Integration · Build & run
App status first. Deploys by approval.
Brigham.ai reads what is running and what shipped. It deploys or rolls back only when you approve.
Read first, act second
1
Read status
Which apps are up, which are failing, and what version runs.
2
Read deploys
What shipped, when, and whether it succeeded.
3
Propose an action
A deploy or rollback is proposed with the reason.
4
You approve
Nothing deploys until a person says yes.
Scopes and access
- Connects as
- Each person, their own account
- Access
- Read-only by default
- Reads
- App status, deploy history, rollbacks available
- Writes
- Deploy and rollback (separate grant)
- Needs approval
- Every deploy and rollback
- Visibility
- Only apps the connecting person can see
- Availability
- Available
Ask it
- ›“Is anything down?”
- ›“What deployed to production today?”
- ›“Did the last deploy succeed?”
- ›“Propose a rollback of the billing app to the previous version.”
Questions, answered.
Can Brigham.ai deploy on its own?
No. Deploys and rollbacks always wait for approval.
Keep reading.
GitHubBrigham.ai reads your repositories, issues, branches and pull requests, so engineering questions get answers from the source. Read-only by default.Read →
CloudflareBrigham.ai reads your Cloudflare zones, cache behavior and edge health, so “is the site up” and “why is it slow” have real answers. Read-only.Read →
ApprovalsEvery approval is bound to the exact payload hash. Change the action and you approve again. Email links confirm on click, never on open.Read →
Action classesBrigham.ai sorts every action into read, reversible write or sensitive. Sensitive actions always wait for a person.Read →