This product was not featured by Product Hunt yet. It will not be visible on their landing page and won't be ranked (cannot win product of the day regardless of upvotes).
Product upvotes vs the next 3
Waiting for data. Loading
Product comments vs the next 3
Waiting for data. Loading
Product upvote speed vs the next 3
Waiting for data. Loading
Product upvotes and comments
Waiting for data. Loading
Product vs the next 3
Loading
Resurface
Score any resume against any job, with quoted evidence
An API for recruiting tools. Send a job description and a resume (PDF, DOCX, HTML or TXT); get a 0–100 score, a verdict for each screening question and the exact resume line behind it. An LLM writes the questions once; a classification model (TypeSafe Jev) answers them for every resume, 8× faster than an LLM, with every quote copied from the resume. Try it in the browser, no code. 50 free scores (100 for Hunters). Open source on GitHub.
Most companies have tens of thousands of resumes in their ATS that nobody searches again. I wanted to rescore them for every new role, fast, and without trusting summaries a model wrote.
Resurface splits the work in two: 1. An LLM reads the job description once and writes 6–8 atomic screening questions. 2. A classification model (TypeSafe Jev) answers them for every resume and selects the line that proves each answer. The evidence is a quote from the resume, never generated text.
In my benchmark against Claude Sonnet 5.5 (20 resumes × 5 questions) it was 8× faster per resume, with 99% of verdicts the same. The script is in the repo, so you can check the numbers.
• Try it without code: sign up and open "Try it" in the dashboard. Sample resumes are ready. • Hunters get 100 free scores instead of 50 this week. • API for PDF, DOCX, HTML or TXT, then packs from $10 per 100 scores. • Open source with 100 fictional resumes: github.com/dolevhayut/resurface
Next: ATS integrations (Greenhouse, Ashby, JobAdder). Which one would you connect first?
About Resurface on Product Hunt
“Score any resume against any job, with quoted evidence”
Resurface was submitted on Product Hunt and earned 11 upvotes and 1 comments, placing #40 on the daily leaderboard. An API for recruiting tools. Send a job description and a resume (PDF, DOCX, HTML or TXT); get a 0–100 score, a verdict for each screening question and the exact resume line behind it. An LLM writes the questions once; a classification model (TypeSafe Jev) answers them for every resume, 8× faster than an LLM, with every quote copied from the resume. Try it in the browser, no code. 50 free scores (100 for Hunters). Open source on GitHub.
On the analytics side, Resurface competes within Developer Tools, Artificial Intelligence and Human Resources — topics that collectively have 1M followers on Product Hunt. The dashboard above tracks how Resurface performed against the three products that launched closest to it on the same day.
Who hunted Resurface?
Resurface was hunted by Dolev Hayut. A “hunter” on Product Hunt is the community member who submits a product to the platform — uploading the images, the link, and tagging the makers behind it. Hunters typically write the first comment explaining why a product is worth attention, and their followers are notified the moment they post. Around 79% of featured launches on Product Hunt are self-hunted by their makers, but a well-known hunter still acts as a signal of quality to the rest of the community. See the full all-time top hunters leaderboard to discover who is shaping the Product Hunt ecosystem.
For a complete overview of Resurface including community comment highlights and product details, visit the product overview.
Dolev Hayut
Hi Product Hunt 👋
Most companies have tens of thousands of resumes in their ATS that nobody searches again. I wanted to rescore them for every new role, fast, and without trusting summaries a model wrote.
Resurface splits the work in two:
1. An LLM reads the job description once and writes 6–8 atomic screening questions.
2. A classification model (TypeSafe Jev) answers them for every resume and selects the line that proves each answer. The evidence is a quote from the resume, never generated text.
In my benchmark against Claude Sonnet 5.5 (20 resumes × 5 questions) it was 8× faster per resume, with 99% of verdicts the same. The script is in the repo, so you can check the numbers.
• Try it without code: sign up and open "Try it" in the dashboard. Sample resumes are ready.
• Hunters get 100 free scores instead of 50 this week.
• API for PDF, DOCX, HTML or TXT, then packs from $10 per 100 scores.
• Open source with 100 fictional resumes: github.com/dolevhayut/resurface
Next: ATS integrations (Greenhouse, Ashby, JobAdder). Which one would you connect first?