◈Talent Intelligence

Live

StoryHire

Skills-first talent intelligence

Recruiting reimagined around candidate potential. StoryHire uses deep AI understanding of career trajectories and skill adjacencies to find the right people — not just the right keywords.

Request a demo How it works

OUTCOMES IN PRODUCTION

68%

Reduction in time-to-shortlist

3.2×

More diverse candidate pools

91%

Recruiter satisfaction score

< 2s

Per-candidate scoring latency

"StoryHire found candidates our previous ATS would have filtered out in the first pass. The skills inference is genuinely impressive — it surfaces potential, not just keyword matches."

— Head of Talent Acquisition, Series B fintech, 400 employees

How it works

From resume to shortlist in five steps

StoryHire orchestrates a sequence of specialised agents — each one handling a single concern, with results flowing into the next step.

01

◈

Resume & Profile Ingestion

Upload resumes in any format — PDF, DOCX, plain text, or LinkedIn exports. The Talent Intelligence Pack parses raw documents into structured candidate profiles with 200+ extracted attributes.

Supports bulk ingestion via S3 / GCS bucket sync, webhook push, or direct API upload. Deduplication across profiles is automatic.

02

⬡

Skills Inference & Competency Mapping

Beyond keyword extraction — the agent infers latent skills from job history, tenure patterns, and project context. Skills are mapped to a normalised taxonomy with confidence scores.

Handles ambiguous titles ('Growth Lead' → inferred skills: go-to-market, analytics, experimentation). Adjacent skill inference surfaces hidden talent.

03

◎

Role Fit Scoring

Each candidate is scored against an open role using multi-dimensional fit: skill match, experience trajectory, domain alignment, and cultural signal detection from writing style.

Scores are explainable — recruiters see exactly which signals drove the rating. Bias guardrails run on every scoring event.

04

◇

Career Coaching Workflow

Candidates receive personalised coaching: skill gap analysis, recommended learning paths, and career trajectory projections — generated by the same agent that scored them.

Coaching output is scoped to what the employer has enabled. Guardrails prevent advice that conflicts with employer policy or applicable regulation.

05

◬

Recruiter Copilot

Recruiters interact with candidates via an AI copilot that has full context: scores, skill maps, interview notes, and conversation history — across every session.

Copilot suggestions are guardrail-wrapped: PII redacted from shareable outputs, bias filters on shortlist recommendations, full audit trail.

API Walkthrough

One call. Full intelligence.

Score a candidate against a role with a single API call. Guardrails run automatically — bias detection, PII redaction, audit logging.

request.sh

curl -X POST https://api.liyaengine.com/v1/run \
  -H "x-api-key: $LIYA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "pack": "talent-intelligence",
    "intent": "score-candidate",
    "input": {
      "resume_text": "Sarah Chen — 6 years building data pipelines...",
      "role": {
        "title": "Senior Data Engineer",
        "requirements": ["Python", "Spark", "dbt", "SQL", "cloud infra"],
        "level": "senior"
      }
    },
    "guardrails": {
      "bias": { "policy": "eeoc-compliant", "action": "flag" },
      "pii": { "action": "redact", "fields": ["name", "email", "address"] }
    }
  }'

response.json

{
  "response": {
    "candidate_id": "cand_8f3a2b",
    "fit_score": 0.87,
    "skill_match": {
      "matched": ["Python", "Spark", "SQL", "GCP"],
      "inferred": ["dbt", "pipeline orchestration"],
      "gap": ["Kafka"]
    },
    "trajectory": "strong upward — 3 promotions in 6 years",
    "coaching_insight": "Kafka gap closeable in ~6 weeks; strong RAG signal",
    "guardrails": {
      "bias_flags": [],
      "pii_redacted": ["name", "email"],
      "audit_id": "aud_7c2d9f"
    }
  },
  "execution": {
    "steps": 4,
    "latency_ms": 1240,
    "agent_mode": "agentic"
  }
}

Under the hood

Liya Engine components powering StoryHire

Intelligence Layer

Talent Intelligence Pack

Agent Mode

Multi-step agentic pipeline

Memory

Cross-session candidate context

Retrieval

Role requirements + skills taxonomy RAG

Guardrails

EEOC bias detection, PII redaction

Audit

Full scoring audit trail, GDPR-compliant

Ready to find better candidates?

StoryHire is live and accepting design partners. Request a demo to see the scoring engine on your own job reqs.

Request a demo Read the docs