In branching scenarios with simulated conversations, sometimes I see people build every single exchange as an interaction. With that approach, if you’re controlling a character, then every single sentence that comes out of that character’s mouth has to be a decision point. It can get pretty tedious, both for the user and for the ID building it.

Example without a cutscene

Here’s what that might look like with some dialogue excerpted from the middle of a larger scenario.

Decision point 1

Decision point 2

Decision point 3

With a choice for every line of dialogue, that creates 3 decision points, each with 3 choices. That’s 10 screens that have to be built.

Example with a cutscene

Compare the version above to this version using a cutscene. This time, all of the dialogue continues seamlessly. You see some back and forth between the two characters before having a single decision point at the end. Instead of 10 screens, this is only 4 to build (the conversation shown here plus the results of the 3 choices).

See the cutscene in action

You can see the cutscene in action on its own or as part of the complete branching scenario. This full cutscene includes some additional dialogue prior to the script excerpt shown above.

I wrote about the specifics of building a simulated phone conversation previously.

Advantages of cutscenes

Simplify the scenario

The biggest advantage of showing a conversation in a cutscene like this is reducing the total number of slides (from 10 to 4) and decision points (from 3 to 1). That reduces time building the other options, as well as the time writing plausible distractors for the additional decision points.

Reduce cognitive load

Trimming extraneous decision points helps reduce the cognitive load on users. With a cutscene, they can see the conversation and focus their efforts on the decisions that matter. They don’t need to put in cognitive effort on the less important decisions of every line of dialogue.

Meet critical objectives

The cutscene moves the conversation forward quickly to get to the next critical point. In this particular example, the objective is to propose a road mapping. That needs to be a decision point.

The other parts of the conversation aren’t as critical for the learning objective. Therefore, it’s not as important for them to be decision points. I can collapse that dialogue into a single, non-interactive conversation. We need the context, but not everything has to be a decision point.

More tips on streamlining branching scenarios

For more tips for making branching scenarios easier and more manageable, download my guide on Streamlining Branching Scenario Planning and Design. This is a free 25-page PDF guide on how to save time and manage the complexity of branching scenarios while still providing rich, valuable learning experiences.

Originally published 3/3/2020. Updated 4/23/2026.

The post Cutscenes in Branching Scenarios appeared first on Experiencing Elearning.

AI image models compared

These are the specific models I used for testing. Except for Midjourney, I generated all of these within Flora. Flora makes these sorts of comparisons much easier, since you can add the prompt once, select multiple models, and generate them all at the same time.

• Nano Banana 2
• GPT Image 1.5
• Midjourney v7 or v8.1
• Flux 2 Pro
• Recraft v4
• Seedream 5.0 Lite

Prompt 1: A single person

For my first test, I wanted a photorealistic image with a focus on a single person. As I expected, all of the results were pretty good; this is something all the tools can generate now. I like the aesthetic and pose for some results better than others, but none of these were failures.

Editorial photo, an Indian woman, mid 40s, dark hair pulled back in a single long braid, wearing a kurti with a small burgundy geometric pattern, walking in past desks in a modern open office, trees visible through the windows

Prompt 2: Photorealistic objects

For my second test, I used a prompt for two objects: a hard hat and a pair of safety glasses. There were a few issues with these images (the plywood in the Nano Banana image looks too worn, for example), but they weren’t bad. All of the models followed the directions for the focus objects, setting, and camera angle.

Editorial photo, a yellow hard hat and a pair of safety glasses on a stack of plywood sheets on a construction site, low angle

Prompt 3: Illustration

For this prompt, I used the style of “digital illustration” as a starting point. However, Recraft and Flux both failed to generate illustrations initially; they generated photorealistic images instead. I had to change the prompt to “vector illustration” for those image models. With illustrations, you see more variety in the default styles. Obviously, I don’t have a lot of detail in the prompt about the style; that would affect the similarity more.

While it’s not my favorite of this set, I was pleasantly surprised at how well ChatGPT did. The most recent updates to ChatGPT’s image model have made it much more comparable to other tools. It doesn’t always have the yellow filter, and the overall illustration style has greatly improved. His back blends into the back of the bench in this example though, so this would require some editing or iteration to be usable.

Digital illustration, modern corporate style, a Black man typing on his phone, thoughtful expression, wearing a dark blue t-shirt, sitting on a bench in a park, medium shot from the waist up, viewed at a side angle

Prompt 4: Group of people plus text

For my final prompt, I wanted to challenge the models. This time, I prompted for a group of people, plus I asked for text on a whiteboard in the background. The more people you add to an image, the more likely it is that something goes wrong in the generation.

The Recraft image here is the biggest failure out of all of the images for all of the prompts. All of these images have some issues though; this is still where the image models require a lot more iteration and editing to get it right (if it’s possible at all). Most of these images look very obviously AI, especially in the text. Midjourney looks a little better partly because it didn’t actually try to make readable text.

Candid photo of a racially and ethnically diverse team of designers discussing solutions, sitting around a light wooden table in an office conference room, gray walls, whiteboard with brainstorming mind map on one wall

Reflections on the differences

Reflecting on these results, I still find myself drawn to Midjourney. I like the overall look of Midjourney more, and I find that it’s easier to generate a wider range of faces. But Nano Banana is great, and better than Midjourney for consistency (although I may revise that opinion after I test the new Midjourney v8.1 a little more). ChatGPT has improved enough to be genuinely useful now, although it still looks more like stock photography. Flux, Recraft, and Seedream are all useful in some situations too.

If you’re going to pay for a single image tool, I recommend Flora or Freepik. Even though they don’t have access to Midjourney, both Flora and Freepik give you access to multiple image models. You have a lot more flexibility that way.

Your thoughts?

Which examples do you think turned out the best? Which models do you prefer working with? Let me know in the comments.

Further reading

Check out my comparison of AI image generation tools for more information on the strengths and weaknesses of different tools.

The post Same Prompt, Different AI Image Models appeared first on Experiencing Elearning.

How AI is affecting entry-level jobs

The Perils of Using AI to Replace Entry-Level Jobs | Harvard Business Impact Education

One theme I see coming up repeatedly in L&D conversations is that using AI requires expertise to evaluate AI-generated results. That’s fine right now where we have experienced people who built skills pre-AI. But what about entry-level workers now and in the future? If those entry-level jobs are eliminated, how will the next generation learn those skills and judgment? This article has some ideas about restructuring work. This also points to some areas where L&D could help support people whose jobs are redefined and restructured. Training people to question and evaluate AI output and apprenticeships are two possibilities to address the challenges.

Imagine recruiting managers who have never worked at the front lines, never handled customer complaints, never written up notes from consequential meetings, never grappled with the minutiae of operational work. Leadership would become abstract, detached, and dangerously naive.

Junior roles must no longer be defined by the repetitive, automatable tasks that AI can do better and faster. Instead, they should be designed to expose people to the why behind the work.

AI is only useful when paired with critical thinking. Productivity gains are meaningless if they come at the expense of professional judgment.

The default use of AI is substitution: Let the machine do the work and cut headcount. A smarter approach is to redesign workflows, so AI handles rote execution while humans focus on framing the problems, asking better questions, and building relationships.

Consider the analogy of education: If a student outsources every essay to generative AI, they bypass the intellectual struggle that produces deep learning. It is like microwaving ideas: fast, convenient, and unsatisfying. The effort, even the pain, of thinking for yourself is what builds a student’s capacity.

—All quotes above by Amy C. Edmondson and Tomas Chamorro-Premuzic

Is AI closing the door on entry-level job opportunities?

AI will result in both job losses and opportunities, changing the career ladder that used to provide entry-level opportunities and a mostly linear path upward. But eliminating entry-level roles will dramatically affect the long-term talent pipeline.

AI images

Three Steps for L&D Professionals to Legally Use AI Images and Video

Debbie Richards shares tips for using AI image and video legally. Personally, I’d probably add a few other image tools to that list of professional options (like Flora and Freepik), but she’s correct that Firefly is the safest for images based on training on licensed data. Free tools are fine to experiment with, but don’t use them for commercial projects.

Simple Ways to Create Consistent Characters in ChatGPT

Tom Kuhlmann shares his workflow for generating consistent character images using ChatGPT using a GPT or a project with saved instructions. Even if you don’t use ChatGPT for image generation, the descriptions of image styles in the download are useful for working with any tool.

The AI Image Generation System for Learning Designers

Despite the article title of “How to Get Consistent, On-Brand Course Images from Any AI Image Tool,” this system doesn’t actually work with all AI image tools. The process is different with Midjourney, Recraft, Brushless, Flora, etc. But this process will work with any of the LLM-based image tools like Nano Banana, ChatGPT, and Copilot, since those all work in similar ways. That means it covers what most people have access to. The character reference images are key to getting scenes with consistent characters in LLM-based image tools.

The fix is an 3-step process which gives you superpowers in AI image generation:

• Write a visual brief — answer six questions that close the creative and pedagogical gaps before you generate a single image.
• Build a mood board — gather images that capture the lighting, energy, and environment of your learner’s world. Select the 3 that look like they were shot by the same photographer on the same day and upload them individually as style references.
• Create character anchors — your style references fix the visual world; your character references fix the people inside it. For each named character, generate a head-and-shoulders image on a neutral background, facing forward. This is your master reference. Attach it alongside your style references every time you generate a scene featuring that character — and the tool stops making casting decisions on your behalf.

—Dr. Philippa Hardman

AI literacy framework

AI Literacy Framework updated April 2026

Stella Lee has updated her AI Literacy Framework to include 8 interconnected domains covering foundational knowledge, critical practice, and responsible leadership.

Rebuilding simulations with AI

I Rebuilt a 10-Year-Old Simulation with AI in Half a Day. Here’s What I Learned.

Trina Rimmer shares her experiences rebuilding an old Rise scenario activity as a new experience with Claude. You can see the projects side-by-side to compare. Trina’s reflections add a lot of value here; you can see how the AI tools enabled her to do something new, but that was only possible because of her existing instructional design skills. If she didn’t have that expertise, then she couldn’t have gotten as successful a result with AI.

And then there was Claude’s desire to help. It was relentless. I pushed back constantly on anything that broke the “fourth wall,” anything that handed the learner an insight before they’d reached for it themselves, and anything that sounded like a training exercise instead of a real situation. Productive struggle is where learning happens.

AI is a design collaborator, not a design replacement. Every meaningful improvement in the rebuilt project came from my instructional design judgment, not from Claude’s defaults. The dialogue, the model interaction structure—me insisting that learners identify what worked before being told—and the debrief—me pushing back on Claude’s first version until it asked more than it told—that was all me. Claude made those things possible faster, but without the ID judgment driving the prompts, the end result would have been slicker but shallower.

—Trina Rimmer

The post Entry-Level Jobs, AI Images: ID Links 4/14/26 appeared first on Experiencing Elearning.

You’ll learn how to:

• Apply a repeatable prompting framework that works across AI image tools
• Create diverse, representative character images for scenario-based learning
• Keep a consistent visual style across an entire course
• Generate icon sets and visual metaphors in a single prompt
• Navigate copyright, ethics, and commercial use considerations

For the post header image below, I used Midjourney to create the four images in a consistent style and colors. While Nano Banana is better at consistent character images, Midjourney is still my favorite tool for interesting and cohesive illustration styles. This set uses sref 361625325, which means I just needed to add that code to the end of my prompts to get these results fast. You can explore more styles to use on Midjourney’s website.

Watch the recording

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

Handout and practice exercises

This was a hands-on webinar, and you can follow along with the practice exercises with the recording.

IDIODC podcast

For more about AI images with the folks from dominKnow, watch or listen to my conversation about AI-generated images with Paul Schneider and Chris Van Wingerden on the Instructional Designers in Offices Drinking Coffee (IDIODC) podcast.

Character consistency webinar

If you’re interested in learning more about character images with AI, check out my webinar Character Consistency Solved: AI Image Generation Workflows and my follow-up character Q&A post.

I try not to post webinar recordings back-to-back on my blog, but March was a busy month for speaking for me with five webinars. At least this week’s recording is on a different topic from the branching scenario webinar I shared last week. I’ll be back to my regularly scheduled post schedule soon!

More on AI and instructional design

Check out my growing collection of articles about AI and instructional design, including a number of posts specifically focused on AI image generation.

The post dominKnow Webinar: Build Cohesive Learning Visuals with AI appeared first on Experiencing Elearning.

I gave a quick overview of branching scenarios, their benefits, and when to use them. We looked at some before and after examples of branching scenarios. This included comparing a scenario I built manually pre-GenAI and how the workflow can change with AI. I shared some examples of how my process is changing with AI-generated images for scenarios and using scenarios to assist and augment my writing. We discussed the options for AI video generation and how fast those tools are improving. Mike demonstrated some new capabilities in Near-Life to speed up the process of building scenarios where the AI generates a draft structure for you.

Watch the video

If the video isn’t embedded below, you can watch the recording of my Near-Life webinar on YouTube.

More webinars on scenarios

I’ve given a number of webinars in the past few years through Training Mag Network, TLDC, and other organizations. Check out my collection of webinars on scenarios for tips on working with SMEs, improving engagement, managing the complexity of scenarios, and more.

The post Near-Life Webinar: Leveraging the Power of AI in Branching Scenario Design appeared first on Experiencing Elearning.

I use affiliate links when I share books and some additional resources (like the SiteGround link below). It won’t cost you anything additional, but a small portion of the purchase price comes to me to help pay for hosting my blog. I have partnered with elearningfreak on this post, but all opinions are my own.

Why do you need a portfolio?

If you’re wondering why you need a portfolio, read Tom Kuhlmann’s explanation about being “at the crossroads when opportunity and preparation meet.” Christopher Pappas provides another 7 reasons you need a portfolio, if you need more motivation.

I have heard all the excuses why you can’t build one: everything is confidential, you don’t have the tools, no time to work on it, etc. But if you’re looking for work and trying to get interviews or attract freelance clients, you still need to be able to show that you have the skills you say you do.

What to include

My post on 30+ ideas for portfolio samples can give you some inspiration if you need to create new artifacts.

Watch the recording of my webinar with Danielle Watkins on 5 Portfolio Mistakes Instructional Designers Keep Making (and How to Fix Them).

Kristin Anthony’s “Go Design Something” site automatically generates ideas for portfolio samples.

This post on building an instructional design portfolio includes what to include and additional tips.

These 10 tips for building a portfolio include picking the right projects and pairing each project with a description.

Tools for creating samples

Storyline and Rise

Prospective employers expect to see a few samples using standard tools. Two of the most common tools are Articulate Storyline and Rise.

Rise is part of the Articulate 360 Suite. It’s easy to learn, but be cautious of relying too heavily on their templates and course starters. Plenty of hiring managers will recognize those course starters.

Job seekers often can’t afford to purchase expensive software licenses. If you’re a student, discounts are available for Articulate 360 (which includes Storyline and Rise).

Articulate offers 30-day free trials. If you storyboard and plan before you start your trial, you can make several samples during that month.

Authoring tool options

Although employers are likely to look for Storyline, you can use other tools. In fact, right now I see a lot of interest in other authoring tools. Mike Stein’s comparison of elearning authoring tools is a great place to look for alternatives, many of which are more affordable than Articulate.

iSpring’s tools are solid alternatives, and they’re hosting a course creation contest this spring. If you register by April 24, you’ll get free access to iSpring and training to help you use it effectively. This would be a great way to create a sample and potentially win prizes. I’m on the panel of judges for this contest.

I’ve used Genially to build interactive activities for a client before, and it’s another good alternative authoring tool for samples. Genially’s free plan would be sufficient for your portfolio samples.

I haven’t personlly tried Parta, but I’ve heard it as another option. One reason it might be a better choice for a portfolio is that you can pay for the license monthly, rather than for the whole year. If you just need a month or two to build your samples, then you can pay for that and then unsubscribe later.

Adobe Captivate is much less in-demand than it used to be, but it’s an option for portfolio samples. It’s also possible to earn a free Captivate license by participating in their community.

Video tools

Camtasia is a great option for videos. Check out Cara North’s video series on creating a Camtasia portfolio sample from start to finish for a plan and example.

Animated videos can make great, visually appealing portfolio samples. PowToon and Vyond are popular choices.

Open source tools

If you want to use open source tools, check out Adapt and H5P. Neither one has seen widespread adoption, partly because they both require more technical expertise. However, you can create some really cool things with both.

It’s more specialized, and therefore not necessarily a good choice for everyone, but I also have Twine samples in my portfolio. Twine is great for branching scenarios, plus it’s free and open source. Learn more about Twine from my posts to get some ideas.

Hosting your portfolio

This blog and my portfolio were both built with WordPress. These are both self-hosted sites now, although my blog was on WordPress.com for many years. You can use a free WordPress.com site as your portfolio as a job seeker, but you’ll have to host your samples somewhere else or upgrade to a paid plan that allows plugins. (And if you’re upgrading to a paid plan for WordPress, you might as well just pay to host it yourself—you can do that cheaper.)

Check out Dianne Hope’s article on how to build a portfolio in WordPress.

In her article, Dianne explains how to use a free WordPress plugin to upload elearning samples. That plugin works regardless of what tool you use to create your samples (Storyline, iSpring, etc.).

I host my websites on Siteground. Shared hosting starts at $2.99/month for the first year, so it’s quite affordable to get your own site and have full control.

Free and low cost hosting options

Some people use template sites like use Google Sites, Wix, Weebly, or Squarespace. Those sites can work, especially if you find a template you like since editing can be challenging. The designs can be limited, and it can be challenging to post real samples with interactivity. It’s not my first choice personally, but it definitely works for many people.

If you’re using a free site like Wix, you probably need to host your samples elsewhere. WordPress.com and other free hosts don’t allow you to upload published Storyline or SCORM files (at least not on the free plan, and not necessarily even on a paid plan).

You can use Amazon AWS storage to host and share your files, linking to them from your portfolio. Google Cloud is another option; Kimberly Goh’s video explains how to use Google Cloud to host portfolio samples. Both of those options for file hosting are either free or very low cost for most portfolios.

Mike Taylor lists several free or low-cost options for hosting in this post (although a few, like Dropbox, are no longer options).

Portfolio examples

It helps to see other portfolios as inspiration for your own work. See how others have organized their samples and what they include.

Check out this post with 24 great examples of instructional design and elearning portfolios, collected by Scott Winstead. (Mine is included.)

The Articulate community also has a collection of portfolios.

Portfolio building course with personalized assistance

What if you need more than a collection of resources—you need a structured process for building your portfolio with step-by-step guidance and personalized feedback? Dani Watkins and I are re-launching our portfolio course, Create a Portfolio That Gets You Hired. We previously taught this course for UC-Irvine, but now we’re offering it publicly with new updates. If you want a clear framework to build your portfolio so hiring managers can see how you think, design, and solve problems, this course is for you.

Your favorite resources?

Do you have a favorite tool for creating portfolios or a resource I’ve missed? Let me know.

Originally published 3/16/2011. Republished 7/2/2019, updated 7/21/2022, 1/1/2024, 3/6/2024, 2/3/2025, 12/5/2025, 3/19/2026.

The post Instructional Design Portfolio Resources appeared first on Experiencing Elearning.

Elearning Characters

Character-Driven Learning Experiences

Great insights here from Teresa Moreno about using characters effectively in elearning. I especially appreciate the learning science angle here focusing on improving self-efficacy through “coping models.”

A mastery model demonstrates perfect performance from the start. They know exactly what to do, execute flawlessly, and model ideal behavior. This is what most learning designers and SMEs default to: show the “right” way immediately.   A coping model struggles, verbalizes their thinking process, makes mistakes, and demonstrates the process of overcoming challenges. They eventually succeed, but only after working through realistic difficulties.

Characters in learning design don’t need movie-like backstories. They need a recognizable problem intrinsically connected to what people need to learn. The swap question is the real test: could this character or story be replaced without changing what’s learned? If yes, it’s probably decoration.

—Teresa Moreno

Generating AI images

Agentic Image Generation

This is an interesting example of using agentic AI to generate an infographic based on a blog post. This uses Claude Code to connect Nano Banana Pro for image generation with an additional tool for providing AI feedback on the image. The workflow iterates and improves the initial image based on the AI-generated feedback, without human intervention.

How to use JSON to build better AI image prompts

JSON is a way of structuring your image prompts, clearly labeling what each detail is. It can help you think through the specifics of your prompt and generate more systematic and repeatable prompts. This prompt structure doesn’t work with all tools (including Midjourney), but it’s something to consider for more advanced prompting in other tools.

Fixing Plastic AI Skin: The Complete Guide to Realistic Prompts – Rezience | Andy H. Tu

While I don’t think that prompting alone will fix all problems with waxy skin texture in AI images, better prompting can improve your results. The specific phrases and tips here should work in any image generation tool (but watch out for the negative prompts; sometimes those confuse the models).

Midjourney releases Niji v7 & an interview with Google

Midjourney’s new Niji 7 model is designed especially for anime, but it should show improvements for other character illustration styles in consistency and prompt understanding. This article also includes some notes on Freepik’s prompt generation feature.

Working with AI

AI: You Still Have to Know Stuff – Usable Learning

Julie Dirksen articulates what many of us have experienced. Yes, AI can be useful…but we still have to have enough expertise to know what’s good about the AI output. You have to know what to discard or revise. Even as AI gets more accurate, you need to know what quality results look like. Plus, what happens when people come into jobs and don’t have that prior experience that helps them evaluate AI output?

I need to use my expertise to craft a prompt that will get the most accurate result, while still recognizing the parts that need revision.

—Julie Dirksen

Making the Grade: Can AI Be Trusted to Score Assessment Tests?

How do you train AI to score open-ended assessments and provide feedback? The same way you train human assessment scorers (a job I did for a few summers): with a detailed rubric, examples, and spot checking the results.

Memory research

Memory Rewritten: Study Finds No Clear Line Between Episodic and Semantic Retrieval – Neuroscience News

Previous research had pointed to the idea that episodic and semantic memory were different types of memory that used different parts of the brain. This study contradicts that earlier theory, finding that the whole brain is involved in memory.

…there is no difference in neural activity between successful semantic and episodic retrieval.

Episodic memory refers to the ability to remember a past event that occurred in a particular spatial and temporal context. This type of memory supports the human capacity to re-experience events from our past, as a form of “mental time travel”. Semantic memory, on the other hand, refers to the ability to remember facts and general knowledge about the world that are retrieved independently from their original spatial or temporal context.

Useful tools

BuddyBar – Color Palette Manager for Design Tools

A free color palette tool for Windows, Mac, or Chrome. Add your colors so you can copy hex codes or apply them in programs. This works with Storyline and Rise.

Grasp

AI tool to create a personalized collection of resources and a sequence to help you learn a skill based on a goal you identify. h/t Nejc

Chat Scenario Builder

Beta version of a vibe coded tool to create branching scenarios that look like chat conversations. I’m saving this to test later.

The post Elearning Characters, Generating AI Images: ID Links 3/17/26 appeared first on Experiencing Elearning.

Obviously, working with an LLM isn’t the same as working with an actual SME on a project. For a real project, even if you did use an LLM this way, you’d need to verify everything with an actual expert with the knowledge to find errors. LLMs can confidently produce inaccurate information, and they probably will sometimes with these prompts. But even though hallucinations are possible (and generic content is likely), the risk of inaccuracy isn’t that high for a portfolio sample. You’re showing your process and how you would work with a SME if you had access to one, not trying to build something for actual implementation. Still, use your common sense; if something seems off, verify it with other sources.

Brainstorm portfolio sample ideas

One way to use an LLM is to brainstorm ideas for your portfolio samples. Yes, you can build something about how to make a sandwich or about a hobby where you have expertise. But sometimes one of the blockers in looking for an ID job is showing that your skills translate to workplace training, especially if you’re changing careers from teaching or another field. In those situations, having samples explicitly related to workplace training might give you an edge over other candidates. You can use my post with 30+ ideas for portfolio samples, but of course that’s just a starting point. AI can easily help you brainstorm more.

Here’s a sample prompt for brainstorming. Adjust this to target the type of work you’re most interested in and skills you want to highlight.

I'm an instructional designer building portfolio samples to demonstrate my skills to potential employers. I want to create samples that show range across different formats and contexts.

Please brainstorm 10 ideas for portfolio samples I could create. For each idea, include the format (e.g., elearning module, job aid, video script, facilitator guide), a potential topic or industry, and one specific skill it would demonstrate to a hiring manager.

I'm particularly interested in [insert any preferences: industries you want to work in, formats you want to practice, skills you want to highlight].

Generate a Fictional Organization and Training Need

Another problem with making your own portfolio samples is that it doesn’t reflect a real business problem. You can create your own fictional business problem though; that lets you show your thought process and how you’d approach similar issues in your work.

Sample training scenario prompt

I'm an instructional designer creating a portfolio sample on the topic of [insert topic]. I need a realistic but fictional scenario to work from.

Please create a fictional organization and training need for me. Include the organization name, industry, size, and a brief description of what they do. Then provide a one-paragraph summary of a training need related to [insert topic], including who the learners are, what problem or gap prompted the training request, and any initial goals the organization has mentioned. Make the scenario feel grounded and realistic rather than overly simplified.

Example adapted prompt and results

I already had a topic in mind: stormwater protection. I’ve created some elearning on this topic in the past. While I’m definitely not a SME, I know enough to at least recognize glaring errors in the LLM-generated content. So, I adapted the prompt to focus on that topic and an audience I’m familiar with.

I'm an instructional designer creating a portfolio sample on the topic of stormwater protection. I need a realistic but fictional scenario to work from.

Please create a fictional municipal government department and training need for me. Include the department name and a brief description of what they do. Then provide a one-paragraph summary of a training need related to stormwater protection, including who the learners are, what problem or gap prompted the training request, and any initial goals the organization has mentioned. Make the scenario feel grounded and realistic rather than overly simplified. The problem or gap should help narrow the topic to something achievable rather than the broad topic of stormwater protection.

Using Claude Opus 4.6 as my LLM, I got this scenario to work with.

Department: City of Lakeport Department of Public Works — Stormwater Management Division

The Stormwater Management Division oversees the maintenance, inspection, and regulatory compliance of the municipal stormwater drainage system for the City of Lakeport (pop. ~95,000). The division is responsible for managing approximately 340 miles of storm drain infrastructure, ensuring compliance with the city’s Municipal Separate Storm Sewer System (MS4) permit under the Clean Water Act, and coordinating with other city departments and private contractors on construction and land disturbance activities that affect stormwater runoff.

Training Need

The division’s MS4 permit requires that all city personnel whose work involves or impacts stormwater infrastructure follow proper illicit discharge detection and reporting procedures. Following a recent state audit, the division learned that field crews in three departments — Public Works, Parks and Recreation, and Fleet Maintenance — were inconsistently identifying and reporting non-stormwater discharges entering the storm drain system, such as wash water, chemical spills, and sediment-laden runoff from maintenance activities. In several cases, crews observed discharges but did not file reports because they were unsure whether what they saw qualified as a violation or did not know how to use the city’s updated reporting system. The Stormwater Management Division has requested training for approximately 160 field crew members and their supervisors, with the goal of improving crews’ ability to recognize common types of illicit discharges they are likely to encounter during routine work, follow the correct escalation and reporting procedures, and document incidents using the city’s FieldReport mobile platform. The division hopes to see a measurable increase in properly filed discharge reports and a reduction in repeat audit findings when the state returns for a follow-up review in eleven months.

Stand-In SME Interview

Use this sample prompt as a starting point to prompt for a SME interview.

Sample SME interview prompt

I'm an instructional designer creating a portfolio sample, and I need to practice conducting a SME interview. Please act as a subject matter expert on [insert topic] who works at [insert organization name or describe the fictional context].

As we talk, respond the way a real SME would. This means you should answer my questions based on practical, real-world knowledge of the topic, but also introduce realistic constraints I'd encounter in an actual project (limited time, budget, resources, or learner availability). If I make assumptions or suggest approaches that might not work well, push back or ask clarifying questions. Be occasionally skeptical of my recommendations—not difficult for its own sake, but the way a busy expert might question whether a suggested approach is really necessary or feasible.

I'll ask you a series of questions about the training need, the content, the learners, and the context. Ready to begin?

Example Simulated SME interview

I adjusted the first paragraph of the interview prompt to align with my Lakeport scenario above.

I'm an instructional designer creating a portfolio sample, and I need to practice conducting a SME interview. Please act as a subject matter expert on water systems and protection who works at the City of Lakeport in the Department of Public Works.

Claude’s “thinking” about how to respond:

The user wants me to role-play as a subject matter expert (SME) at the City of Lakeport’s Department of Public Works, Stormwater Management Division. They want me to behave realistically — knowledgeable but busy, occasionally skeptical, introducing real-world constraints, and pushing back when appropriate. I should stay in character and wait for their questions.

Let me establish a persona. I’ll be someone like a Stormwater Program Coordinator or Compliance Manager — someone who knows the technical side well and has been dealing with the audit findings. I’ll be cooperative but realistically busy and occasionally questioning whether certain instructional design approaches are practical for field crews in a municipal setting.

I’m ready to engage with whatever they throw at me.

Claude’s SME persona and intro

Yeah, I’m ready. I’m Dan Morella, Stormwater Compliance Coordinator here in the division. I’ve been with Public Works going on twelve years now — started out on a field crew myself before I moved into the compliance side of things. I’m the one who put in the training request after we got the audit results back, so I can speak to most of what you’ll need.

I’ll be honest with you, though — I’ve got a pretty full plate right now between the corrective action plan and our wet season prep, so I’m hoping we can keep these conversations focused. I’ve done training projects with consultants before and sometimes it feels like we spend more time in meetings talking about training than it would take to just do the training, if you know what I mean. But I get that you need information from me to build this thing right, so let’s get into it. What do you want to start with?

Questions and answers

Then, I used questions from “How to Conduct a Lightning-Fast Needs Assessment Clients Will Love.” (As a side note, I met Sardek Love at the Training 2026 Conference and thanked him for this article since I use and cite it regularly. He said it’s the most popular piece he’s written for ATD.)

OK, let's get right into it then. I promise to stay focused. I've got a few questions to start with to make sure nobody wastes time and money on something we don't need. What's the problem we're trying to solve here?

So the short version is, we got dinged on our state audit back in October. The auditors reviewed our illicit discharge detection records and found significant gaps. We’re required under our MS4 permit to show that we have a functioning program for detecting and reporting non-stormwater discharges — things like wash water going into a storm drain, sediment runoff from a job site, somebody dumping something they shouldn’t. And we couldn’t demonstrate that consistently.

But here’s what really got my attention. It’s not that discharges were happening and nobody was catching them. I mean, some of that too, probably. But when I started digging into it after the audit, I talked to a bunch of the crew leads, and what I kept hearing was, “Yeah, I saw something but I wasn’t sure if it was a problem,” or “I didn’t know I was supposed to report that.” One guy in Parks told me he saw soapy water running into a catch basin from a fleet vehicle wash and just figured someone had already handled it. Nobody had.

And then on top of that, we rolled out the FieldReport app about eight months ago for digital reporting, and I don’t think half these guys have even opened it. Some of them are still trying to fill out the old paper forms, which technically we don’t even process anymore.

So it’s really two things — people not recognizing what they’re looking at, and people not reporting it properly even when they do. Does that help narrow it down, or do you need me to get more specific?

Let's get a little more specific. Which metrics really matter here? What are we trying to affect that we can measure?

Good question. Alright, so the biggest one — the one my boss cares about and the one the state cares about — is the audit. We’ve got a follow-up review coming in about eleven months. If we get flagged again on the same findings, we’re looking at potential fines and a consent order, and nobody wants that. So at the end of the day, we need to pass that follow-up.

But that’s kind of a lagging indicator, right? I can’t wait eleven months to find out if the training worked. So the things I’m watching closer to real time are, first, the number of illicit discharge reports coming in through FieldReport. Right now we’re averaging maybe eight to twelve reports a month across all crews. Frankly, for a system our size with 160 people in the field every day, that number should be higher. I’d like to see it at least double, and I want to see reports coming in from Parks and Fleet, not just my Public Works crews who were already doing most of the reporting.

Second, report quality. We’re getting reports that are missing key fields — no photos, no location pin, vague descriptions like “saw something in the ditch.” That’s almost as bad as no report because I can’t action it.

Now, if you’re about to ask me about test scores or something like that, I’ll be honest — I don’t really care if somebody can pass a quiz. I care if they do the right thing on a Tuesday morning when they see something weird flowing into a drain. Can we measure that?

Full simulated interview

My full simulated SME interview ended up being 9 pages long, so I won’t include it all here. You can download the entire chat if you want to see how I used Claude as my stand-in SME and role played an interview. Even if you’ve never actually had an instructional design job, an LLM gives you the opportunity to practice interviewing a SME or stakeholder. You could even have a document to show your skills.

More ideas for using an LLM to build portfolio samples

While role playing a SME is one way to use AI to build your portfolio samples, you have plenty of other options too. Here’s a few more ideas.

• Act as a learner persona to test whether your content and explanations make sense to someone unfamiliar with the topic
• Review your storyboard or script and provide feedback on clarity, flow, and instructional effectiveness
• Generate realistic sample data or scenarios for practice activities and assessments
• Suggest potential misconceptions or common mistakes learners might have on a topic so you can address them in your training
• Brainstorm visual or interaction ideas when you’re stuck on how to present content in an engaging way
• Write placeholder content or first drafts that you then revise and improve in your own voice

Human help with your portfolio

While AI can be a great help with your portfolio, sometimes you need a human to provide feedback and guide you. Dani Watkins and I are launching a new step-by-step course: “Create a Portfolio That Gets You Hired.” This is an updated version of the portfolio course we previously co-taught for the University of California – Irvine as part of their eLearning Instructional Designer certificate program.

Your portfolio is not a storage unit. It’s a strategic story about how you design learning experiences. This course teaches you how to tell that story clearly, confidently, and professionally.

Would it help you to have a framework for building your portfolio, breaking the tasks down over 5 weeks? Would you like personalized feedback and coaching as you build and iterate your portfolio? Read more about the course so you can decide if it’s the right fit for your needs.

The post How to Use AI as a Stand-In SME for Portfolio Samples appeared first on Experiencing Elearning.

Katrina Kennedy on Learning Transfer

While I’ve known Katrina online for years, I think this was the first time I’ve ever had the opportunity to hear her speak live and in-person. If you ever get a chance, please attend her sessions! She did such a fantastic job modeling all of the techniques she talked about throughout her session. For me, this session was as much about learning from her example as a speaker as it was about the content.

One key idea I noted was some learning research I hadn’t seen previously about the “Optimal Error Rate” for training, which was about 16%. Learners should get answers right in practice most of the time. If it’s too hard, we check out. If it’s too easy, we get bored and check out.

While we often focus on techniques to improve learning transfer during sessions, we don’t always do as much before and after. Even something simple like a “pre-flection” question before starting can help focus attendees and improve transfer.

Chrisanna Paxton McMillan on Accessible Elearning

I appreciated seeing Chris’s examples of accessible elearning that isn’t boring and her tips on how to build interactive elearning that meets WCAG requirements.

One tip I want to try is including text with 0 opacity for screen readers. You can remove some objects from the focus order and then add objects that are only readable by screen readers.

Another idea I noted: pregnant women working are underrepresented in training images. That makes sense; stock images of pregnant women tend to show hands holding their belly, eating, or feeling sick. That’s something I’d like to see if I can do better with AI image generation now.

Jeff Batt on Vibe Coding

When I attended Jeff’s session on vibe coding at Training 2025, I felt like you really needed to have some programming or app development background to be able to describe what you want in specific enough terms to build anything usable. In fact, my notes say, “I think this is too complex for the typical user.”

I don’t feel that way anymore. The technology has advanced to a point where you can describe what you want in plain language, and the tools can build something usable quickly. It works best if you start simple and then add features iteratively, rather than trying to do everything in a single perfect prompt to start.

I have to think about how I might use this for practical purposes, but for fun in the session I created an 80s-style arcade game with questions about instructional design models and principles. You can try the game and the flash cards I built; I added them both to a Rise course as embedded code blocks.

Diane Elkins on Getting Value from Visuals

I appreciated Diane’s session on getting the maximum instructional value from visuals because it relates to the work I do with AI images. We have the ability to generate just about anything we want for images now, but if those images are irrelevant or distracting, it doesn’t do us any good.

The first principle Diane shared was “illustrate, don’t decorate.” Every slide and image should have a goal. Use images to help people understand or remember. Give them a reason to care about the topic with an emotional connection. Use images to provide sign posts or signal structure in your training.

Kassy LaBorie on Real Connections in Virtual Classrooms

Kassy had lots of fun activities to demonstrate, as she always done. This year, she used Suno to generate a song for the session with details we picked as the audience with polls. Suno (and other tools like Udio) are so easy to use that you could generate “theme songs” for each week in a multi-week course.

Karin Rex on Storytelling with Data

I don’t actually do much work with data, but I was interested in learning Karin’s framework.

• Examine the data for patterns and contrasts.
• Expose the danger of doing nothing
• Explain the heart of the matter. Write one sentence that captures what needs to happen for a happy ending.

Megan Torrance on AI Implementation

Megan’s session was about moving “beyond the pilot” and making thoughtful AI implementation decisions. What I got out of this session was a framework with questions to guide my conversations with clients related to AI. I appreciated thinking through both her sample case and one of my own real projects to think through where I might have gaps in what I know and need to probe deeper.

“The accessibility of AI tools and the illusion of instant results demand more deliberate, inclusive approaches.”

A few more images

I didn’t take as many photos this time as I have at past conferences. I was more focused on my conversations with all the wonderful folks attending than I was at pulling out my phone. But here’s a few more snapshots from Training 2026.

The post Key Ideas from the Training 2026 Conference appeared first on Experiencing Elearning.

What we discussed

• Challenges with Stock Photos
• AI Image Generation for Scenarios
• Experimenting with AI for Blog Posts
• Tools for Consistent AI Images
• Advanced AI Tools and Techniques
• Discussing Free AI Tools and Budgeting
• Subscription Models and Tool Switching
• AI Image Generation and Bias
• Legal and Ethical Considerations in AI
• Effective Prompting Techniques
• Upcoming Hands-On Session

Watch the IDIODC podcast interview

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

Listen to the podcast

I didn’t show any images during this interview, so you can just listen to it without losing anything important. The podcast is available on Apple Podcast and Spotify.

Read what we discussed

Don’t feel like listening? Check out the AI images post on the dominKnow blog for a longer summary of our conversation.

Upcoming hands-on session on AI images

Next month, I’ll be leading a hands-on session where you can get tips and practice using my framework for image prompting. This webinar, hosted by dominKnow, is on Thursday, March 26 at 11 AM EDT.

Register for Build Cohesive Learning Visuals with AI: A Hands-On Session.

The post IDIODC Podcast: AI-Generated Images for Learning Content appeared first on Experiencing Elearning.