Your RAG Architecture Is Wrong — Do This Instead
Most RAG architectures are built to answer questions from documents. But in real enterprise work, users often need artifacts: RFP responses, compliance matrices, risk registers, architecture reviews, and proposal drafts. In this video, I use an RFP response example to show why retrieval should be a lookup primitive inside a broader runtime — not the whole architecture. I also discuss the runtime/simulator approach using Pydantic Monty, a minimal secure Python interpreter written in Rust for AI-generated code: https://github.com/pydantic/monty

▶︎
Is RAG Still Needed? Choosing the Best Approach for LLMs

▶︎
Task vs ValueTask in C#

▶︎
Train Your Own Tiny LLM on Your PC In Just A Few Hours

▶︎
LangChain Full Crash Course - AI Agents in Python

▶︎
Graphify vs GitNexus vs CodeGraph — Which Code Knowledge Graph Should You Use?

▶︎
Turing Award Winner: Disagreeing with Google, Postgres, Future Problems | Mike Stonebraker

▶︎
Stop Using AI Wrong — Agentic AI vs RAG Explained

▶︎
Zig 2026: No-AI Policy, $670K Foundation, Left GitHub & Why Zig Isn’t 1.0 - Andrew Kelley Explains

▶︎
Mr.Bean Making Celebrities Cry With Laughter NONSTOP!

▶︎
Android 17 sucks. So I put Linux on a phone.

▶︎
China Is About To Pop The AI Bubble

▶︎
What does '__init__.py' do in Python?

▶︎
I'm leaving Germany | Brutally Honest Review

▶︎
Somali Pirates Made One Huge Mistake — They Boarded a Ship With Ex-U.S Marines

▶︎
Against Inhumane Methods of Code

▶︎
Typical Family Apartment Tour (How Russians REALLY Live) 🏠

▶︎
Abstract Art Slideshow for your TV | 1hr of 4K HD Paintings.

▶︎
MIT Just Revealed the AI Bubble's Fatal Flaw

▶︎
China’s Sodium Battery Breakthrough Just Made Lithium OBSOLETE

▶︎
