Skills-based matching, built for real complexity.
Eight tightly-integrated capabilities that work together as one model.
A knowledge graph mapping skills, occupations, and the bridges between them.
Astris HR maintains a curated graph of skills with bidirectional transferable links. When a candidate is missing a required skill, we look at the skills they do have and check the graph for equivalents. Partial credit is granted, with the bridge logged on the match.
Foreign occupations and credentials are preserved in their source language. The graph maps them into US-anchored equivalents without erasing them.
The great candidate a keyword search would skip.
Someone who led a farm team for seven years — managing people and supplies — could be a great Warehouse Lead. A keyword search skips them, because their résumé uses different words than the job post does.
Astris connects the dots for you: growing crops is a lot like managing stock, driving a tractor is a lot like driving a forklift, and leading a team is leading a team.
The employer sees exactly why, in plain words — 'Crop cultivation → Inventory handling' — so every match is easy to check and trust.
The next roles each candidate could grow into.
For each person, Astris suggests 3–5 next roles their current skills already point toward — and estimates how many months of training it would take to qualify for each one.
Every pathway lists exactly which skills and certifications to add. For workforce development teams, that's a ready-made plan for an upskilling program.
Seven independent dimensions, one composite score, full transparency.
Every match weighs seven independent dimensions: skills, experience, language, distance, schedule, certifications, and transportation. Each one is scored on its own, explainably, then combined into a single composite score.
On top of that, the model keeps learning from real outcomes — so matches get sharper as more placements come in, including specialization by industry.
Every match shows the breakdown, the gaps, the transferable bridges, and a plain-language rationale.
- Skills
- Experience
- Language
- Distance
- Schedule
- Certifications
- Transportation
Probability of 30, 90, 180, and 365-day retention — with the why.
Astris HR doesn't stop at placement. Each match comes with a retention forecast — the probability the candidate is still employed at each milestone. We surface the factors driving the forecast: transportation match, childcare match, schedule match, employer training, employer track record.
The forecast sharpens as real outcomes come in, and the improvement is automatic — you never wait on it.
The forecast feeds back into matching. Candidates with the same skill profile get different recommendations based on which employer has actually retained people like them.
Speak the candidate's language. Always.
We meet candidates in their own language — from resume parsing to follow-up messages, validation emails, and match notifications.
35+ resume languages, a UI in 8 languages, and native-language messaging at every step.
See the languages we supportThe candidate approves their profile before anyone sees it.
After Astris parses a resume, the candidate gets an email in their native language with a link. They review the parsed profile — skills, languages, work history, education — and either approve or reject with a reason.
Only approved candidates enter matching. Rejections come with a reason that gets routed to the caseworker for correction.
This solves three problems: misparses, misrepresentations, and the bias that comes from employers seeing AI-generated profiles the candidate never agreed to.
The model learns from every rated parse, every employer match feedback, every retention milestone.
The model gets better every time someone corrects it. Caseworkers, candidates, and employers can rate what Astris produces, and a low rating with a suggestion feeds a better result next time.
Translations improve the same way — a thumbs down leads to a better translation. Employer ratings on each match, and real retention outcomes at 30, 90, 180, and 365 days, all feed back in to sharpen future recommendations.
- Parse correctionsA reviewer flags a mistake→Better parsing next time
- Translation feedbackA thumbs down on a translation→A better translation
- Match ratingsEmployers rate each match→Sharper future matches
- Retention outcomesWho's still employed later→Smarter recommendations