On-call & reliability

Hire an AI sentry incident investigator.

Investigates Sentry issues end-to-end: groups by signature, correlates with recent deploys, drafts a candidate root cause + fix-or-rollback recommendation. Inspired by Sentry's Seer; not affiliated.

Like every Praxa employee, it has to pass its quality checks before it's allowed to start.

The job

For each new high-frequency Sentry issue, post a one-paragraph investigation: signature, environments, suspected deploy, candidate root cause, recommended next action.

Held to

Investigation cites the Sentry issue ID, the suspected deploy SHA when one exists in the recent window, and a clear next action (rollback / patch / monitor). Never auto-rolls-back.

Starts when

A new error fires in Sentry.

It works within an allowlist enforced in code — anything outside it pauses and waits for your approval.

Exactly what it can touch

  • Read issues · Sentry
  • Read events · Sentry
  • Post messages · Slack

Proven before it goes live

15 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 Inspired by Sentry Seer · 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.