Stop fixing your AI agents in chat

Описание и применение

Переход от исправлений в чате к хранению правил в общих Markdown‑файлах обеспечивает единую точку правды, историю изменений и возможность ревью, устраняя необходимость в чат‑корректировках.

Задача

Chat corrections to AI agents are transient and unreviewable, causing repeated mistakes and lack of traceability.

Результат

Persisting rules in shared Markdown files provides a single source of truth, version history, and reviewability, eliminating the need for chat‑based corrections.

Рабочий процесс

• 1. Identify the incorrect behavior in chat.
• 2. Ask the agent which file should contain the correct rule.
• 3. Edit the identified Markdown file to add or modify the rule.
• 4. Commit the change to the repository.
• 5. Run the agent again; it reads the updated file and applies the new rule.

Доказательства

A correction in chat lives in one conversation. When that session ends, so does the rule.

Источник

Commit it like any other change. The next run, in your session or a teammate's, uses the new rule.

Источник

You get three things chat never gave you: One source. History. Review.

Источник

We keep the agents' knowledge as plain Markdown files and let the agent search them, instead of running them through an embedding index first.

Источник