Notes on building AI systems that ship.
Agentic architecture, RAG, eval-driven development, and what actually breaks in production — written from inside the build, not after a demo.
What Actually Breaks When You Put LangGraph Agents in Production
Reducer bugs, state bloat, and the deep-merge fix that took a full day to trace — lessons from running multi-agent workflows on AWS Bedrock at scale.
Chunking Strategy Matters More Than Your Embedding Model
Why fixed-size chunking quietly tanks retrieval quality, and what content-hash dedup buys you at scale.
LLM-as-a-Judge: Building Quality Gates Into CI/CD
How an eval pipeline caught stale-context regressions before they reached production, and what it cost to build.
Bedrock + AppSync: A GraphQL Front Door for Agentic Workflows
Decoupling frontend from backend on multi-step AI processes without losing type safety or introducing polling.
Claude Code as a Force Multiplier, Not a Replacement
What actually changes on a team's velocity and review process once AI-assisted engineering is the default, not the exception.
From Front-End to Principal AI Engineer: What Actually Transferred
A decade of component-driven thinking turned out to be surprisingly good prep for orchestrating agents.
Multi-Tenant Vector Isolation: Namespaces Aren't Enough
Why structural IAM scoping matters more than an application-layer tenant filter when the stakes are a data leak.