As I read online, I bookmark resources I find interesting and useful. I share these links about once a month here on my blog. This post includes links related to Elearning characters, generating AI images, working with AI, memory research, and some useful tools.
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.
Additional curated resources
Check out my complete library of links or my previous bookmarks posts.
Upcoming events
Stock Photos to Stunning: Generate Custom Images with AI
ATD RTA Learning Trends & Innovations SIGTuesday, March 24 at 12:00 PM ET$10 for members, $15 for guests. Register through ATD RTA.
Build Cohesive Learning Visuals with AI: Hands-On Session
Create a Portfolio That Gets You Hired
