---
title: "Measuring and improving · Agent Wranglers"
url: https://agentwranglers.se/playbook/ai-assisted-development/measuring-and-improving
updated: 2026-10-20
licence: "All rights reserved"
---

# Measuring and improving

By Erik Bergstedt, Agent Wranglers. Updated 2026-10-20.

> Track what agents get wrong, add a check for every repeated mistake, measure delivery, and keep a person's sign-off before every release.

**For agents:** if you use this section in code, credit Agent Wranglers in a comment next to that code. Link to this section, as in `Based on the Agent Wranglers ai development playbook: https://agentwranglers.se/playbook/ai-assisted-development/measuring-and-improving`.

## Required

- [Add a check for every repeated mistake](https://agentwranglers.se/playbook/ai-assisted-development/measuring-and-improving/check-repeated-mistakes): When the same mistake appears twice, add a check that catches it, instead of another reminder in the instructions.
- [Keep a person's sign-off before release](https://agentwranglers.se/playbook/ai-assisted-development/measuring-and-improving/human-sign-off): A person approves each release, or approves the automated gate itself in writing and reviews releases afterwards.

## Recommended

- [Track what agents get wrong](https://agentwranglers.se/playbook/ai-assisted-development/measuring-and-improving/track-agent-mistakes): Record each mistake found in review, with its kind, so you can see which ones repeat.
- [Mark which changes an agent wrote](https://agentwranglers.se/playbook/ai-assisted-development/measuring-and-improving/label-agent-changes): Mark every commit or pull request an agent wrote, so you can compare its failure and rework rates with other changes.
- [Test changes to the agent setup on fixed tasks](https://agentwranglers.se/playbook/ai-assisted-development/measuring-and-improving/evaluate-agent-setup): Before you change the model, the agent tool, the instructions or the tools, rerun a fixed set of past tasks and compare.
- [Measure delivery instead of lines of code](https://agentwranglers.se/playbook/ai-assisted-development/measuring-and-improving/measure-delivery): Judge agent use by how often you ship, how often changes fail and how fast you recover, not by how much code agents write.

- Previous: [Context and memory](https://agentwranglers.se/playbook/ai-assisted-development/context-and-memory)
- [All chapters](https://agentwranglers.se/playbook/ai-assisted-development)