Harnessing AI Agents P2: I stopped guessing what my AI agent should know
TL;DR: Your codebase already contains a feature list, scattered across routes, services, schema, tests, and issues. I'll show you how to extract those into a structured JSON inventory that anchors your AI agent and makes every task scoped and verifiable. All demonstrated on a real Cloudflare Workers project.
30 分钟
Harnessing AI Agents P1: My AI agent kept "finishing" features that didn't work
TL;DR: AI coding agents are great at small tasks but fall apart on anything that spans multiple sessions. I built a 4-pattern framework (feature list, progress tracking, environment init, verification loop) to fix that, based on Anthropic's harness design guide. This is the overview; each pattern gets its own deep dive.
8 分钟
