Play 59
AI Recruiter Agent
Resume screening with bias detection and explainable hiring decisions.
AI recruitment assistant with resume screening, job-candidate matching, and interview scheduling via Microsoft Graph. Features bias detection across demographic attributes, skills assessment with configurable rubrics, and diversity analytics dashboards. All decisions include explainability reports for compliance with fair hiring regulations and internal audit requirements.
Architecture Pattern
RAG-powered matching: responsible AI bias detection, explainable scoring
Azure Services
DevKit (.github Agentic OS)
- agent.md — root orchestrator with builder→reviewer→tuner handoffs
- 3 agents — Recruiter Builder (gpt-4o), Reviewer (gpt-4o-mini), Tuner (gpt-4o-mini)
- 3 skills — deploy (234 lines), evaluate (149 lines), tune (195 lines)
- 4 prompts — /deploy, /test, /review, /evaluate with agent routing
- .vscode/mcp.json — FrootAI MCP with OpenAI + Doc Intelligence inputs + envFile
TuneKit (AI Config)
- config/openai.json — matching precision, explanation generation
- config/guardrails.json — bias detection thresholds, fairness constraints
- evaluation/eval.py — Match accuracy >80%, Bias disparity <10%
Tuning Parameters
Machine evidence
FrootAI evidence lifecycle
This is an internal evidence maturity label, not third-party certification, accreditation, legal compliance, or a production guarantee. Missing or expired evidence demotes automatically; catalog claims cannot promote a play.
This play currently has design evidence only. A runnable scenario, endpoint evaluation, and build receipts are the next contiguous gates.
Repo Intelligence
v1A no-clone, revision-pinned map for agents and humans. Observed evidence is separated from inferred flow so the output stays useful without pretending to be a full call graph.