James Washington
writing about archive utils free game ideas replays
Technique

Autonomous agents get one narrow lane that ships

Unattended AIs work best with one small job they can finish without asking, not broad advisory reports.

Running a team of AI agents

how it works

Scope scheduled agents to a single lane with explicit ship authority; pairs with per-role eval rubrics.

Technique: A pattern or hard-won lesson, written down so it isn't learned twice.

The code for this one lives in a private repo. This page explains the idea so you can build your own.

agentsautonomytechnique

related

  • Agent git fleet: worktrees, sweeper, ship Automation Gives every AI session its own copy of the code, then automatically opens reviews for finished work and cleans up.
  • Loop engineering (Addy Osmani clipping) Note A saved article about making AI agents prompt themselves in loops instead of a human prompting them each turn.
  • Git discipline for agent fleets AI skill Rules that stop many AI assistants working in the same code from trampling each other's changes.
  • agent-merge: Jev-gated self-merge for agent branches Automation The one sanctioned way an AI may merge its own work: a script that reviews it first and refuses if it didn't show its work.
  • Agent Scratchpad: a moderated GET-addressable commons for sandboxed LLM agents Note An idea for a public message board that locked-down AI agents could use to coordinate, built so the humans can always watch.
← everything I've built
© 2026 James Washington
github twitter rss