---
title: "Comment by Mateo Ruiz on \"When your coding agent repeats a mistake, move the lesson out of chat.\" | Hashnode"
description: "I like the distinction between fixing the current task and improving the system that produces future tasks. That's a pattern that applies well beyond coding age"
url: "https://hashnode.com/posts/when-your-coding-agent-repeats-a-mistake-move-the-lesson-out-of-chat/6a70d2a0f40be8a79446c4e7/comment/6a71b6eb398282c2e2421fd5"
---

[Discussion](https://hashnode.com/posts/when-your-coding-agent-repeats-a-mistake-move-the-lesson-out-of-chat/6a70d2a0f40be8a79446c4e7)

Comment [When your coding agent repeats a mistake, move the lesson out of chat.](https://hashnode.com/posts/when-your-coding-agent-repeats-a-mistake-move-the-lesson-out-of-chat/6a70d2a0f40be8a79446c4e7)

[Mateo Ruiz](https://hashnode.com/@mateoruiz)

[Aug 4](https://hashnode.com/posts/when-your-coding-agent-repeats-a-mistake-move-the-lesson-out-of-chat/6a70d2a0f40be8a79446c4e7/comment/6a71b6eb398282c2e2421fd5)

I like the distinction between fixing the current task and improving the system that produces future tasks. That's a pattern that applies well beyond coding agents. Too many teams keep adding instructions to prompts when the real fix belongs in the harness, a reusable skill, a deterministic check, or a regression test. Treating repeated failures as signals to improve the surrounding system not just the model's immediate output is what makes agent workflows scale instead of accumulating more prompt debt over time.

[Bryce Darling](https://hashnode.com/@mindrealm)

[Aug 4](https://hashnode.com/posts/when-your-coding-agent-repeats-a-mistake-move-the-lesson-out-of-chat/6a70d2a0f40be8a79446c4e7/comment/6a71b6eb398282c2e2421fd5#reply-6a720f850f8f3a18f2ffa94a)

Prompt debt is a good name for it. What have you found works for you in your setup?
