Writing
Long-form notes on AI systems, engineering leadership, design systems, and building in public — written the way I think aloud, not the way a press release sounds.
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.
The Case for Sharp Design Systems in 2026
REDLINE is my design system — precise, confident, and built for clarity. Here's why sharp geometry and disciplined red feel more honest than another round of soft corners.
Building Production-Grade AI Agents at Enterprise Scale
Lessons from deploying multi-agent systems integrated with real-time claims, membership, and payment pipelines while maintaining strict healthcare compliance.
Why Go Remains the Best Language for LLM Orchestration
Concurrency, compile-time safety, and deployment simplicity make Go the ideal backend for production LLM workloads.
Engineering Leadership in the Age of Generative AI
How to lead engineering teams through the biggest platform shift since cloud computing — without losing what made your team effective.