Engineering Notes
I write about AI engineering, software systems, and what actually survives production.
These posts are written to make the portfolio discoverable through serious technical writing, not just through a landing page. I focus on agent systems, MCP, observability, and software architecture that teams can really use.
AI Engineering In 2026: The Stack I Trust For Production Systems
A detailed look at the AI engineering stack I believe matters most right now: agent workflows, MCP, Spring AI, LangGraph, observability, and evaluation-first delivery.
Why MCP And Event-Driven Architecture Fit Together Better Than Most Teams Realize
A detailed breakdown of why Model Context Protocol, event-driven design, and bounded agent workflows are starting to form a strong production pattern for AI products.
Observability, Evals, And Latency Budgets: What Makes AI Systems Production-Ready
A detailed guide to the pieces most teams skip in AI delivery: tracing, evaluations, latency budgeting, and the engineering discipline needed to keep non-deterministic systems reliable.