30 Days of a Local AI Agent on My Own Machine: What Actually Broke
Описание и применение
Автоматизация задач локальным ИИ‑агентом столкнулась с проблемами среды, а не модели. Решение включало idempotent‑шаги, логирование и ручной контроль критических действий.
Задача
An AI agent failed to reliably automate tasks on a local machine due to environmental issues rather than model limitations.
Результат
Reliability improved by focusing on environmental stability, idempotency, logging, and human approval gates rather than model upgrades.
Рабочий процесс
- Run agent locally
- Agent drives screen, shell, browser, and Android via ADB
- Agent performs 400 tasks
- Identify failures: stale UI, leaks, prompts, partial writes
- Add idempotent, logged steps
- Add human approval gate for irreversible actions
- Resume tasks instead of restarting
Доказательства
Every serious failure I hit was environmental: a stale browser session, a lock file from a crashed run, a port already in use, a half-typed shell command left by the previous task.
The single biggest improvement was not a better model. It was making every step idempotent and logged, so a task could be resumed instead of restarted.
- Дата записи: 2026-10-20T21:41:06.945Z