---
title: "Give an agent the last mile: watch CI, rebase and retry flaky checks"
description: "Let an agent shepherd each change through CI to the merge."
url: https://starsling.dev/ci-playbooks/techniques/agent-shepherds-merge
canonicalUrl: https://starsling.dev/ci-playbooks/techniques/agent-shepherds-merge
---

# Give an agent the last mile: watch CI, rebase and retry flaky checks

Let an agent shepherd each change through CI to the merge.

## 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#agent-shepherds-merge)**: Use it when Landing a pull request takes repeated manual rebases, conflict fixes and reruns of the same flaky checks. Check before adopting: Bound the retries and record each flake so a retried check still leaves a trail to fix, and leave required checks and approvals in force. Adapted for GitHub Actions; compare the original system with yours.

## Apply this technique

````text
Evaluate and apply this CI technique to my repository: Give an agent the last mile: watch CI, rebase and retry flaky checks.

Let an agent shepherd each change through CI to the merge.

Read the technique and its source-backed company examples: https://starsling.dev/ci-playbooks/techniques/agent-shepherds-merge.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: Give an agent the last mile: watch CI, rebase and retry flaky checks

**Translated to GitHub Actions**

- What OpenAI built: OpenAI's Symphony gives each ticket's agent the gh CLI and skills to watch CI, rebase and retry flaky checks.
- Your GitHub Actions version: An agent that watches CI on its pull request, rebases when needed, resolves conflicts and retries flaky checks.

OpenAI's Symphony gives each ticket's agent the gh CLI and skills to read CI logs. In a large monorepo, where the last mile of landing a pull request is slow and fragile, the system watches CI, rebases when needed, resolves conflicts and retries flaky checks. By the time a ticket reaches Merging, the team has high confidence the change will land without human babysitting.

Evidence: Documented technique

Use it when: Landing a pull request takes repeated manual rebases, conflict fixes and reruns of the same flaky checks.

Before applying it: Bound the retries and record each flake so a retried check still leaves a trail to fix, and leave required checks and approvals in force.

GitHub Actions adaptation: Compare the source system with your own workflow before applying this translation.

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

[Primary source](https://openai.com/index/open-source-codex-orchestration-symphony/)

## 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