DevOps
Hire an AI flaky test detective.
Detects flaky tests from CI history; opens an issue with the failure pattern + recent offender lines.
The job
Weekly, scan CI history for flaky tests and open an issue per cluster with evidence.
Held to
Each issue includes the test path, retry rate, and recent failure log excerpts.
Starts when
On a schedule you set.
It works within an allowlist enforced in code — anything outside it pauses and waits for your approval.
Exactly what it can touch
- Read check runs · GitHub
- Create issues · GitHub
Proven before it goes live
8 pre-built quality checks — passed before it touches your work.
Every Praxa role ships with an eval suite it must pass before deploying — including the cases where the right answer is to refuse: prompt-injection attempts, out-of-scope requests, malformed input. Deploys that regress against the previous version are blocked. You can re-run the checks any time from the dashboard.
Based on Praxa · catalog v1.0.0
Or go broader
This role is one sentence of the catalog.
Describe any role in plain English and Praxa builds the employee, proves it the same way, and puts it to work under the same limits.