I Built an AI That Rewrites Its Own Prompts — Its Safety Gate Rejected Every Single Edit

AgentSelfEdit is an open-source sidecar that rewrites its own system prompt from execution feedback. It A/B tests edits and promotes only statistically-proven winners. Code: github.com/deghosal-2026/agent-self-edit

15 iterations. 4,150 LLM calls. Zero promotions. The gate said no — 15 times in a row.

And it was right every time.

I spent a full session building and testing this system. I thought I'd get a promotion — an edit that the gate approves, the prompt improves, accuracy goes up. Instead, I got the most honest result possible: the gate rejected everything, and the rejections were correct.

Here's what happened, how I found a two-line bug that was letting noise through as "improvement," and why a gate that never promotes is the most valuable thing I built.

I Built an AI That Rewrites Its Own Prompts — Its Safety Gate Rejected Every Single Edit

Related reading

My Self-Improving Agent Still Couldn't Improve. That Was the Breakthrough.

I Thought This Was a Classification Problem. It Wasn't.

I Thought the Optimizer Was the Product. I Was Wrong. The Gate Was.

I Thought Role Separation Would Fix the Optimizer. It Didn't.

I Compared a Local 4B, a Better Cloud Model, and Role Separation. The Results…

The Edit That Fixed 4 Tasks and Broke 1