Structured Screening Interview Agent
Runs a consistent structured screen in text or voice with an identical question set per requisition, records consent and AI disclosure first, scores answers against rubric anchors with quoted evidence, and offers an accommodations and human-escalation path.
How it works
Ask it like
Model & guardrails
- Runs on MYAM shared · open large (Qwen 72B) by default — you can point it at your own model.
- Autonomy: Drafts and acts on request, human approves before anything leaves. Nothing leaves without a human’s approval.
- Data: Restricted — tightest controls. Provenance is attached to every output.
Outcome
Fills in as real usage proves it — from a Target we set, to Eval-measured (passes our test suite), to Platform-measured (across ≥20 accounts), to Verified (customer outcomes).
Also tracked: Scorecard evidence coverage 100% · Consent + disclosure recorded 100%
Works well with
Resume Screening & Ranking Agent
For recruiters
Screens and ranks candidates against a job description with per-criterion sub-scores, each justified by a verbatim resume quote, deterministic score aggregation, tailored screening questions, and an adverse-impact report. Never auto-rejects.
Moves: Screening time per candidate
Candidate Outreach Agent
For recruiters
Drafts honest, personalised candidate outreach grounded in public professional evidence, manages follow-ups, and schedules interviews. Makes no claims about the role absent from the JD; honours opt-out immediately.
Moves: Candidate response rate
Candidate Scorecard Aggregator
For recruiters
Aggregates all stage scorecards with human-set visible weights, computes the ranking deterministically, surfaces divergence between stages and interviewers, and produces a full evidence pack plus an adverse-impact report. Advisory only.
Moves: Decision auditability