James Washington
writing about archive utils free game ideas replays
Note

Loop engineering (Addy Osmani clipping)

A saved article about making AI agents prompt themselves in loops instead of a human prompting them each turn.

built Jun 2026 A second brain the AI can read

how it works

Clipped X/Twitter long-post: five building blocks (timers, sub-agents, self-feeding queues) above the agent harness. Informs James's Mission Control / director fleet design.

Note: A page from the personal wiki.

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

agentsclippingloopsobsidian

related

  • Clippings: AI/agents/engineering reading list (cluster) Note Articles James saved about AI agents, homelabs, HTML tools, and working life.
  • 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.
  • Twice-daily automated life/work digest archive Technique Every morning and evening an AI writes James a summary of where his day went: what got built, what was tracked, what slipped.
  • How James works with AI (preferences) Document A short guide to how James likes AI assistants to talk to and work with him.
  • agent-digest and digest (Telegram/Obsidian briefings) Automation Twice-a-day and every-four-hours summaries of what my AI agents and my computer screen did, sent to my phone.
← everything I've built
© 2026 James Washington
github twitter rss