Lesson 08
Tools
It never gets smarter. It just gets handed better text.
Every time you hear “the AI searched the web,” this is what actually happened. The model writes out a request as ordinary text. Normal software spots that text, does the real work, and pastes the result back in front of the model. That is all a tool is.
1Pick a job it can’t do on its own
Do thisPress Next step four times. The same four beats every time: you ask → the model writes a request → other software runs it → the model reads the result and answers.
2Step through the loop
3Everything the model can see right now
Part two
Two ways to get a fact into an AI: bake it in, or hand it over
Training (lesson 12) melts facts into the model’s settings. Powerful, slow, expensive, and frozen solid the moment it finishes. Retrieval is the document lookup you just stepped through: the app finds the right paragraph and pastes it in front of the model. It changes nothing about the model and everything about what the model can see. People call that second one RAG. The difference shows up the second a fact changes, so change one.
4Change the rule and watch which one keeps up
5Baked in by training
you: What's our refund window?
6Handed over by retrieval (RAG)
you: What's our refund window?
| Training | Retrieval (RAG) | |
|---|---|---|
| To change it | Retrain the model: big computers, weeks, a lot of money | Save the new document. Done in seconds |
| How fresh it is | Frozen on the day training stopped (lesson 07) | As fresh as the documents you keep |
| Can it show you the source? | No. The fact is smeared across a trillion settings | Yes. The paragraph is sitting right there in front of it |
| Best used for | Skills: language, reasoning, general knowledge | Your facts: rules, prices, documents, anything that changes |
| How it goes wrong | Confidently out of date, or invented (lesson 05) | It grabs the wrong document, and the model reads it anyway |