Journal
A compact reading surface for technical notes, architecture decisions, and observations from shipping real systems.
How shifting from "being right" to "helping others improve" transformed my code reviews, accelerated team shipping, and fundamentally changed my leadership approach.
Real-world prompt injection detection and mitigation for production AI systems. Trade-offs between sandboxing, filtering, and risk acceptance with concrete RAG and multi-turn examples.
Close the gap between offline benchmarks and production reality. Concrete patterns for designing evals that catch hallucinations, detect drift, and drive business decisions.
How a team's Docker builds hit 45+ minutes and registry storage exploded—and the diagnostic tools and layer-caching strategies that fixed it.
A practical framework for evaluating LLM providers and models based on token economics, latency percentiles, and cascading system design constraints—not vendor hype.
Why unsexy choices in logging, error handling, and observability silently shape user experience and team velocity—lessons from the trenches.
