Agents · Screen

Screening Agent — one bar, applied to everyone, with evidence.

AI AgentReplaces spreadsheet scorecards and gut calls

The Screening Agent writes a scoring blueprint from your job description — no canned rubric — then scores every applicant across technical, core, behavioural and evidence pillars and sorts them into advance, review and reject at thresholds you set per job. It calibrates those thresholds against who you actually hired, and reports disparate impact both for its own raw calls and after your team’s overrides, so you can prove the bar was fair.

Inside the screen desk

What the Screening Agent actually runs.

  1. 01Scoring blueprint
  2. 02Résumé scoring
  3. 03Composite
  4. 04Thresholds
  5. 05Calibration
  6. 06Fairness
01Scoring blueprint
02Résumé scoring
03Composite
04Thresholds
05Calibration
06Fairness
See it in action

The full evaluation report — exactly what your team reviews.

company-evaluation / Maya Patel — Senior Backend Engineer
EVALUATION REPORT
Maya Patel — Senior Backend Engineer

Strong senior backend candidate. Deep distributed-systems judgment, clean problem decomposition, and clear communication. Has shipped payments infrastructure end to end.

91/100
Strong hire
CONFIDENCE
High
HIRE PROBABILITY
90%
RISK
Low
SCORE BREAKDOWN
Resume
87/100
JD-fit · strong
AI interview
92/100
Strong hire
Screening test
84/100
Passed
Tech interview
88/100
Hire
Notetaker
86/100
Recommended
CORE SIGNALS
Technical executionStrong
Problem solvingStrong
CommunicationStrong
Role fit / readinessReady
HIRING GATES
Screening fundamentalsPASS
Technical executionPASS
Integrity & consistencyPASS
POSITIVE SIGNALS
+Designed a rate-limited fanout unprompted
+Caught the idempotency bug in the live round
+Top 2% of 47 applicants on your rubric
WATCH AREAS
Limited multi-region production experience
Light on formal design-doc practice
SCORE SUMMARY
DimensionScoreWeightImpactAssessmentRating
Distributed systems Tier A9216%decisiveExceedsEXCELLENT
System design Tier A9014%decisiveExceedsEXCELLENT
Coding & implementation Tier A8813%decisiveMeetsGOOD
Communication Tier B9010%contributingExceedsEXCELLENT
Ownership & judgment Tier B869%contributingMeetsGOOD
RECOMMENDED NEXT ACTION
Advance to the onsite panel — probe multi-region trade-offs and design-doc rigor.

The rubric comes from your role.

It reads the whole job description and generates the scoring dimensions and their weights for that specific role, rather than forcing every job through one fixed template. Résumé, interview and assessment signals then roll into a single composite with a verdict and a confidence level.

It tunes itself to your bar.

It compares the scores of people you actually hired against people you rejected and proposes new thresholds when the gap is real. You approve the change — it never silently moves the bar.

Fairness you can hand to legal.

It reports advance, review and reject rates by group with a disparate-impact ratio, shown both for the agent’s raw calls and after your team’s overrides, and exports every decision as a CSV for audit.

What you get
Scoring blueprint generated from your JD
Composite across four weighted pillars
Advance / review / reject, per-job thresholds
Thresholds calibrated from your own hires
Disparate-impact reporting, agent vs human
One-click audit export of every decision
How it works

Set it once. It runs itself.

01

It reads the role

And writes the scoring dimensions and weights.

02

Everyone is scored

Same bar, same evidence format, every candidate.

03

Sorted, with proof

Advance, review or reject — and why, in writing.

Works with
The other agents
See how the six work together →

See Screening Agent in your workspace.

    AI Screening Agent — Resume Scoring & Fairness