AI products that work with GitLab
If your code, merge requests and pipelines live in GitLab, these editions do their work right there. The AI Code Review Agent for GitLab comments on merge requests. The AI QA Agent for GitLab runs structured test plans and reports defects with evidence. The AI DevOps Agent for GitLab watches pipelines, diagnoses failures and proposes fixes.
- Data exchanged
- projects, merge requests and pipelines
- Access you provide
- GitLab project or group access token
- Added to the core price
- $500 for the GitLab edition of a product
- Not included
- GitLab license or subscription costs, and any customization beyond the field mapping agreed during setup.
| Product | What it does in GitLab | Price | Add to cart |
|---|---|---|---|
| AI Code Review Agent for GitLab | Reviews pull requests for bugs, security issues and standards and comments inline, connected natively to GitLab so it reads and updates projects, merge requests and pipelines. | Price range: $4,400 through $5,950 | Add to cart |
| AI DevOps Agent for GitLab | Watches pipelines and alerts, diagnoses failures and proposes fixes, connected natively to GitLab so it reads and updates projects, merge requests and pipelines. | Price range: $5,400 through $7,000 | Add to cart |
| AI QA Agent for GitLab | Runs structured test plans against your application and reports defects with evidence, connected natively to GitLab so it reads and updates projects, merge requests and pipelines. | Price range: $4,400 through $5,950 | Add to cart |
How do these agents work with GitLab?
All three connect natively to GitLab and read and update projects, merge requests and pipelines. That means review comments appear where your engineers already discuss changes, test findings arrive with the evidence attached, and pipeline problems come with a diagnosis and a proposed fix instead of a wall of logs.
- Inline review for bugs, security issues and standards
- Structured test plans with defects reported with evidence
- Pipeline failures diagnosed with proposed fixes
- Projects, merge requests and pipelines read and updated
Which GitLab agent should you start with?
Start with the bottleneck. If merge requests wait days for review, the AI Code Review Agent for GitLab gives every change a first pass on bugs, security issues and standards. If bugs keep slipping through to production, the AI QA Agent for GitLab runs structured test plans against your application.
If your team loses mornings to red pipelines, the AI DevOps Agent for GitLab is the natural first pick. It watches pipelines and alerts, diagnoses failures and proposes fixes, so engineers can get back to building instead of digging through job logs.
Questions buyers ask
Do the GitLab agents merge code?
No. The code review agent comments inline, the QA agent reports defects with evidence, and the DevOps agent proposes fixes. Decisions about what gets merged or deployed stay with your engineers. The agents do the reading and first-pass analysis so the people approving changes have better information in front of them.
Are these agents also available for GitHub or Bitbucket?
Yes. The code review and DevOps agents also come in GitHub and Bitbucket editions, and the QA agent has a GitHub edition. If your repositories are split across platforms, pick the edition for the platform where most of your work happens, or order a separate edition for each one.
Where does each agent's setup live?
In your own accounts. Each GitLab edition is set up within your GitLab and related tooling, then handed over to your team. Your source code stays in the systems you already secure, and the written Scope Card sets out what was built, so your security team can review it before launch.
How the connection is set up
The general pattern we follow for every integration.
- 1You create the necessary access in your GitLab account: a private app, an API key, or an OAuth approval, depending on what GitLab supports.
- 2We agree a secure way to share access during intake. Please never send passwords or API keys by email.
- 3We agree the field mapping with you and test it on sample records before anything goes live.
- 4You can revoke access from GitLab or the portal at any time.
Frequently asked questions
Which GitLab plan do I need?
It depends on the product. Each product page lists the GitLab features it relies on; plan upgrades are not included.
Will it change my existing data?
Only the fields in the mapping agreed with you, and that mapping is tested on sample records before anything goes live.
Can I use a different platform instead?
Many products also have editions for other platforms. See the full integrations list for what is currently published.