Three different problems
Information, state and behavior each need a different mechanism.
What you’ll learn
Four ideas, one module
Semantic search
Embeddings, vector similarity and chunking, without the math.
RAG and grounding
Find the right text, then answer from it, with sources.
Memory and fine-tuning
Where state should live, and when to change the model itself.
Applied exercise
Choose the mechanism
Choose prompt, retrieval, memory, database, fine-tuning—or a combination—for five product scenarios.
- Documents and policies
- Users and live data
- Behavior and style
Cheat sheet
Before choosing a mechanism, ask: is this information, state or behavior?
One page you keep: the questions to ask on every project, the rules of thumb, and a decision guide you can use on your own product. All ten come with The Book.
Leave at the door
Five myths this module breaks
| Myth | What’s actually true |
|---|---|
| “Fine-tuning teaches it our documents.” | It shifts behavior. Retrieval supplies the facts. |
| “RAG stops hallucinations.” | Only if retrieval finds the right, current text. |
| “The vector database is the memory.” | It’s one store. Memory is what you choose to keep. |
| “Similar means relevant.” | Close in meaning can still be wrong or outdated. |
| “Big context windows kill retrieval.” | Cost, latency and access still favor selecting. |
Before you move on
Can you call this one?
A sales bot quotes old prices, forgets clients and sounds off-brand.
Split it into information, state and behavior. Which mechanism fixes each?
How we would answer
- Information old prices. Fix the source and re-index, or look prices up in the database at answer time.
- State forgets clients. Store client notes and history, and load them into context for each conversation.
- Behavior off-brand. Tighten the system prompt with examples first; fine-tune only if that fails at scale.
- The trap fine-tuning on the price list. It bakes in prices that will change again and can’t cite them.
Every module ends on a question like this. Join the waitlist →
The Memory Architect
Nika Soren
explores how AI systems retrieve, retain and adapt knowledge, and why remembering is not the same as learning.
Episode 06 · Retrieval, memory and fine-tuning
Included with the course.
Coming soon · an AI character from the show, not a real researcher.
Next · Module 07