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.

Local LLMs

How To Run an Open-Source LLM on Your Personal Computer – Run Ollama Locally

These directions for running an LLM on your own computer include both the less-technical method with Ollama’s one-click installer and the more technical command line options.

AnythingLLM | The all-in-one AI application for everyone

AnythingLLM makes it easier to run an LLM locally. If you run everything on your local machine, nothing is sent to a server elsewhere, protecting the privacy of your data.

AI ethics and risks

Don’t Panic: When Should AI Coaches and Assistants Request Human Intervention? – Parrotbox

Thinking about a “human in the loop” is a good start, but what does that really look like if you’re using chat bots or AI coaches at scale? I really like the example of levels of risk for safety in mental health and when chats should be reported or escalated to a human for intervention.

Meet Thaura | Your Ethical AI Companion

Thaura AI is designed as an ethical LLM. It doesn’t train models on your private data, has transparency about their business model, and advertises that it uses 94% less energy than ChatGPT.

The Hidden Mirror: Why Your AI is Only as Good as Your Thinking

Debbie Richards writes about critical issues related to working with AI: our own human cognitive biases. AI can reflect and amplify our own mental shortcuts. Being aware of our cognitive biases can make us more effective at working with AI.

The researchers identify three critical stages where our own thinking can steer AI off course:

Before Prompting: Our past experiences create a “halo” or “horns” effect. If you’ve had great results, you might over-trust the tool for tasks it isn’t ready for. Conversely, if you’ve been spooked by headlines about hallucinations, you might avoid it even when it could be genuinely helpful.

During Prompting: How we frame a question matters. “Leading question bias” happens when we bake the answer into the prompt, like asking “Why is product X the best?” This encourages the AI to ignore weaknesses. There is also “expediency bias,” where we settle for the first “good enough” answer because we’re under time pressure.

After Prompting: Once we have an output, the “endowment effect” can make us overvalue it simply because of the effort we put into the prompt. We also have to watch the “framing effect.” How we present that AI-driven data can completely change how our audience feels about it.:

—Debbie Richards

Something Big Is Happening

I’m not entirely convinced by this article, but I try to read opinions from a variety of sources and perspectives on AI. This author explains that the pace of AI is moving much faster than most people realize, and then argues that the amount of disruption AI will cause will be more significant and quicker than most people expect.

AI companies will fail. We can salvage something from the wreckage | AI (artificial intelligence) | The Guardian

Cory Doctorow has written a long article on the risks and problems of AI, particularly in the way that AI companies promote and hype the benefits of AI.

In automation theory, a “centaur” is a person who is assisted by a machine. Driving a car makes you a centaur, and so does using autocomplete. A reverse centaur is a machine head on a human body, a person who is serving as a squishy meat appendage for an uncaring machine.

“And if the AI misses a tumor, this will be the human radiologist’s fault, because they are the ‘human in the loop’. It’s their signature on the diagnosis.” This is a reverse centaur, and it is a specific kind of reverse centaur: it is what Dan Davies calls an “accountability sink”. The radiologist’s job is not really to oversee the AI’s work, it is to take the blame for the AI’s mistakes.

This is another key to understanding – and thus deflating – the AI bubble. The AI can’t do your job, but an AI salesman can convince your boss to fire you and replace you with an AI that can’t do your job.

For AI to be valuable, it has to replace high-wage workers, and those are precisely the workers who might spot some of those statistically camouflaged AI errors.

After more than 20 years of being consistently wrong and terrible for artists’ rights, the US Copyright Office has finally done something gloriously, wonderfully right. All through this AI bubble, the Copyright Office has maintained – correctly – that AI-generated works cannot be copyrighted, because copyright is exclusively for humans.

The fact that every AI-created work is in the public domain means that if Getty or Disney or Universal or Hearst newspapers use AI to generate works – then anyone else can take those works, copy them, sell them or give them away for nothing. And the only thing those companies hate more than paying creative workers, is having other people take their stuff without permission.

Research on AI voices and avatars

Do AI Voices and Avatars Improve Learning? Here’s What the Data Says

TechSmith conducted a global study to determine how AI voices and avatars affect learning. I was surprised at how well the high-quality AI voices performed. We seem to have crossed the threshold where high-quality AI voices perform comparably to human voice actors. I was also surprised at how well the AI avatars did, although their recommendations for specific use cases do make some sense. I wish they’d also done a separate control with no narrator visible on screen (AI or human). The fact that AI avatars can be comparable to humans in some instances isn’t that shocking, I guess, but I really want to see how it compares to just having the slide content and no face on screen.

What really makes learners pay attention? A voice that sounds clear, warm, and polished — not whether it’s human or AI. As voice quality improved in the study, so did professionalism ratings. In fact, 92% of viewers said the high-quality AI voice made the video feel professionally produced.

Results from the “pop quiz” portion of our study make the pattern clear: correct answers increased as voice quality improved. In fact, the high-quality AI voice produced the strongest retention numbers, aside from one low-quality human outlier.

But are AI voices distracting overall? It depends. Low-quality, synthetic voices are unmistakable and draw attention away from the content. When the AI voice sounds natural, many viewers can’t distinguish it from a human voice. The difference is less jarring, and information retention holds steady or even improves.

AI avatars aren’t distracting by default, but size matters. When an avatar fills the screen, viewers are more likely to notice robotic traits like lip sync issues, eye contact, limited facial movement, awkward blinking, or unnatural breathing.

The right format depends on your video’s purpose. Use this quick decision guide: Screen-heavy, procedural, and frequently updated content: High-quality AI voice with screen recording, plus an optional AI avatar in PiP. Emotionally sensitive, culture-setting, or leadership-driven content: Human presenter with a human voice.  Long-form, concept-heavy learning: A mix — human-led modules for core ideas, supported by AI-voiced micro-lessons and refreshers.

—Stephanie Warnhoff

Desirable difficulties

A Deep Dive into Desirable Difficulties

I’ve seen some misunderstandings on desirable difficulties on social media recently. This article has an understandable explanation of what desirable difficulties are (techniques that may initially cause errors and short-term performance issues but in the long run improve learning and task performance). The techniques include varied practice, spacing, reduced feedback and guidance, retrieval, and interleaving. If you’re new to the idea of desirable difficulties, this will give you a solid foundation.

Difficulties are desirable when they boost learning, not performance.

For example, when learning to drive, it would be easier to practice by driving round the same block multiple times, with an instructor sitting beside you and telling you exactly what to do. As a learner under such conditions, you’d make very few errors, if any.

However, once our lessons are over, we have to drive without an instructor telling us what to do, on complex and sometimes unfamiliar roads. The desirable difficulties framework would suggest, therefore, that practice should resemble that realistic situation, with a variety of road conditions to deal with, and reduced guidance or feedback.

Event segmentation theory

This article includes some great research translation by Tom McDowall about Event Segmentation Theory. We talk about “chunking” content to support learning, but we often rely on time or intuition to determine where to break up content. Event Segmentation Theory provides an evidence-informated approach to more meaningful divisions so you can improve the effectiveness of your training based just on where you add breaks. Tom includes lots of citations for further reading.

Your brain doesn’t process the world as one unbroken stream. It automatically divides ongoing experience into discrete chunks, which researchers call “events,” and does so continuously, without you deciding to do so or being aware that it’s happening.

Information present at a boundary, the moment when one event ends and another begins, gets encoded more strongly than information in the middle of an event. The boundary acts like an attentional gate: it opens briefly to let new information in, and that information gets a better foothold in long-term memory as a result (Kurby and Zacks, 2008).

There’s a trade-off, though. While boundaries improve memory for what happens at the transition point, they impair memory for temporal order across the boundary. Items that span a boundary are harder to sequence correctly and are remembered as being further apart in time than they were (Ezzyat and Davachi, 2014).

Six features of a situation reliably trigger event boundaries: spatial or location changes, character entrances or exits, new object interactions, goal shifts, changes in causal structure, and temporal discontinuities (Speer, Zacks, and Reynolds, 2007). In practical terms, the most reliable triggers for workplace training are changes in what you’re trying to achieve (the goal), changes in where you are or what you’re looking at (the environment), and changes in why the current action matters (the causal structure).

The most direct way to apply EST is to structure process training and standard operating procedures around the natural event structure of the task. Rather than organising steps by convenience or by how they appear in a system, map them to the hierarchical structure of the activity: major phases first (the coarse events), then detailed steps within each phase (the fine events).

—Tom McDowall

Job search and LinkedIn tips

“Steal My Wins” | Kimberly Scott

Kim Scott has been sharing lots of details on her job search and the strategies that are working for her. As a consultant, I’ve been out of the job market for a long time, so it’s helpful to have folks like Kim that I can point others to who are looking for work in this lousy job market.

How to fix your LinkedIn feed in one hour

If you find scrolling on LinkedIn terribly annoying, you may not have trained its algorithm well. Follow these tips to improve the quality of your LinkedIn feed.

You manage your feed by giving AI the signal. Signal for what you want. Signal for what you do not want. Then you reinforce it until the algorithm adjusts to your taste. That is it. Not complicated. But most people never do it.

—Tianyu Xu

The post Local LLMs, AI Ethics: ID Links 2/17/26 appeared first on Experiencing Elearning.

Tip 1: Actual mistakes

The ideal way to create realistic wrong answers in branching scenarios is, of course, to reflect actual mistakes people make in their work. This means you have to gather information about those mistakes and points of confusion during your analysis, before you start writing. Ask SMEs, stakeholders, and learners questions about what goes wrong and why it happens. You can use my list of questions for SMEs as part of your analysis to collect that information.

Tip 2: Partially correct

Another way to create more realistic wrong answers is to provide options that are partially correct. For example, if you’re writing a scenario on communication skills where the best option is to ask an open-ended question, a closed (yes/no) question might be partially correct. A closed question is closer to the right answer than a statement; it continues a conversation. However, you won’t get as much information from a yes/no question as you do from an open-ended question.

Tip 3: Right answer, wrong time

Especially for scenarios training on processes with multiple steps, a “right answer, wrong time” option can be an effective approach. For example, I developed a branching scenario for training doctors on motivational interviewing, a technique for conversations that increase motivation for long-term behavior change. In motivational interviewing, it’s important to understand the patient’s own individual values and concerns first before setting specific goals for behavior. Setting specific, small goals is a “right answer” in that process—but if you jump ahead to setting a goal without taking time to understand first, it’s less likely to stick.

Tip 4: Tradeoffs, not mistakes

This won’t work for every branching scenario, but sometimes decisions are really more about tradeoffs than about something truly right or wrong. In project management, for example, you have tradeoffs of time, cost, and quality. A branching scenario on project management can show those tradeoffs and the consequences. In some scenarios, your focus can be on showing the consequences of prioritizing one factor or another. Even in a scenario that mostly has an “ideal path” of best answers, you might have a decision point or two that focus more on tradeoffs and values.

Tip 5: Good, better, best

I often use “Good, OK, Bad” as my default for scenario choices. I know what my “Good” option is based on the behavior I’m training for and what the organization wants to see. If we’re training people to avoid mistakes, then the “OK” and “Bad” options are the realistic wrong answers that reflect those mistakes. However, that can lead to wrong answers that are obviously incorrect. If someone can go through the whole scenario and immediately identify the worst choice without any training or feedback, then the decisions are too easy.

Sometimes it’s better to use “Good, Better, Best” for the choices instead. Karl Kapp talks about this in his LinkedIn Learning course on branching scenarios and other places. If you’re training experienced people to improve their skills, then more nuanced choices like this are more effective. Maybe you’re training sales people who are already pretty good at their jobs how to tweak their language just a little to reflect different customer needs. In that kind of situation, people aren’t really doing anything bad or making mistakes. It’s just that they could optimize their process a bit more to increase their sales. The “Good” choice might be what they’re already doing, with the other choices reflecting two improvements.

Tip 6: Tempting mistakes

Another option to write realistic wrong answers is to rephrase them to make the mistakes more tempting. By “tempting,” I mean answers people are drawn to because they feel like something you’d really think or do in a particular situation. In my scenario the New Hire with Attitude, the first decision point is how to respond to a conflict between two employees you manage. If I wrote the first option as “Ignore the problem and hope it goes away,” then that would be far too obvious. You’d know immediately that was a wrong answer, even though we know that’s sometimes what happens in real life. So, I rewrote it, keeping in mind how someone might rationalize that action: “Give them space to resolve the conflict on their own.” Now that choice feels like a realistic wrong answer. It’s a more tempting mistake too. Sometimes, giving people space would be a better choice than intervening too soon or making people feel micromanaged. Rewriting mistakes to make them more tempting requires some empathy with your audience. What might be going on in their heads to make that choice? What story are they telling themselves when they make that mistake?

Tip 7: AI brainstorming

My final tip is to use AI to help brainstorm options for realistic wrong answers in your scenarios. If you’re stuck, any LLM (ChatGPT, Claude, etc.) can be a way to get unstuck in your writing. Even when I get good examples and details from SMEs and others during my analysis, sometimes I have trouble figuring out good alternatives. Sometimes I know the best answer, and I know one mistake, but I struggle to come up with a middle option. While I generally don’t use an LLM to write a complete branching scenario, I do find it helpful for brainstorming mistakes and wrong answers. It can also help in rewriting those alternate choices to make them more tempting.

Your tips?

Do you have any tips for creating realistic wrong answers and plausible distractors in branching scenarios that I missed here? I’d love to hear your suggestions and examples.

The post 7 Tips for Writing Realistic Wrong Answers in Branching Scenarios appeared first on Experiencing Elearning.

Drawbacks of 4 options

By default, we usually see multiple choice questions with 4 choices or options. That’s the traditional number, used to reduce the chance of getting it right just by guessing.

Sometimes I see branching scenarios where the instructional designer has created 4 choices for each decision. I suspect that’s mostly out of habit rather than really a good practice for branching scenarios.

First of all, it’s hard to write good distractors (wrong answers). The more of them you have to write, the harder it is. Providing 4 options means you have to come up with 3 choices for every decision point that are realistic, relevant, and reflect mistakes people actually make.

Second, in a branching scenario, each of those choices leads to more choices. The complexity can grow exponentially (4 choices to 16 choices to 64 choices). Even if you reuse options, let people correct mistakes, or use other techniques to manage the complexity, 4 choices at each decision point quickly become unwieldy.

2 options works sometimes

Sometimes providing 2 options works for branching. It’s much easier to manage, and the number of slides and links doesn’t get out of control so fast.

However, if every decision point can be reduced to a simple “good or bad” choice, is this really a skill that requires a branching scenario? Branching scenarios are great if the process or skill has some “gray area” where decisions might be OK but not ideal, or they might be partially correct. If the situation doesn’t have any shades of gray, maybe you should use another approach to storytelling.

Two options might work for a branching scenario if you have a very long process to show, where providing even 3 options would be unmanageable. If you have over 50 total decision points, for example, I would strongly consider reducing the number of options to 2. The classic Choose Your Own Adventure books often offer only 2 choices, partly because they are lengthy stories.

Two options might also work if you’re trying to focus on a particular mistake, and that decision really only has two paths forward. I’d rather see a scenario use 2 realistic choices than 2 realistic choices plus 1 obviously made-up, wrong option.

Two options can also work for some decision points while you also use 3 or 4 options for other decision points. There’s no absolute rule that every choice in a branching scenario has to have the same number of choices. I sometimes narrow the options to 2 near the end of a scenario because that fits the actual process better.

3 options is usually best

Most of the time, I use 3 options in my branching scenarios. I aim for one good choice, one bad, and one OK. The OK choice is often partially correct or a minor error that would be easy to recover from. You can also use three choices with more nuance: one good, one better, and one best.

I find that 3 choices is more manageable. It doesn’t expand as quickly as 4 choices, but it has enough complexity to provide a rich scenario with some shades of gray.

Research support for 3 options

At the beginning of this post, I noted how multiple choice questions often have 4 choices in an attempt to reduce guessing. However, 4 choices isn’t the best option for traditional multiple choice questions either. In fact, research by Rodriguez shows that 3 options is the best for multiple choice. Why?

But the number of answer choices is not the only thing that determines the chance of guessing correctly. Quality of answer choices makes all of the difference.

Patti Shank in How many answer choices is best for a multiple-choice question? Probably not what you think.

Instead of spending time and effort creating additional wrong answers, reducing the number of choices to 3 means you can work on making those 3 options higher quality.

In one 2011 study, researchers randomly removed wrong answers and compared questions with 3, 4, and 5 options. Their main finding was that question difficulty and reliability weren’t significantly affected by the number of items.

Considering the amount of time and energy needed for developing multiple-choice tests with more distracters, three options per item were concluded to be optimal.

—Baghaei & Amrahi (2011)

A 2025 meta-analysis by Sridharan and Sivaramakrishnan of multiple choice questions found that student scores were higher with 3-option questions and that people could complete the assessments faster, but that the reliability of the questions wasn’t significantly different. The researchers also concluded that the number of options didn’t affect the discrimination; in other words, the questions still accurately identified which students really know the answer and which don’t.

However, this research was about traditional multiple choice questions, not branching scenarios. Research findings don’t always apply consistently when you change the context, so some caution is warranted. I’m not aware of any research directly assessing the number of options in branching scenarios though, and the explanations for the effect seem to apply to branching scenarios as well. I think it’s reasonable to stretch the research to assume 4 options wouldn’t provide additional benefit for branching scenarios. Future research may clarify more nuance for the specific context of scenarios.

Research

Baghaei, P., & Amrahi, N. (2011). The effects of the number of options on the psychometric characteristics of multiple choice items. Psychological Test and Assessment Modeling, 53(2), 192-211.

Rodriguez, M. C. (2005). Three Options Are Optimal for Multiple-Choice Items: A Meta-Analysis of 80 Years of Research. Educational Measurement: Issues and Practice, 24(2), 3-13.

Sridharan, K., & Sivaramakrishnan, G. (2025). Less is more? A systematic review and network meta-analysis on MCQ option numbers. BMC medical education, 25(1), 1430. https://doi.org/10.1186/s12909-025-08026-5

Originally published 1/7/2020. Updated 1/29/2026.

The post How Many Options in Branching Scenario Decisions? appeared first on Experiencing Elearning.