Agentic Workflow Design: Building Thinking Machines
How to structure AI agents to think, act, collaborate, and improve systematically. Seven principles for production-grade agentic systems.
Read more →THOUGHTS · ARCHITECTURE · HEALTHCARE · AI
Writing about what I build.
Microservices, .NET, observability, spec-driven development, and the craft of building systems that last.
LATEST
ARCHIVE
Microsoft APM: Package Management for AI Agents
npm for agents. How a single manifest file is solving agent portability across GitHub Copilot, Claude Code, Cursor, and beyond.
Grill-with-Docs: Making Planning and Documentation Inseparable
Why relentless interrogation during design sessions should produce ADRs and glossaries as a byproduct, not separate work.
Microservices Observability: Three Levels of Insight
Logs, metrics, and traces. Why you need all three, and how to pick the right tools for healthcare systems at scale.
Spec-Driven Development
How executable specifications turn requirements into living documentation and regression protection.