Autonomous AI Recruitment

From CV to hire decision, fully autonomous.

TalentForge runs your entire top-of-funnel autonomously — CV screening, real-time AI interviews, and explainable evaluation. You stay in control of every final decision.

GDPR Compliant
EU AI Act Ready
SOC 2 Type II

End-to-End Pipeline

Six steps. Fully autonomous.

Human-in-the-loop checkpoints at every critical stage. AI assists, you decide.

CV Upload

Portal or API

AI Screening

RAG + Rubrics

Scheduling

Auto-negotiate

AI Interview

STAR framework

Evaluation

XAI Report

ATS Sync

Webhook push

Capabilities

Built for how hiring actually works

Not another ATS. An autonomous pipeline that does the work while keeping you in control of every decision that matters.

RAG-Powered CV Screening

AI extracts skills and scores candidates against your JD and knowledge base. Weighted criteria you control.

Real-time AI Interviews

30-min structured STAR interviews via WebRTC with live follow-ups. Avatar lip-sync. EN, JP, VI.

Explainable Evaluation (XAI)

Chain-of-thought reasoning, per-competency STAR analysis, and risk flags. Defensible decisions.

Smart Schedule Negotiation

AI proposes slots from Google Calendar. Candidates pick or counter. No email chains.

Human-in-the-Loop

Pipeline pauses at configurable checkpoints. You approve, reject, or override. AI never makes final calls.

Conversational HR Assistant

Chat with your pipeline data. Ask questions or execute actions directly via natural language.

AI Transparency

No black box. Every decision traceable.

Two AI models prevent single-model bias. Full chain-of-thought reasoning saved for every candidate.

1

Screen & Score

CVs are parsed, PII stripped. LLM scores against your JD + knowledge base using weighted criteria.

technical: 40% · experience: 30%
education: 15% · culture: 15%
2

Interview (STAR)

30-min structured behavioral interview. AI detects STAR gaps live and probes deeper. Full transcript saved.

Situation → Task → Action → Result
Gap? → Follow-up probe
3

Evaluate & Explain

Separate model evaluates against rubrics. Chain-of-thought, risk flags, recommendation with full justification.

score: 82 · recommend: HIRE
reasoning: "Strong system design..."

Security & Compliance

Security by design, not afterthought

PII never reaches AI unprotected. Tenant isolation, encryption, and regulatory compliance baked in.

PII Pseudonymization

Names and emails replaced with pseudonyms before AI processing. AES-256 encrypted storage.

Tenant Isolation (RLS)

PostgreSQL row-level security. Each tenant's queries physically cannot access another's data.

GDPR + EU AI Act

Right to erasure, consent management, XAI. HITL satisfies high-risk AI requirements.

Injection Defense

Hidden text detection, prompt injection guard. Flagged CVs route to quarantine review.

Bias Monitoring

Continuous fairness metrics. Alerts on scoring pattern drift across protected characteristics.

Full Audit Trail

Every action logged with timestamp, actor, context. Immutable records for compliance.

AWS Infrastructure

ECS Fargate in private subnets, WAF, encrypted RDS, Secrets Manager. Zero public backends.

Integrations

Fits into your existing stack

Full REST API + webhooks for custom integrations.

Google Calendar
Free/busy + auto-scheduling
SSO (OIDC)
Okta, Azure AD, Keycloak
Slack / Teams
Pipeline notifications
ATS Webhooks
Greenhouse, Workday, custom
Built with Python + FastAPI LangGraph LiveKit WebRTC PostgreSQL + pgvector AWS ECS Fargate Next.js 15

Ready to automate your
top-of-funnel?

See how TalentForge handles screening, interviewing, and evaluation for your open roles. Demo uses your actual JD.

Request a Demo

No commitment. We'll set up a live demo with your job descriptions.