AI Concepts in Pictures
The big ideas of AI, one picture at a time, in plain English.
One map of AI with six layers, then a lesson for each: how models read and are made, prompting versus RAG versus fine-tuning, retrieval, context engineering, tools and MCP, agents, vision and voice, open and local models, and keeping AI honest. A diagram in every lesson.
11 lessons · about 3.2 hours
Certificate of completion
Earn your AI Concepts in Pictures certificate
Verified edition
Mark every lesson in this course complete. You have finished 0 of 11. 11 to go.
See a sample certificate. Anyone can check a certificate with its code at /verify. It records course completion. It is not an exam or an accredited qualification.
A single map that shows where every AI idea fits, and how to use it to find what to fix.
How a language model reads and writes, step by step, with no maths.
The stages of training, and the tricks that make models smaller and cheaper.
A simple ladder from cheap fixes to costly ones, and how to match the fix to the problem.
How AI looks things up in your documents before it answers.
Choose what the model sees, keep it tidy, and keep long jobs on track.
How AI connects to other systems and to other agents, and how to stay safe.
Workflow or agent, the agent loop, and AI that clicks and types.
How models see, hear, speak and make images and video, and the risks.
Where models run, what each choice costs, and how to choose.
Hallucinations, tests, limits, red teaming and review, and the whole map once more.