# Tune the dependency-update bot

An update bot opening more pull requests than anybody merges, grouped and scheduled so its queue is workable.

Category: Pipeline speed and cost
Source: https://letsship.ai/use-cases/tune-the-dependency-update-bot
Published: 2026-08-25

## Goal

Configure the dependency-update bot so its output is a queue the team actually works.

## Acceptance criteria

- Related updates are grouped into single pull requests
- A schedule replaces continuous opening
- Auto-merge is enabled only for changes the pipeline fully verifies
- Open pull request count is recorded before and after

## What lands as proof

The open pull request count before and after, which is the measure of whether the queue became workable.

## Prompt

Copy this to an agent to open the ticket:

```text
Create a Linear issue in my team and assign it to the SHIP agent.

Title: Tune the dependency-update bot configuration

Description: Configure the dependency-update bot so its output is a queue the team actually works.

Acceptance criteria:
- Related updates are grouped into single pull requests
- A schedule replaces continuous opening
- Auto-merge is enabled only for changes the pipeline fully verifies
- Open pull request count is recorded before and after

Before you create the issue, count this repository's open bot pull requests and how many were merged last month.
```

## Questions

### What does the agent actually change?

The ticket is scoped to one outcome: configure the dependency-update bot so its output is a queue the team actually works. Work that serves that outcome is in scope, and anything outside it is left for a separate ticket, so the pull request stays reviewable.

### How do I know the work is done?

The pull request carries the evidence, not only the diff. Here that means configuration change plus the resulting queue size, measured, so a reviewer can confirm the result without reproducing the work locally.

### How much oversight does this need?

The run stops once the plan is written. Somebody reads the approach and approves it before any code exists, which is the cheapest moment to redirect the work.
