[ Topic ]
Designing, building and orchestrating autonomous LLM agents.
How to give AI coding agents the right context in a monorepo — scoping tasks to packages, sharing type contracts between sessions, and preventing cross-package regressions.
How to identify independent workstreams, fan them out to multiple AI agent sessions simultaneously, and merge results without conflicts.
How to split a complex feature into agent-sized sub-tasks that execute reliably — with concrete patterns and scope rules that prevent drift and rework.
Practical techniques for recognizing when an AI coding agent has gone off track and redirecting it effectively — before it digs you deeper into the wrong solution.
How to extend your AI coding assistant with Model Context Protocol servers — connecting it to your database, APIs, and custom tools in about ten minutes.
A from-scratch walkthrough of the agent loop — tools, reasoning, and termination — using the Claude API and plain TypeScript. No frameworks.