Crustdata Recruiter - Claude Skills to turn Claude into a 100x Recruiter

A set of recruiting skills that runs inside Claude on live data from 1B+ profiles from Crustdata. It learns your judgement with every search, ranks candidates the way you would, explains every candidate it picks, and drafts outreach into your ATS.

Add a comment

Replies

Best
Hey Product Hunt 👋 We built a suite of recruiting skills so you can build your recruiting twin on Claude. These run inside Claude on Crustdata's live people data, and learn your judgement until searches come back the way you would have run them yourself. The problem with every sourcing tool we've used is that the candidate ranking is the same for everyone. Your competitors type the same role into the same box and see the same list. Whatever judgement the tool applies, everyone gets an identical copy of it. Claude running on our data eliminates that. The candidates you see are ranked by how you weigh a role, and nobody else sees your list. We think taste is the hardest skill to build and the most defensible one a recruiter has now that everyone has AI. Renting a sourcing tool's ranking means renting judgement you can't inspect or change. Own that layer and you can build a clone that sources the way you do. You tell it what factors matter for each kind of role, weigh them, and correct it in plain words. "Never anyone from big aerospace." "A 3-month internship doesn't count as PCB experience." Every ruling gets saved and applied to the next search. There is no text box for that in a sourcing tool. The workflow ends with Claude pushing customized outreach for each candidate into your ATS as drafts. You review and you hit send. Who it's for: 1. Recruiting agencies that want to take on more clients without hiring more recruiters 2. In-house talent teams sourcing hard technical roles (robotics, AI, defense) 3. Executive search, where the pool is small and your judgement is vital The skills it runs on: 1. Sourcing: ranked candidates with a reason for every pick 2. Market Mapping: the companies and teams worth searching, before you search 3. Contact Enrichment: personal emails and phone numbers on every finalist 4. Outreach + ATS Push: personalized drafts, staggered sends, you hit go The data it runs on: 1. Full career history on 1B+ people and 60M+ companies 2. 15+ sources: Full career histories, research papers, patents, developer profiles, social posts etc 3. Data refreshed on a real-time basis so there's never inaccurate profile about a candidate What The Firm, a two person recruiting agency, got out of it: 1. A full day of sourcing done in 2.5 hours 2. 700 profiles down to 50 worth calling 3. Roles closed 2x faster, 4x candidate response rates 4. Took on more clients without hiring a third recruiter That's the outcome we care about. More revenue without more headcount, and candidates other tools never surface. Happy to answer anything below. If you want to watch your own recruiting twin get built, book a demo at crustdata.com/demo.

 Hey; this sounds powerful. Curious: how do you surface and explain the specific judgement signals your Claude-skill used for each ranking? Also, how easy is it to transfer or share a recruiter’s “taste” between teammates or clients without leaking that person’s private rules?

Whats the data source for candidates? outdated profiles have always felt like a flaw in the industry you just live with. how do you guys keep it fresh?

 We get data from across the web for candidates. Any place where folks list their work history, their work, research papers - we get it from there. And we keep pulling this data from the web in real-time, hence the candidate data is always accurate.

Maker

   Adding to what Nithish said, we also detect any change events (job switches, promotions, title changes) in real-time, so you can search but also filter by candidates who just joined or just left a company for example.

This is impressive! Curious, how quickly does the model adapt when a recruiter's judgement shifts for a new role with different requirements than previous searches?

Best of luck with the launch excited to see how this reshapes sourcing workflows!

 Hey Muhammad, from our experience it does a pretty good job of adapting to different roles with different requirements, but the quality of it lies in the feedback the recruiter provides to the models. The better the feedback, the quicker and the better results they get!

Maker

  Hey Muhammad, adding to Nithish's point, it will keep getting better with every new search you make, since Claude keeps the context from your previous searches saved in the skill.

The memory part is great. feels like the real difference between this and other saas tools.

 Exactly Himanshu. Recruiters can literally clone their judgement with our skills in Claude. That's something that can't do with other saas tools right now.

honestly this looks really useful, one thing i'd love is a way to test the api in a sandbox with fake data before committing. like a playground where you can see what job change or promotion alerts actually look like in the response. would save a lot of trial and error

 That's a great idea Ferdi, thank you! Will pass this on to the team!

Maker

 Hey Ferdi, this is now possible! You can get an API key with free credits and test out the entire workflow without having to commit to anything!

This looks like a great tool - congratulations on the launch. 1 billion profiles is pretty impressive! My question is primarily about the way the data is harnessed and the sustainability of that model. Put simply, if you are pulling candidate data from a job board then you are potentially skipping the need for a recruiter to have a licence for that job board? In which case, there is a future risk to the job board's sustainability commercially. And then, of course, you lose that data source. Is that something you've got covered? If so, how do you compensate your data sources?

Maker

  Hey Martin, thanks for the thoughtful question! Our candidate data comes from the open web, places where people publicly list their own work history, projects, research and so on.

💎 Pixel perfection

We've been using Crustdata for quite a while now, and honestly they've been one of the best vendors we've worked with.

Really like this direction too. I think the interesting part isn't just searching 1B+ profiles—it's that the system learns how you evaluate candidates over time instead of making you start from scratch on every search. The explainability is also a nice touch. As AI gets more involved in recruiting, understanding why a candidate was recommended becomes just as important as the recommendation itself.

Also just wanted to give a shoutout to the team. Every time we've had questions, missing data, or feature requests, they've been incredibly responsive and thoughtful. Great product, even better people.

Congrats on the launch! 🚀

Maker

 Thanks so much, Carin - we're so glad to hear this incredible feedback! 🙏

What tools can i connect it to? if i wanted to hook up my email and slack, is that possible?

 You can connect it to any tool that can connect with Claude. Email and Slack are possible and some of our users connect it so Claude can derive insights from their conversations there

How long before it actually starts thinking like me? like how many rounds of feedback until it's calibrated?

Maker

  Hey Suyash, there's no fixed number! It gets better with every search since Claude keeps the context. The better the feedback you give it, the faster it calibrates!

How is the coverage outside the US? most of our hiring is eastern europe and some LATAM and this is where every sourcing tool we've tried is falling short

Maker

   Great question! Eastern Europe and LATAM are both well covered (part of the 1b+ profiles we currently have)

Give it a shot and let us know how it holds up against what you've tried before!

1234
Next