IDEAS, DECISIONS & LESSONS

Journal

Notes on AI, architecture and building useful products.

11 articles

17 Feb 2026 · 7 min read

Testing AI Agents Is Nothing Like Testing Regular Code

How to test LLM outputs, validate RAG retrieval quality, and verify vector search accuracy using DeepEval, Ragas, and Testcontainers. Part 2 of the AI-powered quality engineering series.

15 Jun 2025 · 4 min read

Our First RAG System Was Terrible (Here's What We Fixed)

We built a RAG knowledge base. The first version gave wrong answers half the time. Six months of iteration later, it actually works. Here's every lesson.