What can an AI agent do with Bitbucket?

A Bitbucket AI agent can list and inspect repositories, review open pull requests, check pipeline status, browse commit history, open new PRs, and add inline comments - all automatically on a schedule or on demand. Write actions like creating pull requests or posting comments require your approval.

Can my AI agent review code in pull requests?

Yes. Your agent can read the full diff of any pull request and post structured review comments based on instructions you define - checking for style, missing tests, or common patterns. You approve the comments before they're posted.

Does it work with Bitbucket Pipelines?

Yes. Your agent can fetch the latest pipeline run status for any branch or commit, making it easy to monitor CI/CD health and alert you or your team when a build fails.

Is my source code stored or used for training?

No. Code and commit data is only processed during task execution and is never stored permanently or used for model training. Only task outputs such as summaries and reports are saved to your run history.

Developer tools

Bitbucket, run by an agent.

An AI agent that reviews, tracks, and manages your Bitbucket repositories.

Connect Bitbucket Book a demo

What it does without asking

11 tools

get current user
get file from repository
get pull request
get pull request diff
get pull request diffstat
get snippet
list branches
list issues
list pull requests
list repositories in workspace
list repository paths

These run without asking so your agent can gather what it needs. Anything that changes Bitbucket goes through approval: your agent shows you the plan first, and you can approve a recurring task once so it runs unattended after that.

A real run

An example of how a run works, including the approval step. Not a Bitbucket run.

Google Ads

Paid search

Working

review last week's google ads and cut wasted spend.

Queried Google Ads · last 7 days · 4 campaigns

Analyzed search terms · 312 terms · 18 with zero conversions

Drafted changes · 12 negative keywords · 2 budget shifts

Found $1,840/mo going to search terms that never convert. I'd add 12 negatives and move that budget to your two best campaigns. This changes the account, so it's your call before I touch anything.

Plan approval

Add 12 negative keywords stops $1,840/mo on terms with 0 conversions · reversible
Shift budget move the freed spend to your 2 best campaigns · roas 4.2×

Waiting for your approval. Nothing runs until a human decides.

example

Connecting Bitbucket

About 10 minutes

Auth: OAuth, managed
Setup: About 10 minutes

Example tasks

Real work people hand to an agent that uses Bitbucket.

review all open pull requests each morning and post a summary to Slack with who's blocking who
monitor pipeline failures on the main branch and alert the team in real time
generate a weekly commit activity report per team member across all repositories
automatically add a review comment checklist to newly opened pull requests