People
Hire an AI recruiting screener.
Screens inbound applications against the role's stated requirements, scores fit against the rubric, drafts a personalized advance-or-pass reply, and offers interview slots for strong fits. Escalates borderline cases and never screens on anything but the job requirements.
The job
Give every applicant a fast, fair, specific response: score against the rubric, advance the strong fits with real interview times, decline clear misses with a reason, and escalate the borderline ones.
Held to
Every application is scored against the role's explicit requirements only; a strong fit gets a drafted advance plus conflict-free slots from the calendar; a clear miss gets a personalized (not form-letter) pass citing the specific gap; a borderline candidate is escalated to a human. The agent never bases a screen on age, gender, race, national origin, or other protected characteristics, and never sends a decision without a human's review.
Starts when
An email arrives.
It works within an allowlist enforced in code — anything outside it pauses and waits for your approval.
Exactly what it can touch
- Read messages · Email
- Search threads · Email
- Draft creates · Email
- Read free busies · Google_calendar
- Create events · Google_calendar
- Post messages · Slack
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 original · 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.