How I made my AI agents learn from every approve, edit and reject

Description and use

<p>I run a one-person education business in Korea, and AI agents (Claude Code, Codex) write most of my first drafts: posts, replies to comments, product pages.</p> <p>For a while they kept making the same mistakes. One agent turns notes I send it on Telegram into social posts, and it kept adding lines like "when I tried this with my clients..." when nothing in my notes said that. Reads great, totally made up. I'd fix it, and the next session would do it again, because my corrections lived in a chat the next session never saw.</p> <p>The fix turned out to be boring: a feedback table, a split be

Problem

<p>I run a one-person education business in Korea, and AI agents (Claude Code, Codex) write most of my first drafts: posts, replies to comments, product pages.</p> <p>For a while they kept making the same mistakes. One agent turns notes I send it on Telegram into social posts, and it kept adding lines like "when I tried this with my clients..." when nothing in my notes said that. Reads great, totally made up. I'd fix it, and the next session would do it again, because my corrections lived in a chat the next session never saw.</p> <p>The fix turned out to be boring: a feedback table, a split be

Outcome

<p>I run a one-person education business in Korea, and AI agents (Claude Code, Codex) write most of my first drafts: posts, replies to comments, product pages.</p> <p>For a while they kept making the same mistakes. One agent turns notes I send it on Telegram into social posts, and it kept adding lines like "when I tried this with my clients..." when nothing in my notes said that. Reads great, totally made up. I'd fix it, and the next session would do it again, because my corrections lived in a chat the next session never saw.</p> <p>The fix turned out to be boring: a feedback table, a split be

Evidence

How I made my AI agents learn from every approve, edit and reject

Source