Use reference images

My first lesson learned was to use reference images. I already knew that, to some extent, because I use reference images for character images. I used those same character reference images for all of the videos you’ll see in this post.

However, I didn’t use a reference image for the setting. While I did have images I could have used for the first frame, I’m still not completely happy with what I’d gotten previously. I decided to see how the different tools did at setting the scene without a reference image. That was OK for this experiment, but I think for further development I’d want to have at least one reference image for the setting, if not a storyboard with multiple images.

Instead of a reference image, I included a description of the room in my prompt. I include a description of art on the walls because otherwise the AI tools often fill in other details. I often get unrelated text on a whiteboard or charts on a screen, and I didn’t want those here. (Again, if I’d used a reference image for the room, that would have fixed the problem.)

The dialogue comes from the opening passage of my project management scenario.

Setting: Three people @Jake @Samantha @Alex meeting in an office conference room, all sitting around a table. Laptops and coffee mugs on the table. Light gray walls, overhead lights, abstract corporate art on the walls.

@Jake : "Alright team, we're a week behind schedule on the Healthtrack project, and the client still hasn't provided the data integration requirements we requested three weeks ago."

@Samantha: "Without those requirements, we can't properly design the system architecture. We risk making assumptions that could lead to costly rework down the line."

@Jake "We can't afford to keep falling behind. We should make our best educated guesses based on our experience and move forward."

@Alex "I'm with Samantha on this. If we don't get the integration requirements right, it could severely impact the user experience and data flow."

This first example video was generated in Google Omni 1.1 Flash. I’ve had decent luck with this model for generating b roll videos.

• Model: Google Omni 1.1 Flash
• Video length: 10 seconds
• Cost: $1.20
• Cost/sec: $0.12

All costs noted are my actual costs as calculated in Flora; I did math to determine the cost per second.

Give enough time to include the dialogue

I immediately realized one of my errors: that dialogue was too long for the generation time. The video is 10 seconds, but I had more dialogue than could fit. The AI trimmed my script to fit it in rather than using it verbatim. That would be fine for some uses, but that’s not what I wanted for this scenario.

For my next attempt, I trimmed it to just the first line of the script. I hoped that would give it enough time to keep the dialogue accurate. And…well, you can see for yourself. It was closer, but it still wasn’t quite right. I also adjusted the description of the room; I decided I didn’t like the abstract art.

Setting: Three people @Jake @Samantha @Alex meeting in an office conference room, all sitting around a table. Laptops and coffee mugs on the table. Light gray walls, gray chairs, light wood table, a clean whiteboard on the wall. Overhead florescent light.

@Jake : "Alright team, we're a week behind schedule on the Health track project, and the client still hasn't provided the data integration requirements we requested three weeks ago."

• Model: Google Omni 1.1 Flash
• Video length: 6 seconds
• Cost: $0.72
• Cost/sec: $0.12

Watch for character positions changing

One of the other problems in this video is that Alex shifts position. At the beginning, he’s sitting next to Samantha. Partway through, he magically transports to sit next to Jake. This is another problem I probably could have solved with reference images and a storyboard. I’ve even seen a demo where someone blocked the character positions in Blender for a rough 3D model and then used that to keep each character in the same place around a table. Keeping the characters and objects consistent from scene to scene is a challenge unless you’re directing it.

Some models look more AI than others

I wanted to test several models to be able to compare the results. I used the same prompt again with a different model, MiniMax. These results were even worse; this looked and sounded really obviously AI. The character and dialogue accuracy was lower. Check out how Jake’s background suddenly switches to the studio photo background rather than the conference room background. MiniMax was fast and reasonably cheap, but it’s not the right model for this task.

• Model: MiniMax H3 Max
• Video length: 8 seconds
• Cost: $0.768
• Cost/sec: $0.096

Video generation costs can add up quickly

Next, I tested Seedance. This is a higher quality model, but it’s also slower. Each generation took several minutes, where the previous videos tool under a minute to generate. I have had some good results with Seedance, but it’s also about four times more expensive than the Google or Minimax models. With Seedance, I generated an initial clip of 8 seconds. Then, I used the Extend video function in Flora to generate a second clip for the next clip with Samantha’s response. I stitched the two clips together in Flora.

• Model: Seedance 2.5
• Video length: 21 seconds
• Cost: $3.914 + $6.337 = $10.251
• Cost/sec: $0.488

You can see the Seedance clips combined below. The transition is weird; I should have prompted for the camera angle to change to point at Samantha instead of starting zoomed out and pushing in again. But because Seedance is so expensive, I was reluctant to generate another clip. If this was a real project and not for my blog, I would have had to pay the $6 for another generation.

While Seedance is higher quality (and I know I could improve my results with more detailed prompts and direction), the cost is significant. A 2-minute video would cost about $58 in generation. Knowing that some clips wouldn’t work on the first try and would need to be regenerated, a more realistic estimate for a 2-minute video might be about $75-$80. Maybe it’s because I’m used to how cheap image generation is (images cost 5-7 cents on Flora), but I was surprised at how fast the costs added up.

Voice quality and consistency concerns

AI voice overs have dramatically improved in quality in the past few years. However, in these AI generated videos, you probably noticed some issues. For example, in the Seedance clip above, Samantha has weird, overly dramatic pauses in her line. I’ve also heard issues in keeping the voice consistent for characters across multiple clips.

In order to generate enough videos for a full interactive video scenario or a longer conversation, I think I’d need to generate the audio separately in ElevenLabs or WellSaidLabs. That would give me higher quality and more control over the generation. Plus, that would fix the consistency issue; as long as you use the same voice for each character, you maintain the same sound throughout.

However, bringing in audio also means dealing with lip syncing in the video tool, and that creates a different set of challenges. How accurate is the lip syncing? How many generations does it take to get it right? After you generate clips, how much manual editing is needed?

Reflections on AI videos for training

This is a sample project for my blog and portfolio, so I’m not persisting through challenges the same way I would if this was a real client project. Right now, I feel like the AI video tools like this are good for generating short b roll clips. I’m already using AI videos for that purpose in actual explainer videos now.

For more complicated videos, it’s going to take a lot of time, iteration, and cost. There’s no magic where you drop a script in, press a button, and get a fully formed video with multiple characters, dialogue, camera angles, and consistent background out. It’s possible to generate higher quality videos with AI (check out how the 2-minute animated video Slice was created), but it takes quite a bit of work. I’ve seen some 700+ word long prompts for Seedance; that’s a lot of time directing the AI that I didn’t spend for these samples.

When my clients have asked me about AI video generation over the past two years, I’ve been telling them to wait another 6 to 12 months and then check in again. At this point, I think it can be done, but we have to be realistic about what it takes. All of these models are cheaper than hiring actors for a half day shoot, but it’s expensive and difficult enough that I’d need to scope it realistically.

Will you know that all of these are AI-generated videos? Yes. But getting the quality good enough to be useful for training scenarios doesn’t necessarily mean it has to be indistinguishable from using human actors. In fact, I think sometimes we’re better off using illustrated or animated styles that don’t pretend to be real people. You can still get the value of a conversational example or interactive video with something illustrated.

AI video tool comparison

Here’s my summary of the three AI video tools I tested.

New Hands-On AI Image Workshop

Want to learn how to generate higher quality AI images—visuals that are good enough to actually use in a course? Part of the trick with AI image generation is that even if you start with a good prompt, you still may need to iterate a few times to refine it. Even though I’ve presented on AI images multiple times, it’s impossible for me to give participants enough time to really practice that iteration process in a one-hour webinar.

That’s why I built a new three-hour hands-on AI image workshop. You get six rounds of live practice. After each round, we review your results so we can figure out how to improve them. I’ll give you a reusable prompt framework as a starting point, and then we’ll work on iterating and improving images, using reference images for consistency, and matching brand colors. This is geared for L&D professionals, so I focus on the kinds of images commonly used in training like photorealistic examples and icons. You’ll leave with a small set of images for a real project of your choice, ready to use in a course.

Learn more about the AI Image Workshop

The post Lessons Learned while Generating AI Videos appeared first on Experiencing Elearning.

Typical compliance training: Push

Let’s say you’re creating training for managers on providing reasonable accommodations for disabilities. A typical elearning compliance course on reasonable accommodations would start with a history of the ADA, ADAAA, Civil Rights Act, etc. (Readers outside the US, substitute your own laws about disabilities.) You might compare how the laws have evolved over time, define the terminology, and list some common reasonable accommodations you could provide.

All of that is “pushing” content to learners. The learners are treated as passive receptacles for content. You as the instructional designer control what content is delivered, in what order, and how quickly. The learners don’t make any decisions, and they don’t have any reason to dig deeper into the content.

Alternative compliance training: Pull

You could flip the whole course around though. Instead of pushing content to learners, you let them “pull” what they need. The trick is that you have to give them a reason to need the information.

In the example below, Rosa asks her manager, Cindy, for time off after a surgery. This is a plausible situation managers might find themselves in where the right answer might not be obvious. The managers have to make a decision: to grant the time off or not.

In this scenario, you could just offer the two choices: grant the time off or not. However, I’m deliberately putting them in this situation to give them a reason to look up the policy. Therefore, I have two more choices below: “Ask HR” and “Review Policy.” If learners choose “Ask HR,” they’ll see a simulated conversation with an HR specialist explaining the policy and providing advice. Either way, they’re “pulling” the policy information because they have an immediate need for it.

“It’s easiest to pay attention to content that you can use right away. Use strategies like test-then-tell, scenarios or problem-based learning to create an immediate use for the learning content.”

Julie Dirksen, The Science of Attention and Engagement for Learning

“Pull” options

You might choose to only have one option for explaining the policy rather than two like the above example. Either just reading it or asking another character for advice might be enough. If reading the policy is the only option, it’s helpful to include a plain language explanation. This is especially true if the original policy is written in very formal or legal language. You can provide the original and the explanation side-by-side, or you might just provide the explanation.

If your users will have a job aid when they actually do the task, use that job aid in the course so learners practice with that tool. If they won’t have a job aid in the real workplace, what would they do instead? Would they consult with HR or ask a manager? Figure that out, then build that into the scenario. As much as possible, make the way learners access policy information in your course similar to how they will access it on the job.

Knowing when policies apply

Another advantage to the pull approach is that it helps learners see when policies apply to different situations. This is especially helpful if your audience needs to be able to distinguish between similar situations. Maybe under most circumstances, “guideline A” applies, but there’s an exception where “guideline B” applies instead.

“Learners are motivated when they can see the relevance of what they are learning. If they learn new information in the context of real world problems, if they are shown a demonstration of skills they are expected to acquire (show), if they have the opportunity to apply these skills in the solution of additional real-world problems or the performance of additional real-world tasks (do), then they are much more likely to acquire, retain and be able to use the required skills.”

M. David Merrill, Finding e3 (effective, efficient and engaging) instruction

Another example: Cathy Moore’s Connect with Haji Kamal

Although Cathy Moore’s Connect with Haji Kamal isn’t compliance training, it also demonstrates the technique of having characters ask for advice. Learners need to “pull” information and actively seek it out rather than passively waiting for the course to “push” it to them. It’s the same mechanism, just a different kind of training.

Cathy’s original version is no longer available since it was built in flash, but Stephanie Harnett built The Return of Haji Kamal in Storyline with the original assets (and Cathy’s permission).

Try one-question mini-scenarios

Even with one-question mini-scenarios instead of branching scenarios, you can use this technique to motivate your learners to look up the policies themselves. Give learners a reason to seek out and immediately apply the information. That will make them more likely to remember those policies when similar situations happen on the job.

Image credits

• Characters from eLearning Art
• Document by useiconic.com from the Noun Project
• Conference room from Storyblocks

This compliance course example is also used in What’s Your Character’s Goal?

Originally published with the title “Motivating Learners to Look Up Compliance Policies Themselves” on 3/22/2016. Updated and republished with a new title 7/21/2020. Last updated 9/10/2026.

The post Create Motivating Compliance Training appeared first on Experiencing Elearning.

You’ll learn strategies for writing more effective image prompts to minimize bias and reflect more inclusive representation in your learning. You’ll get tips to more authentically represent your training audience by using AI images. While AI tools are improving all the time, they still have limitations that you need to be aware of. We’ll discuss some of the ongoing challenges with inclusive representation in AI image generation and options to minimize those issues. You’ll leave with a collection of sample image prompts, a prompt framework for better results, plus tactics to make your AI-generated images more inclusive.

Watch the recording

If the video isn’t embedded below, you can watch the presentation recording on YouTube.

Download the slides

Most of the time, I don’t share my slides for presentations. My slides aren’t all that useful on their own, so I build separate handouts with more comprehensive information. However, in this case, where the focus is often on both the inclusive AI images and the prompts to generate them, having the images of the slides is helpful.

AI still can’t show left-handed writing

One of the observations I shared in my session is that AI image generators still can’t show someone writing with their left hand. That’s partly because the majority of images of people depict right-handedness. That becomes the default prediction for the AI when showing writing, and I haven’t found any AI image model that can override that default.

For example, here’s Nano Banana’s result for this prompt:

Editorial photo, a left-handed woman writing in a notebook with her left hand in a charming coffee shop, focus on the hand, notebook, and table. An iced latte is on the table next to the notebook.

Is left-handedness the most pressing issue related to inclusive AI images? Of course not! But it’s an example of how AI predictions about the most likely results can amplify stereotypes in images. The same types of predictions happen with gender, race, ethnicity, nationality, hair, skin color, disabilities, assistive devices, body type, and more.

Generating images of a range of body types

AI images tend toward slender body types. Adding descriptive phrases like “average weight” or “slightly overweight” can help counter that. 

These four images all used the same prompt except changing the body type as shown.

Style: Candid iPhone photo
Subject: Greek woman, mid 30s, black wavy hair, olive skin
Body type: [Very thin, athletic; Average weight; Slightly overweight; Obese, heavyset]
Clothes: Blue and white floral shirt, tan slacks
Action: Laughing at a joke, pointing
Setting: On the sidewalk, outside a cafe
Lighting: Golden hour
No signs or text

More on inclusive AI images

• Disability Representation in AI Images
• Nonbinary Characters in Scenarios
• Considerations for Using AI Images Ethically
• Minimizing Bias in AI-Generated Images (My AIDC presentation last year)

---

Upcoming events

Instructional Design Uncovered: A Community Conversation with Instructional Designers. September 10. ATD Research Triangle Area

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

Creative Solutions with Twine: Design, Streamline, and Refine Branching Scenarios. October 14. ATD Dallas Learning Technology SIG

DevLearn

Register for DevLearn by October 2 for the Advanced Rate. Save an extra $100 with code CHRISTY.

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)

Buzz Discussion: Video & Media

• November 4, 2026 at 3:45 PM

The post Inclusive AI Images for Learning appeared first on Experiencing Elearning.

Conferences

In Defence of Conferences – by Tom McDowall

Tom McDowall reflects on how conferences serve different purposes depending on where you are in your career and what your professional goals are. Consider his questions when making choices about what’s worth your time and money to attend. The biggest and most popular conference might not be right for you, depending on your goals.

Ahead of booking or agreeing to go to anything, ask yourself two questions: What elements of my practice do I want to focus on? What do I want to deliberately improve over the coming twelve months? Once you know the answer to that, then and only then should you start thinking about: Which events in the calendar could support me on that journey?

—Tom McDowall

elearn Magazine: Writing (And Reading) Conference Session Descriptions

Clark Quinn reminded me of this article from 15 years ago about writing proposals to speak at conferences. Even though the article is older, the advice is evergreen, and it overlaps with some of the same key points I shared in my recent podcast interview on conference speaking. He also talks about titles and other aspects I didn’t address.

What makes a compelling audience experience? What will make them leave in a state of gratitude for the time spent with you?

You need to be answering three questions: Why should I care, how will this accomplish my goal, and why this speaker? In business, what’s the pain point I’m feeling, how will this session address it.

—Clark Quinn

Camera angles

The Psychology of Camera Angles: How Perspective Shapes Every Photo – PhotoWorkout

As I work with AI images and video more, I find myself needing to learn more about camera angles—how to describe what I want and how to be more deliberate in my choices. This article about the psychology of camera angles and how they affect how the viewer feels about an image.

The Ultimate Guide to Camera Angles & Shots (with AI Prompt Examples for Storytelling)

A guide to different types of shots plus camera angles. This includes examples so you can see the difference (although they’re not amazing AI-generated images, they still serve the purpose). The sample prompts give you examples of how to describe and ask for different results. There’s also some tips on combining shot types and camera angles (like close up and low angle) for different effects.

Videos

I hired an AI agent to edit my videos

Ross Stevenson explains how he uses Riverside’s AI features for editing videos to avoid the tedious parts of editing and polishing.

Seedance 2.5 animation prompts: the ultimate guide to 10 styles | Magnific Blog

While I feel fairly confident describing images in prompts, I know I have a ton more to learn about prompting for video, including for animation. This article gives examples of prompts in different animation styles. It’s helpful to see both the repeated patterns in the prompt structure (starting with the medium, listing numbered shots, describing emotions) and the specific keywords to convey different styles.

Scenarios

How to Design Better Branching Scenarios: Start With the Decision

This article by Garima Gupta has a lot of overlap with my own process for writing branching scenarios (e.g., asking questions to narrow down the specific behavior, identifying decision points first). I like her explanation of the “mental model” behind the choices to get more believable options.

A stronger approach is to make each choice represent a different way someone might genuinely interpret the situation. One manager might think, “I need to establish authority before this gets out of control.” Another might think, “They are upset, so I should probably leave the performance issue for another day.” Someone else might decide they need more information before responding. These are not random distractors. They represent different mental models.

The question I would use is: what is the least complex structure that still allows the learner to practise the thing that matters? Branching complexity should follow the learning need rather than become a goal in itself.

—Garima Gupta

Name Generator Tools

Wordineer has name generators organized by continent and country, primarily European and Asian names. You can generate first and last names and pick options like the type of surname and the meaning.

SCQA: What is it, how does it work, and how can it help me? – Analytic Storytelling

I’d run across this model before in business communication, but Jean Marrapodi brought it to my attention again recently. This is really a story framework for presentations or reports where you want to communicate information. It could work as an overarching pattern in an explainer video or training too. It’s less suited to interactive stories or branching scenarios, but you could adapt it to work there too.

Working with clients

Why Silence Scares Your Clients (And How to Fix It)

Clients get anxious when they don’t hear from you, even if you’re working hard and making great progress. Proactive status updates reduce client stress and make you easier to work with. This is a great approach for L&D freelancers and consultants, and very similar to the structure I use for my own weekly updates to clients. I learned this lesson myself early in my freelancing career.

Clients don’t judge your expertise purely by the quality of your final deliverable. They judge it by how safe they feel while waiting for it.

LinkedIn tips for job seekers

LinkedIn Content Strategy for Job Seekers: 5 Posts That Get You Noticed

Knowing how many folks in my network are looking for work, I thought this list of tips for job seekers for posting on LinkedIn would be helpful.

---

Upcoming events

Instructional Design Uncovered: A Community Conversation with Instructional Designers. September 10. ATD Research Triangle Area

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

Creative Solutions with Twine: Design, Streamline, and Refine Branching Scenarios. October 14. ATD Dallas Learning Technology SIG

DevLearn

Register for DevLearn by October 2 for the Advanced Rate. Save an extra $100 with code CHRISTY.

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)

Buzz Discussion: Video & Media

• November 4, 2026 at 3:45 PM

The post Conferences, Camera Angles, Videos: ID Links 9/1/26 appeared first on Experiencing Elearning.

This year is the final year of the survey; Jane is ending it after this year. She’ll publish the results and her analysis on Monday, September 7, 2026.

Tools I use to create learning experiences for others

I use these tools for creating learning experiences for others: Claude, Flora, Twine, Articulate 360, Affinity, SnagIt, and PowerPoint.

Claude

Claude was on my top ten list in 2024, but last year I primarily used Poe instead. I like how Poe lets me test lots of different models, but it lacks some of the features that modern LLMs have. For working on projects, it’s easiest to work directly in Claude on my desktop. I still use Claude in chat format for tasks like brainstorming, but I’m also starting to use Claude Cowork for more advanced work. I’ve been using it to vibe code practice activities in training, enhance scenarios I built in Twine, and other work. Claude can speed up the process of creating handouts and participant guides based on my PowerPoint slides, and I’ve used it to help organize and build content from multiple source files.

Flora

Last year, I listed Midjourney as my primary image generation tool. I still use Midjourney for my blog header images, but for creating learning experiences for others, I primarily use Flora now. Flora is an all-in-one canvas where you can generate images and videos. It includes all of the major models for AI image and video generation in a single visual interface where you can see your work at a glance or zoom in to focus on a single element. It also includes useful tools for editing media like cropping and separating images into layers. One of my current goals is to learn how to use Flora better; I know I’m not using all of its capabilities effectively yet.

Twine

Twine is my favorite tool for creating branching scenarios. After struggling to write scenarios and make them work in linear tools, it’s amazing how much faster I can develop multiple connected paths in Twine. Being able to generate a lightweight interactive prototype is critical for branching scenarios. Plus, it’s free and open source, with an active developer community working to extend its functionality and user communities for support.

Articulate 360

Most of the elearning content I build for clients is created in either Articulate Storyline or Rise, part of the Articulate 360 suite. Storyline is fairly easy to develop with, but flexible enough to do plenty with if you’re creative. I use Rise for some development as well, depending on the project.

Articulate Review saves me tons of time collecting feedback from clients and stakeholders.

Affinity

I use Affinity nearly every week to edit images for elearning and my blog. Affinity is a great replacement for Adobe Illustrator and Photoshop at a much more affordable price.

SnagIt

I use SnagIt all the time for quick screenshots. If I need to quickly show a colleague or client how to do something, or I need to show an error for troubleshooting, SnagIt is the perfect tool.

PowerPoint

For all that it is a much maligned tool, PowerPoint is still a regular part of my toolbox. I use it to create mockups of elearning layouts and occasionally for basic image editing. As I regularly speak at conferences and online events, I also use PowerPoint to create slides for those sessions.

Personal Development: My own continuous learning tools

Raindrop

I spend time nearly every day reading and learning online. Reading a lot is great, but I also need a way to find sources again when I need them. When I read something interesting, I bookmark it so it’s easy to find and refer to later when I need it. Raindrop is the online bookmarking tool I use for my own personal knowledge management to save and find resources. I also use these saved links to curate resources for blog posts every 4-5 weeks.

WordPress

WordPress has been my tool of choice for blogging for nearly 20 years. This is the place I do most of my personal reflective learning. Frequently, I don’t know what I really think about a topic until I write about it. Writing helps me connect ideas and clarifies my understanding.

In addition, my blog is a place where I try to help others learn. When I “work out loud” and demonstrate how I accomplished something, others can read and benefit from that. When readers email me or comment about how helpful something was, I know I’m meeting that goal too. In addition, clients find me through my blog. If they read something I wrote and find it helpful, they already trust my expertise before they even contact me.

Zoom

Zoom is a tool I could put as both a personal learning tool and one for delivering learning to others. It’s the tool used in several online communities and small groups that support my continuous learning. But I also use it for working with clients and SMEs as we collaborate on learning projects, and it’s the platform I use for coaching and teaching live online sessions.

Past top ten tools posts

Interested in how this list has changed over time? While I haven’t participated all 20 years that Jane has been collecting this data, I shared my top ten tools for learning in 2007, 2008, 2009, 2011, 2014, 2021, 2022, 2024, and 2025. Not a single tool from my list in 2007 is still on the list today, although I do still use some of them for work.

Don’t forget to add your vote for your top 10 tools for learning by August 27, 2026!

The post My Top Ten Tools for Learning 2026 appeared first on Experiencing Elearning.

Compliance training is often boring

As instructional designers, we often build a lot of compliance training. All those policies and regulations that affect our organizations need to be trained. Unfortunately, compliance training is often just a content dump with a narrator reading the policy, followed by some multiple choice questions to see if learners remember what they heard 5 minutes earlier.

This training can be so boring that organizations have to offer bribes (“You’ll be entered in a drawing!”) or threats (“Failure to complete this training may result in termination”) to cajole employees into completing the courses.  In many cases, companies don’t even really seem to care if employees’ behavior changes due to the training. They just want to check a box that says, “we provided training” to cover themselves legally.

If you’re training food production workers on personal hygiene policies, you could simply list the rules. However, just telling people the rules isn’t always enough to convince people to follow them. Have you ever driven faster than the speed limit—even when you knew what the limit was? Knowing the rule isn’t always enough.

Show a worst case scenario

Instead of focusing on just the policies and regulation in abstract, engaging compliance training focuses on when employees need to follow those policies and why they matter.

To show the “why,” start with an example of what can happen if they don’t follow the policies. In the case of food safety, it’s easy to imagine a worst case scenario with a nationwide food recall. In fact, almost 15 years ago, I built a mockup of a newspaper front page showing a headline about a “Nationwide Food Recall.” While now a news website or social media mockup looks more current, the same example warning feels sadly relevant in 2026.

(As a side note, I used to spend so much time manually building fake examples like this in Photoshop for elearning. This took me a few minutes and 3 iterations with AI. It’s much easier to generate these supporting visuals now!)

What could other worst case scenarios be?

• Ethics: A scandal that causes a company’s stock to drop or legal consequences
• Safety: An injury resulting in missed work, lost income, and a long recovery
• Security: A breach that results in data loss and all the ramifications from that

For any compliance training topic, there’s a consequence if the policy isn’t followed. That consequence can be your opening scenario that draws your learners into the story and gets them emotionally involved.

Compliance training with interactive video

A classic example of this technique is The Lab: Avoiding Research Misconduct. This is an interactive video you can play from the perspective of different characters. The story starts with “a very bad day,” where news reporters are interviewing a supervisor about misconduct. Right from the start, you see the consequences of poor decisions. As a learner, you get the opportunity to go back in time to see how those decisions were made and try to avert disaster.

You might not have the resources to hire actors and film scenarios in multiple locations like this, but you could still provide this kind of setup. It’s easy to mock up a newspaper headline like the one above or a fake website screenshot with trending news.

What if your worst case scenario would be internal, like an employee losing sales or being placed on a performance improvement plan? In that case, even a photo of an unhappy manager with voice over or text explaining the consequences can be effective.

Why the worst case scenario works

The worst case scenario gets learners attention because it shows them why the policy or regulation matters. Instead of the compliance training being just a box to check off, it’s teaching them how to be a hero and prevent a disaster.

It’s important to show these consequences and not just tell them. Simply telling people, “Failure to comply with personal hygiene policies could result in a food recall,” doesn’t have the same emotional impact as showing them a fake headline about a recall for contamination.

Show the “Why” and the “When”

Starting with a worst case scenario is the “why” for a policy. For tips on how to focus on the “when” policies apply, check out my post Creating Motivating Compliance Training. That post describes the difference between a “push” training where you give all the info to learners when you decide and a “pull” training where learners get the policy information they need, when they need it.

Originally published 3/10/2016. Updated 7/6/2020, 8/13/2026.

---

Upcoming events

Instructional Design Uncovered: A Community Conversation with Instructional Designers. September 10. ATD Research Triangle Area

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

Creative Solutions with Twine: Design, Streamline, and Refine Branching Scenarios. October 14. ATD Dallas Learning Technology SIG

DevLearn

Register for DevLearn by October 2 for the Advanced Rate. Save an extra $100 with code CHRISTY.

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)

Buzz Discussion: Video & Media

• November 4, 2026 at 3:45 PM

The post Make Learners Care about Compliance Training appeared first on Experiencing Elearning.

Watch the interview

If the video isn’t embedded below, you can watch it on YouTube.

Listen to the podcast

You can also listen to the podcast on Spotify. (We didn’t have any slides or visuals, so you’re not missing anything if you just listen.)

More podcasts

Check out my collection of over 25 podcast interviews on scenarios, ID careers, AI, and more.

---

Upcoming events

Instructional Design Uncovered: A Community Conversation with Instructional Designers. September 10. ATD Research Triangle Area

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

Creative Solutions with Twine: Design, Streamline, and Refine Branching Scenarios. October 14. ATD Dallas Learning Technology SIG

DevLearn

Register for DevLearn by October 2 for the Advanced Rate. Save an extra $100 with code CHRISTY.

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)

Buzz Discussion: Video & Media

• November 4, 2026 at 3:45 PM

The post Conference Speaking Tips for L&D Professionals appeared first on Experiencing Elearning.

Branching scenarios

How to Write Scenario-Based eLearning That Doesn’t Feel Fake | Embark IQ

Tips for making scenarios feel authentic, creating plausible distractors, and supporting learning with feedback.

Enhancing workplace eLearning with branching scenarios: An action case study

A case study on branching scenarios for workplace learning, looking at motivation, engagement, and knowledge retention. The researchers asked how engaging with branching scenarios influenced motivation, what design features supported engagement and minimized cognitive load, and learner perceptions of decision-making support. This is a small study (n=10), with participants from a range of backgrounds and roles.

All quotes below are from the authors of the linked paper: Pimblett, Ceri ;Rowe, Lisa; Fenton, Alex. DOI 10.1108/IJOTB-04-2025-0103

Branching scenarios offer design features that can help reduce extraneous cognitive load through segmented content and scaffolded decision-making. Rather than overwhelming learners with dense information, these structured interactions promote focused engagement and facilitate problem-solving.

The findings indicate that two key design features support sustained learner engagement and minimise cognitive overload. First, relevance was critical: scenarios that closely aligned with real workplace contexts enhanced motivation and perceived usefulness, whereas generic or abstract content reduced engagement (Theme 2). Second, cognitive load was shaped by how content was structured. Overly complex tasks overwhelmed learners, but well-sequenced, chunked scenarios helped them stay engaged and retain information effectively.

Learners perceived branching scenarios as valuable tools for developing workplace decision-making and applying skills in realistic contexts.

Participants consistently identified the branching scenarios as a distinctive and valuable feature of the training. This interactive format enabled them to explore different choices, including deliberately selecting “incorrect” options to better understand consequences and reinforce learning. This aligns with the concept of “safe failure” (Sennett & Vasquez, 2021), which allows learners to make mistakes in a controlled environment without real-world repercussions.

Interviews revealed that participants felt less overwhelmed by branching scenarios compared to previous, text-heavy training modules. Instead of being overloaded with information, scenarios progressed step by step, providing only the necessary details at each decision point.

Working with AI

When AI Gets Better, Do We Get Worse? – Usable Learning

AI is getting better at lots of tasks. But even though we know we should rigorously verify AI outputs, we’re less likely to do so when AI is generally better. If the AI does well 4 times in a row, you’re not going to check the 5th time very closely. Julie Dirksen explains the psychology and gives examples.

Bot or Not? Text Edition (v2), Lancaster University

Quiz yourself to see how accurate you are at distinguishing AI-generated text from that written by humans.

Digital Learning Nook | Digital Learning Nook

Pooja Jaisingh created a quick warm-up practice activity for L&D called “Learndle.” Given a brief description of situation, type the model, tool, or approach to solve the problem. Each time you get it wrong, you get a new hint.

My Turn with Claude — Design, Code, and Everything In Between – Visual-e-Learning

Jerson Campos published a great “show your work” post about his experiences rebuilding some old training using Claude, specifically comparing having Claude Design do the work for him versus using Claude AI and Claude Code with more explicit direction. Jerson was happier with the results when he did more steering of the AI. The first Claude Design version looked polished but lacked interaction and depth.

This, I think, is where it’s going to separate instructional designers who let AI build their projects for them from those with a wider breadth of knowledge who can actually direct AI to build effective training.

Test your prototype early. Once you have a sound design for a few slides, have the AI build it out so you can test it. Nothing is more frustrating than finishing an entire storyboard, only to find the course player isn’t what you imagined — and then having the AI go back and edit every slide or module. It’s a great way to introduce new bugs. Be specific about what you want and what you can provide — videos, audio, narration, animations (if the AI won’t generate them for you). Then ask for an asset list at the end covering the deliverables you’ll be responsible for.

Disability stock photos

All in Frame

Free stock photos showing authentic images of people with disabilities. This library includes suggested alt text for each image. (Thanks to Kayleen Holt for sharing this.)

Changing people’s minds

Why Good Evidence Sometimes Fails to Change Our Minds

This article is about teachers changing beliefs about instructional methods, but the points about psychology and learning apply broadly. Changing people’s minds isn’t just about providing good information, especially when those beliefs are tied to key values and identity.

We do not evaluate new evidence in isolation. We interpret it through the understandings we already possess, sometimes reshaping new ideas so that they fit our existing thinking.

If the new information fits comfortably with our existing understanding, learning can be relatively straightforward. But when it conflicts with the way we make sense of the world, we rarely abandon our existing understanding immediately. Instead, we usually reinterpret the new information in ways that preserve as much of our existing understanding as possible.

—Jim Hewitt and Nidhi Sachdeva

Working with SMEs

Working with SMEs: 6 Types Every Instructional Designer Should Know – Scissortail Creative Services, LLC

Kayleen Holt describes six types of SMEs with tips on how to work productively with each one.

The post Scenarios, Working with AI: ID Links 8/4/26 appeared first on Experiencing Elearning.

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.