The Minimal Agent Workbench
The smallest useful workbench is three files: a root instructions router, a state file, and a task board. Everything else is layered on top. If a repo cannot carry these three, no model will save it. Define the three files that form the minimum viable workbench. Explain why a short root router beats a long monolithic AGENTS.md. Build a state file the agent can read at every turn and write at the end. Build a task board that survives multi-session work without chat history. Most teams reach for a workbench by writing a 3000-line AGENTS.md and calling it done. The model loads it, ignores the parts it cannot summarize, and still fails on the same surfaces it always failed on. You need the opposite. A tiny root file that routes the agent into deeper files only when relevant. Durable state the agent reads before acting and writes after. A task board that says what is in flight, what is blocked, and what is up next. Three files. Each one with a job. Each one machine-readable enough to evolve into a real system later. A good AGENTS.md is short. It points the agent at: The state file (where you are). The task board (what is left). The deeper rules (under docs/agent-rules.md). The verification command (how to know it works). Anything longer…
The Minimal Agent Workbench: The smallest useful workbench is three files: a root instructions router, a state file, and a task board. Everything else is…
This free lesson is part of the AI Engineering from Scratch curriculum. Read the full explanation, run the lesson code, and verify the result in the interactive reader or from the repository source.
Browse the complete course catalog or open this lesson on GitHub.