ShortList
An AI recruiting screener that reads every application, scores candidates against the role, and hands recruiters a ranked shortlist with outreach already drafted.
// The Pipeline view for an open role: funnel tiles, match-score distribution, and an AI-ranked candidate shortlist.
Figures from the engagement, shared under NDA.
We publish them unchanged and can’t break them down any further here. The reference build you can open runs entirely on sample data.
If you read one part of this page, read these 4 lines.
- 342 applications auto-screened to a 24-person shortlist, no manual triage
- Every score is explainable — skills, experience and screening answers, not a black box
- Outreach is written from the candidate's own profile before the recruiter clicks send
- Skill bars plot the candidate against the role bar, so gaps are obvious at a glance
What it does — and which part of it we built.
ShortList turns a flood of inbound applications into a defensible, ranked shortlist in minutes.
For each open role it auto-screens every applicant against a weighted rubric, produces an explainable match score, surfaces strengths and gaps, and drafts personalised outreach — so a small talent team can move from 342 applicants to 8 interviews without reading a single résumé cold. We designed and built the front-end MVP: a "Pipeline" board for an open role and a candidate profile that shows exactly why the AI ranked someone where it did. The demo models a real "Senior Backend Engineer" search end to end, from funnel stats and score distribution down to per-skill fit and a ready-to-send intro email.
Every screen here is from the reference build, not the client’s system.
The captions say what you are looking at. Every name and record on them is sample data.
What the engagement left the client with.
- Compressed a full role's screening from days of manual review to a same-day ranked shortlist
- Gave recruiters an auditable reason for every ranking, defensible in hiring reviews
- Cut time-to-first-outreach by shipping a personalised draft with each shortlisted candidate
- Delivered a clickable, investor- and design-partner-ready MVP validating the core screen-rank-reach loop
The stack was picked per constraint, not per house habit.
8 technologies across 3 layers — the shape of the stack follows the problem.
Every feature in the build (9)
- Role pipeline with live funnel tiles: applicants, auto-screened, shortlisted, interviewing
- Explainable match score (0-100) per candidate against a weighted role rubric
- Match-score distribution chart with a visible shortlist cut line at 80
- Screening funnel from applied to interviewing with conversion rates
- Ranked candidates table with skills, experience, stage badges and one-line AI notes
- Candidate profile with a match ring, AI summary, and strengths / to-probe flags
- Per-skill fit bars showing candidate level vs the role requirement marker
- Auto-drafted, personalised outreach email with an estimated reply rate
- AI-generated screening Q&A with per-answer fit assessment
Don’t take our word for it — it is running in the frame below.
This is the same page the provenance block links to: our reference build for ShortList, with its own look, copy and motion. Scroll inside it, or open it full-screen.
// next
Building something in this space?
A 30-minute call is enough for us to understand your situation and tell you whether we're the right team. Usable version in the first two weeks if we are.