Agentic engineering: speed is cheap, correctness is not
Agentic tools make code cheap. The competitive advantage shifts to constraints, evaluation, and end-to-end autonomy across the value stream.
Engineering Log
Build Notes
Point-in-time thoughts on building code intelligence infrastructure.
Product Systems Engineer (AI-first, Systems-thinking, Serverless)
Product-minded generalist engineer. Uses AI tools with healthy distrust and strong verification discipline. Pragmatic, systems-first, and comfortable on the bleeding edge.
Score an agent’s tool-use trajectory, not the last message
Tool-use agents fail in the loop, not the last message. Trajectory-based evals (with mocked tools + deterministic constraints) catch orchestration errors that output-only scoring misses.
Fast code, blind merges, expensive incidents.
AI coding tools accelerate generation but not understanding. The quality gap shows up at three points: developer time, merge time, and issue time. You need system intelligence at all three.