The Engine of Creation: Generative AI & Multimodality
How generative models actually work — and why text, image, audio, and video are the same trick.
Next action
Start Lesson 02 — 15–20 min
Opens in a new tab. First time? We'll ask for your name and email.
What this is
About this micro-course
A 15–20 minute lesson that opens the hood on how generative models work — from the prediction engine that drives every output to the multimodal capabilities that let AI see, hear, and write. Stop treating outputs as magic. Start steering them.
- 5 chapters
- Worked examples across text, image, and audio
- Hallucination awareness checklist
- The no-code revolution explained
What you'll learn
Generative AI looks like magic. It isn't. This lesson shows you how the prediction engine works, why vague prompts produce generic results, how multimodality changes what you can ask AI to do, and why the skill that now separates strong performers isn't coding — it's communication.
Curriculum
5 chapters · 15–20 min
The paradigm shift
From AI as archivist to AI as creator, and why that changes everything.
The prediction engine
How LLMs generate output and why context is everything.
Hallucination, by design
Why models confidently make things up, and what to do about it.
Multimodality
Text, image, audio, and video as inputs and outputs in the same workflow.
The no-code revolution
Natural language as the new programming language, and what that means for your role.
Practice assignment
Apply the hallucination check
Pick one task from your real work and run it through a generative AI tool. Before you use the output, apply the hallucination awareness check from Chapter 3: does it pass the smell test? Can you verify the key claims? Would you stake your reputation on it? Document what you changed and why.
- Pick a real work task — a summary, a brief, a lookup, a draft.
- Run it through any generative AI tool.
- Apply the hallucination check: smell test → verify key claims → reputation test.
- Write a 3-line debrief: what you caught, what you changed, and whether you'd trust this tool for this task again.
How the practice assignments work
- 1. Finish the lessonEach lesson ends with a short prompt that turns the concept into a one-page deliverable you'd actually use at work.
- 2. Build your artefactUse the copy-paste template inside the course. Most assignments take 15–30 minutes and produce a doc, prompt, or checklist you keep.
- 3. Self-review with the rubricEvery assignment ships with a 4-point rubric (clarity · specificity · safety · usefulness). Score yourself in two minutes.
- 4. Optional: share what you builtBring your artefact to a live session — Office Hours or the weekly build-along — for real-time feedback from our team. Prefer to share publicly? Post it and tag us on LinkedIn (Fear of Becoming Obsolete.).
Assignments are ungraded and self-paced. There's no deadline, no quiz, no certificate gate — the deliverable is the proof you did the work.
Preview · try before you launch
Try this before you launch
“Ask your chatbot the same factual question three times in fresh threads. Note what changes between answers. That variation is the engine — and the reason hallucination is a feature of the design, not a bug.”
What you walk away with
- A clear mental model of how the prediction engine works
- A practical hallucination awareness check you can apply to any output
- An understanding of multimodality and when it actually changes your workflow
Ready when you are
Start Lesson 02 · 15–20 min