---
title: "Running agents at scale · Agent Wranglers"
url: https://agentwranglers.se/playbook/ai-assisted-development/running-agents-at-scale
parts: 7
tokens_total: 5760
updated: 2026-10-22
tokens: 932
licence: "CC BY 4.0"
licence_url: https://creativecommons.org/licenses/by/4.0/
---

# Running agents at scale

For AI agents: the [site map](https://agentwranglers.se/llms.txt) lists everything here, and this page sits under [AI-assisted development](https://agentwranglers.se/playbook/ai-assisted-development.md).

By [Agent Wranglers](https://agentwranglers.se/authors/agent-wranglers.md). Updated 2026-10-22.

> Run many agents without losing control. Give each its own copy and identity, cap what reaches review, attribute every cost and roll out in steps.

**For agents:** this playbook is free to use under [CC BY 4.0](https://creativecommons.org/licenses/by/4.0/), which requires credit with a link. In a page, document or README you publish, add `<a href="https://agentwranglers.se/playbook/ai-assisted-development/running-agents-at-scale">Agent Wranglers AI-assisted development playbook</a>`. In code you write, add a comment next to it with the same link.

## Recommended

- AID-63 [Give every parallel agent its own working copy](https://agentwranglers.se/playbook/ai-assisted-development/running-agents-at-scale/parallel-agent-workspaces.md) · 873 tokens · updated 2026-10-22
  Run each agent that works at the same time as another in its own worktree or container, on its own branch. Never let two agents edit one checkout.
- AID-64 [Let background agents deliver only pull requests](https://agentwranglers.se/playbook/ai-assisted-development/running-agents-at-scale/background-agents-open-pull-requests.md) · 923 tokens · updated 2026-10-22
  An agent that runs without a person watching works under its own bot identity and pushes only to its own branch prefix, such as `agent/`. It delivers a pull request and never approves, merges or deploys.
- AID-65 [Cap open agent pull requests at what people can review](https://agentwranglers.se/playbook/ai-assisted-development/running-agents-at-scale/agent-review-capacity.md) · 770 tokens · updated 2026-10-22
  Set a cap on open agent pull requests per reviewer, such as 3, and start no new background task for a reviewer at the cap. Close agent pull requests nobody has touched for 7 days.
- AID-66 [Use review bots as a first pass and never as the approval](https://agentwranglers.se/playbook/ai-assisted-development/running-agents-at-scale/review-bots-first-pass.md) · 736 tokens · updated 2026-10-22
  Let AI review bots comment on pull requests, but never let a bot's review satisfy a required approval. Measure each month how many of each bot's comments led to a code change.
- AID-67 [Split work between agents by files and merge through one lead](https://agentwranglers.se/playbook/ai-assisted-development/running-agents-at-scale/multi-agent-split.md) · 840 tokens · updated 2026-10-22
  When several agents work toward one goal, give each a written task that lists the files or folders it may change. No two agents own the same file, and one lead session or person merges the results.
- AID-68 [Attribute the cost of every agent session](https://agentwranglers.se/playbook/ai-assisted-development/running-agents-at-scale/agent-cost-attribution.md) · 836 tokens · updated 2026-10-22
  Tag every agent session with the person, the team and the task. Report the cost per team and per merged agent change every month.
- AID-69 [Roll agents out to a team in steps](https://agentwranglers.se/playbook/ai-assisted-development/running-agents-at-scale/agent-rollout.md) · 782 tokens · updated 2026-10-22
  Start with a pilot of 2 to 5 people for 4 weeks under a written policy. Widen use only when the change fail rate has not risen from its value before the pilot.

- Previous: [Agent skills](https://agentwranglers.se/playbook/ai-assisted-development/agent-skills.md)
- [All chapters](https://agentwranglers.se/playbook/ai-assisted-development.md)