All posts
Case StudyFebruary 5, 2026· 5 min read

Case Study: How StoryHire Replaced Resume Screening with Deep AI

A look inside StoryHire's journey from traditional ATS matching to skills-inference AI — built entirely on the Liya Engine Talent Intelligence Pack.

P
Product
Liya Product

Traditional applicant tracking systems match candidates to jobs using keywords. If a candidate's resume doesn't contain the exact phrase from the job description, they don't match. This produces enormous false negatives — talented candidates screened out because they described their skills differently.

StoryHire set out to solve this. Their goal: replace keyword matching with deep AI understanding of candidate potential, career trajectories, and skill adjacencies.

The challenge

Building the AI layer from scratch would have taken StoryHire's small team many months. They needed resume parsing, skills inference, competency mapping, candidate-role fit scoring, and recruiter-facing explanations — all running reliably at scale.

The solution

StoryHire built their entire AI layer on Liya Engine's Talent Intelligence Pack. The pack provided all the components they needed out of the box: semantic resume analysis, skills inference from raw text, adjacency-based competency mapping, and structured output schemas that their existing product UI could consume directly.

const result = await liya.agents.run({ pack: 'talent-intelligence', workflow: 'candidate-analysis', input: { resume: candidateResumeText, jobDescription: jdText, }, }); // result.skills — inferred skills list // result.fitScore — 0–100 role fit score // result.gaps — skill gaps with context // result.coachingNotes — candidate-facing summary

Results

Within three months of launch, StoryHire customers reported a 40% reduction in time-to-screen and a 2.3x increase in qualified candidates surfaced per role. The skills-inference model identified candidates who would have been filtered by keyword matching in traditional systems.