Choose a vector database on renewal risk, not recall
Why ANN recall stopped being the differentiator, and how to evaluate a vector store on exit cost, filter portability and re-embedding cost instead — with the test to run first.
→ read_post() $ git log --oneline posts/ --skip=16
Field notes.
Long-ish posts about work we shipped — the decisions, the bugs, the numbers. No think-pieces, no listicles.
Read everything, write through a gate: permissions for operational agents
Why we give operational agents broad autonomous read access and force every write through a pull request, what that costs during an incident and where we carve exceptions.
→ read_post()Document AI: when a sub-1B specialist beats a frontier model
Cost per page, p99 latency, deployability and fine-tunability decide document pipelines — and on those metrics a 0.9B specialist usually wins, until your document distribution has a tail.
→ read_post()Browser agents: the honest ceiling on unattended web automation
Published web-agent benchmarks put state-changing task success below 50 percent. The compounding arithmetic behind that ceiling, and how we design around it.
→ read_post()MCP in Production: Building Agentic AI Systems That Actually Ship
A practical guide to deploying Model Context Protocol agents in production — from tool registration and multi-agent orchestration to observability and the mistakes we made along the way.
→ read_post()Streaming-First Data Architecture: Why We Replaced Batch ETL with CDC + Iceberg
How we migrated a Fortune 500 company from 24-hour batch ETL to a streaming-first lakehouse with Debezium CDC, Apache Flink, and Apache Iceberg — and what broke along the way.
→ read_post()How We Built a Production Hallucination Detection Pipeline
An end-to-end walkthrough of the multi-agent LangGraph system we built to verify 30K+ content pieces daily at 92% factuality accuracy.
→ read_post()Graph Neural Networks for Real-Time Fraud Detection at Scale
Why rule-based fraud systems miss coordinated attacks, how we built a GNN-powered detection engine processing 2.3M transactions daily at sub-800ms latency, and the tradeoffs we navigated.
→ read_post()