Turn 10,994 Notes Into Memory - Paul Iusztin, Decoding AI & Louis-François Bouchard, Towards AI
Source
AI Engineer
Author
AI Engineer
Date
Terms in this piece · Glossary
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
RAG — Retrieval-augmented generation — fetching relevant documents first and pasting them into the model's context so it answers from your data instead of memory.
Why it matters
It shows how to turn a large personal knowledge base into live, maintainable context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → for coding agents using a plain-file memory layer rather than a vector or graph database, with concrete guidance on when to reach for Codex/Claude Code vs. NotebookLM vs. RAGRetrieval-augmented generation — fetching relevant documents first and pasting them into the model's context so it answers from your data instead of memory.Full definition →.
Key quotes
“Turning thousands of notes, videos, documents, and repositories into usable AI context requires more than a bigger context window.”
“It requires memory and context engineering: organizing sources, indexing what matters, and loading only what the model needs.”
“Build a token-efficient memory layer from plain files, not a vector or graph DB”
videoWhy AI Agents Need Million-Token Context — Thomas Wolf & Olive Song, MiniMax
videoYour company brain will leak secrets: how we stopped it for big banks — Tanmai Gopal, PromptQL
videoTethered: Our Agents Are Us — Shu Fang, Two Sigma
videoAgents' next frontier: agent-to-agent and network effects — Jean-Denis Greze, Town
