Skip to main content
How the AI sees a candidate

Skills extracted from what a candidate built. Not from what they wrote.

Our AI reads the project files — code, thesis, design assets, internship reports — and produces a structured skill list with evidence links. The skill graph is a function of what the student has actually produced. Auditable, explainable, AI Act-compliant.

We connect people and values.

How it works

Artifact in, structured skills out

Four stages, fully automated. The candidate uploads, the AI extracts, the platform shows evidence, the recruiter searches. No manual tagging.

01

Upload

The candidate uploads project files: source code, thesis PDF, design files, internship reports, lab notebooks. One paragraph of description in the candidate's own language.

02

Extract

The AI reads the artifacts. It parses code, summarizes documents, transcribes video walkthroughs. It produces a structured skill list across five typed buckets.

03

Evidence

Each extracted skill is stored with a confidence score and a link back to the artifact it came from. The recruiter clicks the skill, sees the actual code or document where it was demonstrated.

04

Search

Recruiters search by skill, role, location, or in natural language. Matches are ranked on the extracted evidence, not on keyword overlap with the CV.

What gets extracted

Five typed skill buckets

Skills are never a flat list. Every extraction categorizes into the same five buckets, so a recruiter searching for soft skills doesn't have to wade through SQL queries.

Hard skills

Programming languages, frameworks, databases, tools. Extracted from code repositories and technical artifacts.

Soft skills

Communication, collaboration, project management. Extracted from documentation quality, README structure, internship evaluations.

Design skills

UI/UX, mechanical CAD, architectural drawing, graphic design. Extracted from design files, sketches, prototypes.

Domain knowledge

Industry-specific competence: finance, biotech, manufacturing, education, public sector. Extracted from project context and applied work.

Languages

Working languages, certified levels, evidence in the candidate's own work. CEFR-aligned where possible.

Worked example

One README in, five typed buckets out

Real extraction logic running on a fragment of a Politecnico thesis project. Fragment on the left, what the AI returns on the right.

Input — project README excerpt
# Adaptive reuse of the ex-Falck industrial site

Master thesis · Politecnico di Milano · Architecture · 2025

Designed a mixed-use intervention on 12,000 m² of the
former Falck steelworks in Sesto San Giovanni. The plan
keeps three of the original blast-furnace structures
(listed under Italian heritage law D.Lgs. 42/2004) and
inserts new residential, retail, and public-space programs
around them.

Deliverables: 1:200 master plan, 1:50 sectional studies of
the heritage shells, full sustainability assessment under
LEED v4 BD+C, structural feasibility study with FEM
analysis on the reused frames.

Software: Revit (BIM model), AutoCAD, Grasshopper + Rhino,
Adobe InDesign for the boards. Worked with two structural
engineers on the FEM model and with the municipality's
heritage office on the listed-element constraints.

Final review: presented to the jury in English; final PDF
set in Italian for the regional planning authority.
Output — typed skill buckets
Hard skills
Revit (BIM)AutoCADGrasshopperRhinoFEM analysisAdobe InDesign
Soft skills
Cross-disciplinary collaborationHeritage-office negotiationPublic review presentationMulti-stakeholder coordination
Design skills
Master planning (urban scale)Sectional designAdaptive reuseMaterial composition
Domain knowledge
Italian heritage law (D.Lgs. 42/2004)LEED v4 BD+CIndustrial heritage / brownfield reuse
Languages
Italian (native)English (B2+, jury presentation)

Each badge is clickable in the real product — it links back to the artifact line where the evidence was found.

What we show

Every claim links back to the proof

We don't ask anyone to trust the AI on its word. Every skill on a candidate's profile is clickable. The recruiter sees the artifact the skill was extracted from.

  • Confidence score per skill — visible to recruiters and to the candidate
  • Link to the source artifact (code repository, document, file) for every extracted skill
  • Public algorithm registry explaining how the matching engine ranks candidates
What we don't claim

What the AI can't do

We're transparent about the limits because trust comes from honesty about both. Here's what artifact-based extraction is not.

  • It doesn't measure a candidate's potential — only the skills evidenced in what they've already built
  • It doesn't replace the interview — it removes the screening step that should never have been an interview
  • It doesn't certify the work was the candidate's own — that's where the optional professor endorsement adds a trust layer

Search candidates on evidence, not on claims.

Free to browse the verified pool, contact 5 candidates per month with a corporate email. Try the AI search before signing up.

    InTransparency — Verified Student Profiles | University-to-Work Platform