RAG
7 articlesWhat agent memory research taught me about twenty years of notes
Tiered memory for a personal knowledge base: what MemGPT, Zep, and Mem0 teach about structuring two decades of notes so AI agents find the right ten files.
When AI summaries become your sources
AI-generated summaries corrupt a knowledge base when derivative text is promoted to source. Not model collapse: no weights train, but the same failure shape.
RAG Architecture Lessons from Practice
Building a retrieval-augmented generation system revealed patterns the tutorials don't cover. Contractions break search. Not everything needs an LLM. Full docum
Building ownwords: A Synthesis Coding Case Study
What separates synthesis coding from vibe coding isn''t the tools — it''s the decisions. This technical case study walks through the architectural choices,...
RAPTOR: Recursive Thinking for Smarter AI Retrieval – The Executive Code Podcast
The Executive Code podcast explores Stanford's RAPTOR paper on recursive abstractive processing for smarter AI document retrieval and understanding.
Why Vector Databases & Embeddings Used for Prompt Context are Limited for Personalized AI Assistants
Why vector databases and embeddings fall short for personalized AI assistants, and how fine-tuning large language models offers deeper contextual understanding.