Writing
Long-form notes on developer experience, AI systems, engineering leadership, design systems, and building in public — written the way I think aloud, not the way a press release sounds.
Reliability Engineering for Generative AI Platforms
Fifteen years of distributed systems, real-time pipelines, and incident command applied to LLM platforms. How to build agentic systems that degrade gracefully, contain failures, and remain auditable when everything is on fire at 2 a.m.
Context Engineering for Production Agentic Systems
Beyond prompt engineering lies context engineering — the systematic design of memory, state, retrieval contracts, and compression layers that turn brittle LLM workflows into reliable, observable, enterprise-grade agentic platforms.
What My Side Projects Are Really About
ChillStep Radio, quantum chaos, synesthetic pianos, and a robots.txt for AI — the side projects I build when enterprise platforms go quiet and curiosity takes the wheel.
The Boring Go Layer Between Your RAG Demo and Production
RAG demos live in notebooks. Production RAG lives in ingestion pipelines — and I keep choosing Go for the unglamorous middle.
Validating Agent Outputs in Go Before They Touch Production
Structured outputs, schema validation, and the boring Go layer that keeps probabilistic agents from becoming probabilistic incidents.
Context Is the Kill Switch: Go, Cancellation, and LLM Timeouts
Why context.Context is the most underrated tool in production LLM orchestration — and what happens when you forget the kill switch.