Insights
Written by the engineers who shipped the systems. No vendor pitches.
ARCHITECTURE · 12 MIN · MAY 2026
Why recall-tuning your retriever is the wrong default, and how to instrument for it. With code.
EVALUATION · 9 MIN · APRIL 2026
How to bootstrap an evaluation discipline before you've shipped your first feature.
AGENTS · 14 MIN · MARCH 2026
Runaway tool-use, context collapse, prompt-injection, hallucinated tool-arguments. What an enterprise agent must defend.
GOVERNANCE · 11 MIN · MARCH 2026
The minimum viable controls — and what to defer until you have a use-case actually running.
MLOPS · 10 MIN · FEB 2026
A pragmatic versioning + rollout model that gives you the regression-gate discipline you already have for code.
CASE NOTES · 16 MIN · FEB 2026
An evaluated, before/after writeup of a Cohere reranker added to a production KYC retrieval system.
ARCHITECTURE · 13 MIN · JAN 2026
An honest comparison: pgvector, Qdrant, Pinecone — and when each one actually pays off.
AGENTS · 8 MIN · JAN 2026
A flowchart that has saved more than one client a six-figure mistake. With caveats.
EVALUATION · 15 MIN · DEC 2025
Calibration data from 11 production deployments. Where LLM-judge is reliable, where it fails open.
Subscribe for engineering-only content from the teams that ship enterprise AI.