Integration · CI/CD
GitLab + OrchestrAI
Catalog exported 2026-09-02 · GitLab website
Create, trigger, and retry GitLab CI pipelines from chat and read pipeline and job status.
OrchestrAI exposes 4 GitLab operations: 1 is low-risk (read-only or low-impact), and 3 create or modify resources and run only after you confirm the plan. 3 of them also carry a step-level approval gate.
What teams use it for
Teams on GitLab use OrchestrAI to check why a pipeline is red, list its jobs, and retry it after a flaky runner recovers. Reading status is low risk, while creating, triggering with a trigger token, and retrying a pipeline are medium risk and each waits for confirmation. There is no operation to cancel a pipeline, manage CI variables, or interact with merge requests, so those remain in the GitLab UI or API.
Every GitLab operation, with its risk level
| Operation | What it does | Risk | Step-level approval |
|---|---|---|---|
Get GitLab Pipeline Status |
Get GitLab CI pipeline status and jobs | Low risk | No |
Create GitLab Pipeline |
Create GitLab CI pipeline | Creates resources | Yes |
Retry GitLab Pipeline |
Retry failed GitLab CI pipeline | Creates resources | Yes |
Trigger GitLab Pipeline |
Trigger GitLab CI pipeline with trigger token | Creates resources | Yes |
Risk tiers come from the catalog: low is read-only or low-impact, medium creates resources and is reversible, high modifies existing resources, destructive may lose data. Every plan that creates or changes resources is shown with its cost estimate and waits for your confirmation. Operations marked with a step-level approval pause again on their own step. Destructive operations require a typed risk phrase.
What you connect
A GitLab credential (stored as gitlab).
Connected-service tokens are envelope-encrypted with a per-record key wrapped by a cloud KMS.
Prompts that work
- What is the status of the latest pipeline on main in group/backend, and which jobs failed?
- Retry the failed pipeline 48812 in the mobile-app project
- Create a new pipeline on the release/2.4 branch of the storefront project
Before anything runs
Every mutation shows its plan, cost estimate, and blast radius, then waits for your confirmation. Destructive operations require a typed risk phrase. Credentials are minted per run through OIDC federation and discarded afterward; nothing you create here is invisible later, because every resource lands in the desired-state ledger where drift is detected and can be converged. Details on the security page.
Frequently asked questions
- Can OrchestrAI cancel a running GitLab pipeline?
- No. GitLab coverage is limited to creating, triggering, retrying, and reading pipelines. Cancellation is not available yet.
- Does OrchestrAI retry GitLab pipelines automatically?
- No. Retrying is a medium-risk confirmed operation, so it only runs after you approve the specific pipeline it is about to retry.
- How does OrchestrAI authenticate to GitLab?
- You add a GitLab credential once in the connections screen. It is envelope-encrypted with a per-record key wrapped by a cloud KMS and is only decrypted inside the run that needs it.
Related integrations
Try it on your own account
Connect your cloud read-only and see your resources, drift, and costs before anything runs. $5 minimum to start. Unused credits refunded in your first 14 days.
Unused credits refunded in your first 14 days.