Latest
11 min read
MCP's 2026-07-28 spec broke my tool-calling setup
Model Context Protocol's 2026-07-28 spec ships a stateless core, drops Roots, Sampling, and Logging, and hardens auth to OAuth 2.0 — what to migrate first.
Writing.
Notes on AI engineering — RAG, agents, evaluation, and the production-grade infrastructure around them.
5 min read
Chunking strategies for RAG, and when each one bites you
Fixed-size, semantic, and structure-aware chunking all look fine in a demo. Here's how each one actually fails once real documents hit your production pipeline.
5 min read
Choosing a vector store in 2026
A practical comparison of pgvector, Pinecone, Qdrant, and Weaviate — real cost and latency numbers, and when pgvector is enough.
1 min read
Welcome — what I'm writing about
Notes on shipping AI systems, RAG, agents, and the boring full-stack work that makes them production-grade.
3 min read
A production RAG checklist (the boring half)
What separates a working RAG demo from a production RAG system isn't the retrieval — it's the evaluation, observability, and failure-mode handling around it.