One video, one lesson, one experiment at a time
A lesson goes with one full video. Watch it whole or one chapter at a time, read the longer explanation, run the experiment in your own AI assistant and answer 3 questions. Every fact links to its source, and every lesson shows the date it was last checked.
Path 1
How AI works
See what a chatbot does when it answers you, and why a confident answer can still be wrong.
How a language model writes an answer one piece at a time, where its knowledge came from and where it stops. Each lesson goes with one full video, and each chapter has its own short clip.
The whole path
Path 2
AI agents
Know what an agent does between your request and its answer, and what can go wrong on the way.
The loop every agent runs, the tools it calls, what it remembers and what it costs. Then a real case of agents that got out of their test environment, and what it means for anyone who runs one.
The whole path
Path 3
What AI costs
Work out what a job will cost before you run it, and why the price per token is only half the bill.
Tokens are how AI is priced. The lesson runs 3 models on the same jobs and shows where the money goes. The price table and the calculator use each maker's own published prices.
The whole path
Every lesson has the same 4 parts
Watch
The full video, and a short clip at each chapter if you only want that part.
Read
The longer explanation, with the sums worked out and a link to the source of every fact.
Try it
An experiment you run in your own AI assistant, with prompts to copy and what to look for.
Check
3 questions that put the idea in a new situation, each with the reason for its answer.
New videos land on the channel first
Videos on agents, tokens and how models work. The written lesson for each one follows here, once its facts are checked against their sources.