the desk. A bookshelf is visible in the background. No books on the desk or people or plants. 

Original data error spotting activity

I created a similar activity for an introductory data analysis course relating to a learning objective on spotting common errors in data. I’ve changed the questions, data, and other details so I’m not sharing any of my client’s actual information. You can try the activity yourself below (although the spreadsheet data means this activity works best on a larger screen).

Embedding the activity directly in my blog post has been challenging because of the variable height of the activity (plus, embedded html doesn’t play nicely with email). You can view both versions as Rise blocks or open the activity in a new tab.

This activity isn’t the flashiest use of AI, but it’s useful. Users get a way to look at sample data and practice finding errors, which is exactly the skill I needed to support. It’s fun to vibe code things like arcade games, but most of the time workplace training benefits from activities that look like people’s work.

How I created this activity

I created this vibe coded activity in Claude. As I observed after Jeff Batt’s vibe coding session at Training 2026 earlier this year, vibe coding really can be done by anyone now. The key skill is being able to clearly describe what you want and to provide the AI with specific feedback to iterate and improve. Your skills in describing interaction and giving clear directions matter more than your technical skills.

The good news is that instructional designers already have those skills, especially those of us who have experience writing storyboards to pass off to an elearning developer to build. When I started as an ID, I created PowerPoint storyboards and handed them off to our team of Flash developers. That meant I had to very explicitly note how I wanted interactions to work. If I didn’t write clear directions, then the Flash developers couldn’t understand what I wanted and build it. Vibe coding feels very similar, except now it’s the AI doing the role of that custom development.

My prompt to create the activity wasn’t technical; I focused on the content and interactivity.

I'm working on a course on data analysis 101 for [the role in my client's audience]. I need some examples of data errors for some "spot the error" questions in each of these categories.

Create a web-based interactive activity for each of these types of errors. Include some sample data that would be related to [client's industry--changed for the example above]. For each sample, users will click on the mistake in the data. Then, the feedback will confirm if they found the error (or errors) and tell them what type of error this was.

The activity must be a self-contained HTML file with inline CSS and Javascript so I can embed it in an Articulate Rise block.

My prompt continued by listing the four types of data errors and some of the tips from the course content that learners receive prior to this activity.

Iteration and testing

After I got the results, I did some iteration and testing.

• Changed the question labels to numbers; the original version said what kind of error it was, which made the activity too easy.
• Adjusted the instructions to avoid giving too many hints.
• Added follow-up questions about the type of error.
• Changed the colors to match my client’s branding.

All of that iteration happened through ordinary chat with Claude. Obviously, I could build something like this in Storyline, and I have done so in the past. However, this kind of activity is really tedious to build with multiple hotspots or rectangles and triggers. This took about 45 minutes to create, test, and iterate in Claude. That’s saving a significant amount of time.

Improving the accessibility

Unfortunately, I screwed up. I didn’t include any requirements for accessibility in my initial prompting and testing. So, I asked Claude if this activity would meet WCAG accessibility standards and if a screen reader user could use it. Claude replied, “Honest answer: as written, this activity does not fully meet WCAG 2.1 AA, and a screen reader or keyboard-only user could not complete Part 1.” So, I went through some more iteration to improve the accessibility. This still may not be fully accessible for all users, but it’s much more accessible.

This is where my big insight comes in: I really should have prompted for accessibility right from the start. I created extra work and testing by not asking for it in the first place. Fortunately, even though I did mess up by not planning for accessibility at the beginning, it didn’t take Claude that long to rework everything. Claude can build accessibility features, but you have to ask for them.

Accessibility problems and fixes

Claude helpfully suggested making a table with a side-by-side comparison of the problems and everything needed. While I write my blog posts myself with my human brain, I copied this table straight out of my chat.

More accessible version

You can try the vibe coded activity with improved accessibility below. From a user perspective, if you use a mouse, not much looks different. But if you click one question and then tab through the activity, you’ll see that you can now access each cell in the table with a keyboard. You can also see the difference in how the activity previously conveyed feedback through color alone previously, but now also marks answers with an X or check mark.

More on AI

Check out all of my posts about using AI for instructional design for more posts where I show my work (the good and the bad) like this.

---

Upcoming events

Crafting Choices That Challenge: Designing Scenarios for Authentic Practice. July 15 at 12PM Pacific / 3PM Eastern. Register for this free webinar hosted by Training Mag Network.

Scenario-Based eLearning Design Certificate: Strategies to Engage, Motivate, and Transfer Skills. 3 online sessions starting August 5. Register now; only a few spots left!

Creating High-Quality AI Media: Prompting, Scripts, and Consistency. October 8. Register for the ATD AI Intensive.

DevLearn

Branch Smarter, Not Harder: Naming Conventions, Variables, and Bottlenecks in Storyline

• November 3, 2026 at 9:20 AM
• CE01: Storyline & Rise Pro Lab

Cohesive by Design: Generate Consistent AI Icons, Illustrations & Characters

• November 4, 2026 at 10:00 AM
• BYOD (Bring Your Own Device)

The post How I Made an Accessible Vibe Coded Activity appeared first on Experiencing Elearning.

This post contains affiliate links. It doesn’t cost you anything extra, but I earn a small percentage when you buy through these links.

Generalist or specialist

Generalists do a little bit of everything. This is pretty common in instructional design and elearning roles, especially in smaller organizations. Generalists have a broad set of skills. You can have a lot of variety in your work when you’re a generalist.

True specialists have deep skills in one or two areas, but tend to have a weaker base of other related skills. Elearning developers are often specialists; they work best when someone else provides them with a storyboard or script that they can be creative in building and development. AI opens up the possibilities for new specialties in AI media creation or working with agents. Larger teams are more likely to hire specialists who focus on a particular skill or part of the process.

Unicorn or comb

What employers ask for in job openings is often unicorns: people who have deep skills in all the areas. In practice, real unicorns aren’t very common. The quote below is about UX design, but this framework applies to instructional design as well.

Aim towards unicorn, realistically end up as a beautifully misshapen comb

The reality is that to be a unicorn is a worthy goal, but most people won’t get there, and that’s fine! First, find something you’re good at and which contributes towards the field you’re interested in, then you have at least something to fall back on and can bring value to a broad range of teams.

Sophie O’Kelley in Generalist versus specialist? How about a misshapen comb?

Rather than being a unicorn, it’s more common to be a bit of a “misshapen comb.” That means you have the broad base of skills that give you a little knowledge about many topics and help you interact with other specialists. You also have a couple of deeper skills, maybe at different depths. An elearning developer might have deep skills in Storyline, plus moderate skills in AI media creation, UX, graphic design, and a little Javascript, along with a foundation of instructional design principles.

The idea of the comb is related to Cammy Bean’s explanation of broad and deep T-shaped skills in her book, The Accidental Instructional Designer.

It’s effectively a hybrid: you have that broad base of skills as a generalist that makes you an asset for working across teams. You also have some specializations of various depths. That combination of specialist skills are what set you apart from every other generalist out there.

Good organizational fit

Generalists

Generalists have traditionally lots of options for jobs in ID. They can contribute to a team or work as a department of one (fairly common in L&D). Being a generalist is how people often start out in the field of instructional design because you get experience across a broad range of skills.

But being a generalist also can be challenging because you don’t have as clear of a way to stand out in the job market. Your skills may need to look more like the “misshapen comb” from the article I quoted earlier; you have a broad base of generalist skills plus several moderate skills and one or two deep specialties.

Everything I hear from folks looking for jobs right now is that the market is rough, and the competition is hard. Even people with years of instructional design experience and credentials are having a hard time. Entry level generalist positions in ID were hard to come by even before AI, and it seems to be getting harder now as AI redefines roles and other pressures increase competition for jobs.

Specialists

The bad news is that means you may need some sort of specialization to stand out. The good news is that AI is so new that even if you don’t have a ton of experience in ID that almost nobody has more than a few years head start building their skills in AI. There are opportunities to create new specialties for yourself as differentiators.

For example, five years ago, AI image generation didn’t exist. But now I’m not only using AI images for my work, I’m getting paid to teach people about AI images too. It’s taken a lot of work and sharing my expertise for free to get to this point, but I created a specialty for myself. That specialty means I fit with some organizations better than others.

If you’re a true specialist who wants to work in only one area, you may need to be more discerning in searching for jobs or projects that align with your specialty. Larger companies are more likely to have larger teams where different members have different specialties. Elearning vendors, the companies that specialize in creating elearning for other organizations, are other good places to find more specialized roles.

In the past, elearning development specialists seemed to have an easier time finding work, especially as freelancers. Organizations were always looking for developers who can build elearning, even if they have an internal team of instructional designers. Development is the easiest part of the process to outsource to a freelancer or consultant. That might still be true today, but it’s unclear to me right now how that will shift as organizations move away from a short list of traditional authoring tools and into a wider range of authoring and AI tools. Developers with skills using AI tools may have an advantage, at least in the short run.

I know people who want to focus primarily on writing and stay away from development or technical work. Job searching can be a trickier if you want to focus primarily on strategy, analysis, design, and storyboarding. You have to look for those larger teams where roles are specialized, or at least organizations who regularly outsource development work. Those roles are increasingly challenging to find though. Jobs focused on a narrower range of tasks are more at risk from AI. Shifting yourself closer to the business problem and into more performance consulting may be one way to avoid working with development.

Hybrid generalist/specialist

A stronger position is that “misshapen comb” or hybrid generalist/specialist. Combining a broad range of generalist skills means you’re adaptable and can do a bit of everything. Generalists who do many different tasks are harder to replace with AI or automation, and they’re good at combining skills. But there are so many generalists out there that it’s hard to get a job if your differentiator is something like, “I used to be a teacher, and now I’m an ID.”

Pick one skill you’re interested in learning more about: learning science, some aspect of AI, video, UX, scenarios, games, customer enablement, onboarding, etc. You don’t have to learn everything and have deep skills in all of it, but growing your skills in specific areas makes it easier to find roles that use those skills.

Questions to ask

Many people treat job interviews as a one-sided evaluation of your skills, instead of a two-way review for good fit. When you interview, asking questions helps you figure out the role and the culture.

Ask questions like these to learn more about the position:

• What does a typical day or week look like in this position?
• Thinking about the people who have been really successful in this role in the past, what sets them apart from people who are “just OK” in this role? (If they say how pretty they make PowerPoint, but you know you want to focus on performance consulting, you know it’s not a good fit.)
• What’s the most challenging part of this position?
• Tell me about the roles in the rest of the team. Who else would I be working with?
• How do you determine which projects get developed and what projects have priority?
• How do you use AI in your instructional design processes?

If you ask those sorts of questions, you should get a better feel for the job and the organizational culture. Even interviewing with an elearning vendor as a subcontractor, you could ask some of these questions. The answers will help you figure out how much is just order taking from clients and how much is consulting.

More on Instructional Design Careers

Check out all of my posts on instructional design careers, including these:

• Is instructional design the right career?
• Teacher to Instructional Designer: Interview Questions
• Instructional Design Hourly Rates and Salary
• Instructional Design Portfolio Resources
• Instructional Design Careers and Freelancing Presentations and Podcasts

Originally published 11/19/2019. Updated 6/18/2026.

The post Finding a Good Fit in Instructional Design appeared first on Experiencing Elearning.

Obviously, I’m not a lawyer, and nothing I say here is legal advice. This is my understanding of fair use and copyright. Check with your own attorney if you have legal questions.

My goal here isn’t to convince you to use AI images if you’ve already decided it goes against your ethical values. If that’s you, I respect that, and I’m not here to change your mind. I’m writing for those who are using AI images and want to do so carefully.

Training data

I know lots of folks who oppose AI, and AI images particularly, because of the training data. I think it’s totally reasonable to use Adobe Firefly for image generation because it was trained only on licensed stock and public domain images. Because they have permission for everything they used to train their model, that’s the safest option. That’s an easily defensible ethical stance.

Most AI image generation models were trained on a much broader set of data. That includes photos and art that are available online but not in the public domain. Just like LLMs were trained on copyrighted text, image generation models were trained on copyrighted images. That means AI companies are relying on a fair use argument.

I’ve seen a range of legal opinions on AI training. This is clearly an area where the law is still evolving. So far, the decisions support training models on copyrighted materials as long as they were legally obtained. Anthropic is paying a settlement for using pirated books to train on, but the books they legally bought were allowed under fair use. That’s where I generally fall too; as long as the training data wasn’t pirated, training on a broad range of publicly available images is fair use.

I don’t follow the legal landscape in the EU as much as I do in the US. However, it looks like the EU AI Act will require more transparency on data sources. (Any readers with more insight on the EU, feel free to comment and correct me if I’m wrong about that.) I hope we do get more transparency on training data so people can make informed choices about which tools they use or avoid.

Transformative use

Fair use is the US doctrine that allows some use of copyrighted content under certain circumstances. Fair use is very “squishy” though; it’s not a clear cut rule. It’s not as simple as saying there’s a clear line based on any single factor. You have to weigh four factors, and judges sometimes decide individual cases differently even with similar circumstances.

If someone tells you that something is definitely not fair use because it uses the whole source while ignoring the other three factors, be very skeptical. That’s not really how fair use works. Yes, the amount of the source material used matters, but that’s only part of the question.

One of the other four factors is the purpose and character of your use of source content. That’s why parody and satire are often allowed even of copyrighted or recognizable sources; that’s a protected purpose that constitutes fair use. The judge in the Anthropic case ruled that AI training is a transformative use; it transforms the original into something else. Because the character of the use is transformative, it’s fair use.

For my own work, that ruling means I’m less concerned with the input for AI and more concerned with the output. Because of course you can make things with AI that are copies (or very close to copies) and aren’t really transformative. Just because an AI image model lets you generate something obviously based on Star Wars or the Simpsons doesn’t make it transformative enough to be considered fair use. And regardless of the legal landscape, transformative use is more ethically defensible.

Don’t emulate living artists

One of my own guidelines for using AI image generation is that I don’t use it to emulate the style of any single living artist. You want to make a version of Starry Night with a cat in it? Cool, go for it! Van Gogh isn’t alive to be affected by it. But any artist who is alive now, who you (at least hypothetically) could hire to create something? Nope. While it was trendy to do Studio Ghibli style remixes for a while, I opted not to participate in that.

Copying the style of a living artist potentially affects the market for that person’s art—and that’s another of the four factors weighing against fair use. Plus, that use doesn’t feel right to me. Copying a single style doesn’t feel transformational. Plus, why use these tools to simply copy when they’re capable of more?

Instead of emulating a specific artist, use AI to develop a new style. That’s one of the reasons I still use Midjourney even though other image generators are now better at consistency and prompt adherence. Midjourney is the best for creating new styles and mashing up elements of multiple images together.

It’s like the old academic joke: if you copy from one source, it’s plagiarism, but if you copy from a bunch of sources, it’s research. AI image styles feel similar. If you copy from one artist, it’s plagiarism. If you copy from a bunch of artists, it’s transformative and fair use.

AI images can’t be copyrighted

Like anything else produced by AI, AI-generated images can’t be protected by copyright unless a human makes substantial changes to it. Work that is primarily guided by the decisions of a human but is “AI-assisted” may be copyrighted. Read AI and Copyright for more details and examples of what kinds of edits and decisions make something “AI-assisted” rather than “AI-generated” and an explanation of the March 2026 US Supreme Court decision.

In my opinion, that doesn’t matter too much for images within training. If you were using stock images previously, you didn’t own the copyright to those images either.

While there are multiple AI tools for creating business logos, that feels really risky to me. Even if you’re a small business and don’t plan on trademarking your logo, wouldn’t you like the option of doing so in the future? Pay for a human to create your logo so you can protect that IP.

The safest tool related to IP claims is Adobe Firefly, which also gives you indemnity against IP claims with paid plans.

As a side note, this is one of the issues with using AI to generate course content too, especially courses to sell. Someone can duplicate your content and sell it, and you might not have much recourse. This is an area of the law to keep watching, since future court decisions or legislation may change it.

Commercial use of AI images

Check the ToS for your AI image tool. Most free tools for AI images don’t license your results for commercial use. You generally have to use at least a minimal paid plan to get commercial use rights.

Don’t use images of real people without permission

Don’t use images of real people as reference images for AI unless you have explicit permission to do so. That’s not just for cases of deepfakes or sexually explicit images; that goes for everything.

I see way too many examples on LinkedIn where people have done “fun” transformations of people’s photos. Most of that isn’t malicious. It’s stuff like people making composite group images or turning workshop participant images into superheroes or whatever. But people should have the right to not have their images used that way, where your identity is clear.

Plus, even with good intentions, sometimes the images are problematic. I remember seeing someone’s AI-generated image of people they were looking forward to having a beer with…except I noted multiple people who don’t drink shown in that image. I shouldn’t have to explain that you shouldn’t generate images of a Jewish person eating bacon or a Mormon drinking alcohol, but apparently that’s a thing that need to be explicitly mentioned.

Even if you have stock images of real people, you may not have permission to use those images as references in AI. If you need character images, just use AI to generate your reference image and work from there.

Environmental impacts of AI images

The water use for AI data centers gets a lot of attention, but every time I actually dig into the sources and data, I see that the water use is relatively minimal. I don’t want any AI data centers drawing water from the Colorado River where water use is already such a problem. However, I think data centers can be built in places where water is more available, and they can be built and managed in ways that reduce their impact.

Electricity use is potentially a problem, especially at scale. AI models are much more efficient than they used to be, so they don’t use as much energy as early models (at least for regular prompting). I’d love to see more investment in renewable energy in the US. Where I live in North Carolina, data centers don’t pay taxes on electricity. I’d like that to change; I think data centers shouldn’t be incentivized so much that it’s hard to track the real costs.

You can also reduce your energy use by using cheaper models when possible. I often use Midjourney’s draft mode if I know I need a lot of iteration to fine tune something, partly because that reduces my energy use.

It’s important to keep the water and electricity use of AI in perspective with other tasks though. Check out the What Uses More? calculator to compare the energy and water use of different tasks.

For example, would you think twice about the water and energy use for a one-hour Zoom call with 10 people? Probably not.

Guess how many images could you generate with AI for the same resource use as that one-hour Zoom call?

According to the calculator, that one-hour Zoom call is equivalent to generating 1000 images. I generate a lot of AI images, but even I have only generated about 1500 images in Midjourney over the course of two years. Are you going to generate 1000 images in a year? How many Zoom calls will you have in that same year?

Transparency in AI use

One question that comes up often when I present about AI images is about transparency and labeling AI images. This is an interesting question because I don’t think there’s a clear answer that fits every situation. I had a client project where I clearly labeled everything I generated with AI but was asked to remove the disclosures. I can’t find the source right now, but I remember reading somewhere that Americans were generally less worried about having AI labeled, but Europeans (especially Germans) value transparency more. Cultural differences play a role here, as does organizational culture.

I used to label every AI-generated image here on my blog, but these days I admit that I figure people mostly know even without the label. But maybe I should be more explicit? From an ethical standpoint, transparency feels like the more defensible position.

Counter bias in AI images

AI image generators tend to exaggerate stereotypes. If you don’t actively work to counter bias in AI images, it can be worse than stock images. The good news is that AI images can give us even better, more inclusive representation than stock images. We’ve had the ability to create images of nonbinary characters and people of varied racial, ethnic, and national backgrounds for a while. We’re now finally getting to the point where disability representation is better. Inclusive images is one area where I think AI can give us better outcomes than stock photos. Using AI for social good is an ethical consideration too.

Review AI images

Just like you need to review AI-generated text for accuracy, review your AI-generated images. Beyond obvious AI errors, check the background objects, watch out for bias, and verify the results. If you always accept the first image result without refining your prompt or editing the result, that’s a problem. Your human judgement is more important than ever.

Further reading on AI ethics and legal considerations

• Is Any AI Use Ethical?
• Creating AI Art Responsibly: How to Navigate AI Legal Risks
• AI and Branding 2026: Copyright Risks for Content Creators
• Using AI Responsibly For Image Generation: Ethics And Transparency Matter
• The Ethics of AI Generated Images
• Paradox Learning Resources, including an AI Ethics Rubric
• Fairly Trained (certifies consent and licensing in training data)
• Thaura, ethical AI

What do you think?

What are your ethical guidelines for AI image generation? Do you prefer to see AI images transparently disclosed?

I expect a fair amount of disagreement on this. I’ve had some great discussions about this though, even with people who don’t agree. I’m hoping for some nuanced conversations about balancing our ethical considerations. Let me know your thoughts in the comments.

The post Considerations for Using AI Images Ethically appeared first on Experiencing Elearning.

Automation

After Automation | Every

If you’ve ever spent time cleaning up an AI-generated draft, you’ll get the initial point here: AI creates more work for humans, not less. But this article digs deeper into how working with AI, especially AI agents, changes the nature of work. Employees at this author’s company spend more time directing agents (deciding the goal and what “good” looks like) and on judging the results of AI. The easy work that AI can do gets commoditized, but the hard work of taste and judgement become more important.

There’s no tipping point coming where things flip and the jobs are gone. The new reality is the opposite—the more we automate, the more expert human work there is to do. Here’s why: AI commoditizes the residue of human expertise—whatever can be made explicit enough to train on. That collapses the value of default model output and creates demand for what’s different. Demand for what’s different is demand for human experts, even as we approach artificial general intelligence (AGI).

Across both forms—coworker and embedded—the pattern is the same. Employee agents take over more of the stable, repeatable, well-framed layer of work. But there is a lot of work that still requires a human being in the loop. We’ve found over and over that for any kind of complex task, the best way to get great work is to have an AI and a human going back and forth in the same workspace.

In every example, the agent needs a human in order for the work to, well, work. Someone has to point it at the right thing, decide whether the output is good, catch the places where it is wrong, and turn the result into a real-life decision or process. The further away an agent gets from a human who is in charge of making sure it works well, the less well it works.

When work is abundant and looks alike everywhere, the work that doesn’t fit the pattern becomes the rare, valuable, and high-status thing(5).

This is why, in practice, AI does not eliminate expert human knowledge work. It dramatically increases the volume of work being done, and none of that work is differentiated or valuable unless a human being is involved.

—Dan Shipper

AI Brain Fry, Workslop and the Ironies of Automation

This is a long article, but worth spending some time to digest. One of the ways that AI changes the nature of work is by increasing the amount of time we spend in cognitively challenging tasks like evaluation. But human brains need breaks and variety.

What remains after automation is not a simplified role but an arbitrary residue of the most demanding, most ambiguous, and least supported work in the entire system. The human is not replaced. In other words, the human is paradoxically left with the hardest parts, and given almost no preparation for them.

Surveying nearly fifteen hundred full-time workers across industries, roles, and seniority levels, the researchers found that intensive oversight of AI tools was the single most mentally taxing form of engagement their participants described. Workers required to monitor AI agents closely reported fourteen percent more mental effort, twelve percent more mental fatigue, and nineteen percent greater information overload than those whose AI engagement was less demanding.

The final irony of automation, she wrote, is that the most successful automated systems, those with the rarest need for human intervention, are precisely the systems that require the greatest investment in human skill.

—Carl Hendrick

AI

AI and Copyright: What You Can and Can’t Do with AI-Generated Content (2026)

An overview of AI and copyright. Who owns it? When can you use it for commercial purposes? How can you protect your AI-assisted work?

Image AI prompts

A large collection of images generated in Nano Banana, ChatGPT, and Seedream plus their prompts. Seeing how others have prompted for images is helpful in figuring out what works and what doesn’t.

AI Effectiveness Rating

Christopher Lind’s simulation tool for rating effectiveness working with AI

Oboe

Ask this AI about a topic and get a lesson on it. This is for self study, and it seems potentially useful for basic topics where there’s a lot of high-quality publicly available information to draw from. You can generate flash cards or study guides too. This might be something that’s more useful for students in school, but I can see it for employees wanting to learn the basics of visual design, copywriting, etc.

Scenarios

New Scenario-Question Generator — Version 5 » Work-Learning Research

Will Thalheimer released an updated version of his template for generating scenario questions. This includes notes about differentiating people who know how to do a task successfully and those who don’t know. The template also includes an annotated example scenario.

Clinical Case Study: Diane

This is a short scenario built in 7Taps by IDLance to use as spaced repetition to reinforce prior training. One aspect I really liked in this was the interaction where you listen to two people’s arguments for different courses of action. Then, you have to decide which is the better way forward. This technique could help make binary choices feel more realistic in the context of a scenario, especially if the justification for the worse answer is plausible for how people think.

Visual inspiration

21 Ways To Get Visual Ideas

Connie Malamed recently published a significant update to her article with resources for getting visual ideas and inspiration. This includes so many links to visual resources across the 21 categories.

---

Upcoming events

Crafting Choices That Challenge: Designing Scenarios for Authentic Practice. July 15 at 12PM Pacific / 3PM Eastern. Register for this free webinar hosted by Training Mag Network.

Scenario-Based eLearning Design Certificate: Strategies to Engage, Motivate, and Transfer Skills. 3 online sessions starting August 5. Register now; only a few spots left!

Creating High-Quality AI Media: Prompting, Scripts, and Consistency. October 8. Register for the ATD AI Intensive.

DevLearn

Branch Smarter, Not Harder: Naming Conventions, Variables, and Bottlenecks in Storyline

• November 3, 2026 at 9:20 AM
• CE01: Storyline & Rise Pro Lab

Cohesive by Design: Generate Consistent AI Icons, Illustrations & Characters

• November 4, 2026 at 10:00 AM
• BYOD (Bring Your Own Device)

The post Automation, AI, Scenarios: ID Links 6/9/26 appeared first on Experiencing Elearning.

Example scenario with inconsistent perspective

Let’s look at an example. For this scenario, the objective is to help new managers conduct effective performance conversations with underperforming team members.

Evie is a first-time manager. Her team member Lincoln has missed three deadlines in the past month, and the quality of his recent deliverables has dropped. Evie has scheduled a one-on-one to address it.

With this setup, Evie is the protagonist. She’s the manager who the audience should identify with. That means Evie is the character who should be making decisions; the action should focus on her.

But look at the first decision point after Evie starts the meeting and asks about the missed deadlines.

What should Lincoln say next?
A. Promise to do better at meeting the deadlines moving forward.
B. Explain the problems he's had getting critical information from another team.
C. Ask for help prioritizing his responsibilities.

Instead of a scenario about how managers talk to their employees, suddenly this has become a scenario about how employees respond to criticism. The action is focused on the employee’s perspective; it no longer aligns with the role of the manager.

How to check alignment

When you review scenario decisions, you’re watching for alignment between the audience role, the skill being trained, and the decision points themselves.

• Does the protagonist of the scenario have a similar role to the audience’s role in their work?
• Does the decision point show the protagonist acting, or does it show another character’s actions?
• Does every decision point relate to the same character’s actions, or does it shift throughout the scenario?

Of course, it’s possible to create a branching scenario that shows multiple perspectives. Hana Feels is a great example of an interactive story where you make choices based on multiple characters who talk to Hana, who is ostensibly the main focus of the story. But you only guide Hana indirectly, trying to shape her emotional responses based on her conversations with others. A multi-character scenario like that requires a lot of planning though, and it’s more complicated to maintain a consistent narrative over the course of various paths. Most of the time, when I see this in training branching scenarios, it’s haphazard rather than well-planned.

How to fix the consistent perspective problem

Fixing the problem of inconsistent perspective requires stepping back to the planning stage. Every decision point should focus on what your protagonist is doing. The actions of other characters are the consequences and challenges that your protagonist responds to, rather than the decision points themselves.

When I start planning a branching scenario, one of my early steps is to draft an outline of the main actions. A simple numbered list like this helps make sure I’m on the right track with my focus before I get too far into prototyping or development. These actions reflect the “ideal path” someone might take if they followed the process perfectly and chose the best options every time.

For this example scenario on performance conversations, that outline of actions in the ideal path could look like this:

1. Opening: Open with a clear, specific statement of the issue.
2. Gather Info: Ask open-ended questions to understand the context.
3. Listen: Listen actively and acknowledge what she hears.
4. Set Expectations: Restate what success looks like to clarify expectations moving forward.
5. Action Plan: Clarify concrete next steps for follow-up and support.

With that outline guiding me, I know each of my decision points connects to those actions. Since the first step is the opening the conversation, I can diagnose the problem: my first decision point actually happens too late in the story, after Evie has already opened the conversation. I need to back up and put the decision point right at the beginning of their meeting.

What should Evie say?
A. "Your work hasn't been great lately. I know you can do better, so let's talk about how to get back on track."
B. "I can't believe you missed the deadline for the Q3 dashboard! That's the third deadline you've missed recently. This is a becoming real pattern, and it's a problem."
C. "In the past month, you've missed multiple deadlines: the Q3 dashboard, the Henderson report, and the Palmer project QA review."

Now the decision is clearly about the performance conversation and the actions Evie takes as a manager. Lincoln’s reactions are the consequences and effects of what Evie says. The next decision point will respond to Lincoln’s words. If he’s resistant to the feedback, then Evie needs to ask questions and actively listen to understand and work past that resistance. The scenario decisions remain focused on Evie’s actions though, not Lincoln’s responses to feedback. The scenario has a consistent perspective that reflects the learners’ experience.

What branching scenario challenges can I help you with?

Do you have a challenge writing or building branching scenarios? What would you like to see me write about in future posts? Let me know in the comments or by replying to this email.

---

Upcoming events

Crafting Choices That Challenge: Designing Scenarios for Authentic Practice. July 15 at 12PM Pacific / 3PM Eastern. Register for this free webinar hosted by Training Mag Network.

Scenario-Based eLearning Design Certificate: Strategies to Engage, Motivate, and Transfer Skills. 3 online sessions starting August 5. Register now; only a few spots left!

Creating High-Quality AI Media: Prompting, Scripts, and Consistency. October 8. Register for the ATD AI Intensive.

DevLearn

Branch Smarter, Not Harder: Naming Conventions, Variables, and Bottlenecks in Storyline

• November 3, 2026 at 9:20 AM
• CE01: Storyline & Rise Pro Lab

Cohesive by Design: Generate Consistent AI Icons, Illustrations & Characters

• November 4, 2026 at 10:00 AM
• BYOD (Bring Your Own Device)

The post Consistent Perspective in Branching Scenarios appeared first on Experiencing Elearning.

This update includes the podcasts I recorded in 2025-2026.

• Freelancing for IDs (ID Lounge Part 1, April 2026)
• Artificial Intelligence and Instructional Design (ID Lounge Part 2, April 2026)
• AI-Generated Images for Learning Content (IDIODC, February 2026 )
• The Future Isn’t Flashier—It’s Smarter (EdUp L&D Podcast, July 2025)

Jump right to the section you want:

• Scenarios and storytelling
• ID careers, freelancing, and consulting
• AI and instructional design
• Other topics: engaging learners, time and cost estimates, general ID

Podcasts on scenarios and storytelling

My Approach to Scenario Writing and Multimedia: Visual Lounge Podcast

My Approach to Scenario Writing and Multimedia: Visual Lounge Podcast

I shared tips for writing, using storytelling elements, and when to use multimedia to enhance your messaging. We explored why knowing your audience and context is the starting point of all successful content and how you can learn more about your audience’s challenges, scenarios, and goals (even when you don’t have direct access to the information).

The Power of Practice in Workplace Learning

The Power of Practice in Workplace Learning: Podcast Interview

Most workplace training stops at delivering information – but does that actually help people apply what they’ve learned? In this episode of The Learning+ Podcast, I joined the conversation to explore how scenario-based learning bridges the gap between knowledge and action. We discuss how practice and feedback build confidence, when branching scenarios are most effective, and how to get stakeholder buy-in. I share insights on how to make learning stick.

Scenario-Based Learning 101

Scenario-Based Learning 101: Animaker Interview

This is Scenario-Based Learning 101, serving primarily as an introduction to the topic for people who are just getting started with scenarios. I unpack some of the common misconceptions surrounding scenario-based learning, discuss the various types of scenarios, and offer practical advice on how to apply scenarios effectively in different areas of training.

Scenario-Based Software Training

Scenario-Based Software Training: Digital Adoption Show

What makes training truly effective? Is it about teaching “click here” steps, or is it about empowering learners to make real-world decisions with confidence? That was one of the core ideas in my interview on the Digital Adoption Show podcast from Whatfix. In this interview, I focused specifically on software training, addressing when scenario-based software training is the right approach and when you should use other training methods. Honestly, a lot of the time scenarios are overkill for software training, but they are helpful in some specific situations.

Scenario-Based Learning for Learning Impact

Scenario-Based Learning for Learning Impact

How do you increase learning impact through scenario-based learning? While no solution is right for every training situation, we know that providing opportunities for practice with feedback is critical for developing skills. Scenario-based learning is one way to provide that practice with feedback to help learners improve their performance. In this interview with Amit Garg on the L&D Go Beyond Podcast, I discuss scenario-based learning and how that can increase skill transfer to real-world environments.

Scenario-Based Learning Q&A with Devlin Peck

Scenario-Based Learning Q&A with Devlin Peck

In this interview, I discussed when to use scenarios, tips for working with SMEs and stakeholders, planning and designing branching scenarios, and tools and resources.

Scenario-Based Learning Experiences

Scenario-Based Learning Experiences Podcast Interview

For one of my first podcast interviews, Jacqueline Hutchinson of The Lounge podcast and I had a lovely conversation on scenario-based learning. She had some great questions about how to use scenarios and storytelling in learning experiences that led to a really fun chat. We talked about some “horror stories” and scenarios gone wrong, using scenarios to make compliance training not sleep-inducing, and options besides branching scenarios for incorporating storytelling.

MADE Podcast on Branching Scenarios

MADE Podcast on Branching Scenarios

My interview for the MADE podcast on branching scenarios: when to use them, challenges, tools, planning, and getting started. This is a short conversation (about 20 minutes), if you’re looking for a quick intro to scenario-based learning.

Branching Scenario Podcast with Mark Parry

Branching Scenario Podcast with Mark Parry

Mark Parry interviewed me for his podcast, Perspectives in Parryville. We talked about branching scenarios and Choose Your Own Adventure stories. His audience is primarily teachers, so this interview connects ideas from workplace training and education. This includes some discussion of the way feedback is used in branching scenarios, since feedback is an important topic for teachers as well.

Redefine Instruction: Storytelling for L&D

Interview on Storytelling for L&D

Kicking off the 2nd season of the Redefine Instruction podcast, I had a great conversation about storytelling for L&D with Sandhya Lakhanpal. We discussed a range of options for using storytelling and scenario-based learning. We also talked about my journey from teaching to instructional design.

Podcasts on instructional design careers, freelancing, and consulting

Freelancing for IDs

Freelancing for IDs with the Southern Nazarene University ID Lounge Podcast

This episode, Part 1, focuses on the practicalities of starting a freelance career and the necessity of a strong digital presence.

• Understanding the Terminology: The difference between W2 contracting and 1099 freelancing.
• Making the Leap: How I transitioned to full-time freelancing
• Where the Work Is: For those starting out, subcontracting through e-learning agencies is a recommended path because the agency handles the sales and project scoping, allowing the designer to focus on development.
• The Power of Networking: Rather than traditional “sales,” I emphasize “stealth mentoring” and being a “good online neighbor”.
• The “Required” Portfolio: A digital portfolio is considered the minimum requirement to be taken seriously as a freelancer.
• Portfolio Maintenance: Keep a “rainy day list” of portfolio updates to work on during slow periods.

The Future isn’t Flashier: It’s Smarter

The Future isn’t Flashier

I spoke with Holly Owens on the EdUp L&D podcast again in July, 2025. Our conversation covered the nuances of scenario-based learning, common pitfalls in instructional design, and the evolving role of AI in the field. I shared insights on how to effectively implement branching scenarios and the importance of aligning practice with real-world skills. Our conversation wrapped up with my thoughts on the future of instructional design—which is where Holly’s title of “the future isn’t flashier” comes from.

How I Became an ID

How I Became an ID

In this podcast interview with Dr. Robin Sargent, I discuss how I transitioned from teaching to instructional design and provide tips for new IDs.

Freelancing and Consulting

Podcast Interview on Freelancing and Consulting

Kristin Anthony talked to me about moving into freelancing and consulting, positioning yourself in the market, finding clients, pricing strategies, and managing my business.

Instructional Design Certificate or Master’s Degree

Instructional Design Certificate or Master’s Degree

I spoke Luis Malbas and TLDC about whether it’s better for your career to get an instructional design certificate or a master’s degree. This is part of their Certificates and Certifications playlist (members only for the videos for the whole playlist). We also talked about portfolios, as your portfolio is often as important (maybe more so) than your formal credentials.

Podcasts on AI and instructional design

Artificial Intelligence and Instructional Design: Insights from Christy Tucker

Listen to Part 2 of my interview with SNU’s ID Lounge podcast

This part of our conversation focused on AI and instructional design, published in April 2026.

• Practical applications of AI
• Analysis and skill mapping
• The efficiency illusion
• AI as a thinking partner
• Navigating ethics and privacy

From Generic to Custom: AI-Generated Images for Learning Content

IDIODC Podcast: AI-Generated Images for Learning

We talked about the challenges with generic stock photos and how my workflow has shifted to custom AI-generated images. I shared how I’ve used my blog posts for experimentation and building my skills with AI images. We talked about how to get consistency in images across several tools (the strategies are different in chat tools like ChatGPT and Nano Banana versus specialized image generators like Brushless and Recraft). We also talked about costs and subscription plans as well as legal and ethical issues.

AI Right Now

AI Right Now: Mindset to Learn Podcast

In season 2 of her podcast, Joanie Musser hosted a series of interviews about AI and how it affects our field. My discussion with Joanie was focused on my experiences as a practitioner. We talked about the tools I actually use like Midjourney and Claude. I shared how these tools can be helpful as well as some of the challenges I’ve experienced.

Podcasts on other topics: engaging learners, cost estimates, instructional design

Estimating eLearning Development Costs

Cost of eLearning Development based on Learner “Seat Time”: What the Research Says

This is a direct link to the YouTube recording for the IDIODC show (Instructional Designers in Offices Drinking Coffee). I reviewed Bryan Chapman’s research and the ATD research on estimating development time and cost.

Designing Engaging Digital Learning

Designing Engaging Digital Learning

In this podcast with Keith Quinn, we discussed a range of topics related to online and digital learning. We started with blogging as a way to “show your work” and reflect on your practice. The conversation touched on a number of other topics, including providing information versus practicing skills and using tools that aren’t intended for learning.

Emotionally Engaging Content

Emotionally Engaging Content

I spoke with JW Marshall on the Voices of E-learning podcast. We talked broadly about trends in workplace training. One of the themes of our conversation was how emotionally engaging content can improve learning outcomes.

Your podcast?

If you host a podcast related to learning and development, instructional design, elearning, AI, or other related topics, contact me about scheduling an interview.

Originally published 12/6/22. Updated 5/2/24, 5/15/25, 5/21/26.

The post Podcast Interviews on Scenarios, ID Careers, AI, and More appeared first on Experiencing Elearning.