AI Recruitment Agent
Screens against the role, not against a résumé aesthetic
- 4output fields
- A structured result, not a paragraph you have to re-read
- ≤7steps per run
- Bounded work: at most 6 tool calls, enforced by the runtime
Read-only by design. This agent has no path to sending, spending, publishing or committing anything. Where that limit is the product, removing it would remove the reason to trust the output.
Overview
Turns a role brief into a job description, then screens applications against criteria you define — each assessment tied to evidence in the application.
It is instructed to evaluate only job-related criteria and to refuse inference about protected characteristics. Screening output is a recommendation for a human decision, never an automated rejection.
Benefits
Per application
Consistent screening
Every application assessed the same way.
Auditable reasoning
Assessments can be reviewed and challenged.
Refuses the inference that gets you sued
It is instructed to assess against the criteria you set and to decline any reasoning about protected characteristics, and it says when it has declined.
What it does
Job description writing
Clear, requirement-led descriptions.
Criteria-based screening
Assesses only the criteria you define.
Evidence-linked assessments
Every judgement cites the application text behind it.
Human decision required
Produces a recommendation, never a rejection.
What this changes
What this changes about your week
- It takes over
- Running a role end to end: sourcing, screening, scheduling and keeping candidates warm.
- Done today by
- A hiring manager doing it alongside their real job.
- How often
- Every open role.
- Typical manual effort
- A single role consumes days of a manager's month.
Why People and hiring in particular. Roles stay open because nobody has time to run them, and an open role costs more every week than the work of filling it.
Runs unattended
Started by you or by an event, and it finishes on its own. Nothing waits for someone to be at a desk.
The same standard every time
The two-hundredth item is held to the bar the first one was. Consistency is the part people cannot sustain.
It cannot act on its own
AI Recruitment Agent has no path to sending, spending or committing. That limit is why its output is safe to act on.
How it runs
This agent runs server-side through the PROMIVO runtime. Each run is logged step by step and every tool call is permission-checked before it executes.
- 1InputValidated against the agent input schema
- 2Modelclaude-sonnet-5 with automatic fallback
- 3Toolsextract_structured_data, summarize_text
- 4PermissionsRuns READ actions automatically; anything higher waits for approval
- 5OutputStructured result matching the output schema
- 6LoggingTokens, duration and every step recorded
Demo
Demo dataIllustrative sample output.
Input
{
"role": "Senior backend engineer",
"criteria": [
"5+ years production Go or TypeScript",
"Distributed systems experience"
],
"application": "…"
}Output
{
"cautions": [
"Distributed systems experience is asserted but not evidenced"
],
"assessments": [
{
"met": "likely",
"evidence": "6 years listed at two employers",
"criterion": "5+ years production Go or TypeScript"
}
],
"recommendation": "advance"
}Requirements
Integrations
No integrations required.
Before you start
- A role brief and explicit screening criteria
- Requires the Starter plan or higher
Use cases
High-volume roles
Screen a large applicant pool consistently.
Role definition
Turn a vague brief into a real description.
Pricing
Starter
Billed monthly through your PROMIVO subscription. Cancel at any time.
Runs consume your plan allowance for agent executions and tokens. See plan limits
FAQ
Does it make hiring decisions?
No. It produces evidence-linked assessments for a human recruiter. It is instructed to refuse inference about protected characteristics.
Can I attach the CV instead of pasting it?
Yes. A PDF or DOCX application is read on upload and its text goes into the input; the file itself is discarded when the run ends and is never stored.
Who pays for the AI usage?
You do, on your own key. It runs once per application, so cost tracks applicant volume — worth knowing before pointing it at a role with a thousand applicants.
Reviews
Reviews open once customers have run this agent.
Need this agent to work differently?
Tell us what to change and our team will scope a customised version for your business.
Customize this agent