---
title: "Run a recurring agent that fixes stale documentation"
description: "Validate the docs in CI and let a scheduled agent open fix-up pull requests."
url: https://starsling.dev/ci-playbooks/techniques/doc-gardening-agent
canonicalUrl: https://starsling.dev/ci-playbooks/techniques/doc-gardening-agent
---

# Run a recurring agent that fixes stale documentation

Validate the docs in CI and let a scheduled agent open fix-up pull requests.

## How to choose an approach

This technique currently has one documented company example. Validate its prerequisites, tradeoffs and original CI environment against your repository before adapting it.

- **[OpenAI](https://starsling.dev/ci-playbooks/openai#doc-gardening-agent)**: Use it when Docs and agent instructions drift from the code, and agents act on the stale text. Check before adopting: Review the fix-up pull requests like any other change, and keep the validation jobs deterministic so the structure stays checkable.

## Apply this technique

````text
Evaluate and apply this CI technique to my repository: Run a recurring agent that fixes stale documentation.

Validate the docs in CI and let a scheduled agent open fix-up pull requests.

Read the technique and its source-backed company examples: https://starsling.dev/ci-playbooks/techniques/doc-gardening-agent.md

Inspect this repository’s CI workflows, build and test commands, dependencies, and recent run timings. Identify where this technique applies and explain the expected benefit using this repository’s evidence.
Measure a baseline from recent comparable runs: elapsed time, queue time, runner minutes and failures where available. If data is unavailable, say what cannot be measured.
Compare relevant company approaches, checking prerequisites, platform differences and tradeoffs. Rank applicable options by evidence, fit and measurable opportunity; do not present company results as predictions for this repo.
Recommend the smallest safe change, show what checks and fallback paths remain, and ASK ME WHICH CHANGE TO APPROVE BEFORE EDITING ANY FILES.
Only after approval, work on a new feature branch, make one reversible change, and open a reviewable pull request. Never merge or push to a default or protected branch.
Keep required checks, test coverage, deployment and release behavior intact. Validate the change and compare equivalent runs where possible; report limitations and what should be monitored after merge.
````

## How OpenAI used this technique

Read what OpenAI changed and follow the original sources.

### OpenAI: Run a recurring agent that fixes stale documentation

OpenAI's agent-first team keeps its knowledge base in a structured docs directory, with a short AGENTS.md as the map. Dedicated linters and CI jobs validate that the knowledge base is up to date, cross-linked and structured correctly, and a recurring doc-gardening agent scans for stale or obsolete documentation and opens fix-up pull requests.

Evidence: Company-reported result or observation

A short AGENTS.md (roughly 100 lines) is injected into context and serves primarily as a map ([Source](https://openai.com/index/harness-engineering/))

Use it when: Docs and agent instructions drift from the code, and agents act on the stale text.

Before applying it: Review the fix-up pull requests like any other change, and keep the validation jobs deterministic so the structure stays checkable.

[Read more in the OpenAI playbook](https://starsling.dev/ci-playbooks/openai#doc-gardening-agent)

[Primary source](https://openai.com/index/harness-engineering/)

## CI optimization is continuous work.

Apply this technique yourself, or use StarSling Runners for faster GitHub Actions and optional agent-driven optimization PRs, which teams on eligible paid plans can turn on.

[Get self-improving CI](https://starsling.dev/products/runners)

## Company Playbooks

### [Anthropic](https://starsling.dev/ci-playbooks/anthropic)

Run only affected tests

### [DoorDash](https://starsling.dev/ci-playbooks/doordash)

Run build and test in parallel, sharded across CI agents

### [Linear](https://starsling.dev/ci-playbooks/linear)

Benchmark the same job on faster hardware

### [Mastra](https://starsling.dev/ci-playbooks/mastra)

StarSling runners for the slowest test workflow

### [OpenAI](https://starsling.dev/ci-playbooks/openai)

Rank CI fixes by the minutes they save

### [Ramp](https://starsling.dev/ci-playbooks/ramp)

Move a CPU-bound test suite to a faster CPU

### [Shopify](https://starsling.dev/ci-playbooks/shopify)

Let an agent iterate against one CI metric

### [Spotify](https://starsling.dev/ci-playbooks/spotify)

Build arm64 on native arm64 runners

### [Stripe](https://starsling.dev/ci-playbooks/stripe)

Run only the tests a change can reach

### [Uber](https://starsling.dev/ci-playbooks/uber)

Build the merge-queue speculations most likely to be needed