Technical authorship
Technical authorship
All knowledge hub articles in Technical authorship.
Agent architecture
A curated path from Cursor setup through repo-level AGENTS.md, private knowledge bases, MCP tool design, RL-trained models, and single-agent coding loops.
- Getting started with Cursor: automate the loop Treat Cursor as an automation surface — rules, tests, MCP, and agents run the boring parts so you keep one thread for judgment. Read →
- The AGENTS.md standard for AI coding agents One open Markdown file per repo — closest AGENTS.md wins; user prompts override. Read →
- Organizing knowledge for AI agents Pair a public site with a private brain — progressive disclosure, lifespans, verification metadata. Read →
- Building MCP servers with search and execute Two MCP tools — search and execute — beat hundreds of per-operation tool definitions. Read →
- Reinforcement learning for tool calling in agent models RL specializes models for the tool loop — Composer is the public case study. Read →
- Keep the thread: why plan–critique–build pipelines fail modern coding agents One agent, one thread, small units — verify with tests, not lossy handoffs. Read →
More in this category
- Why Mirror for Unity multiplayer Mirror is a pragmatic default when Unity teams need a complete networking architecture. Read →
- Progressive disclosure for learning: maps, not memorization Orchestrate agents across a navigable map — learn foundations deeply, index everything else, verify with the environment. Read →