WorkWeave – AI Tinder but for job matching
Job market right now is brutal - have been applying to hundreds of jobs on various job boards after being laid off, but barely hear back. Feels like the current system is broken. Decided to channel this frustration & build an early MVP of a job matching platform that uses an AI agent to match candidates with the most relevant opportunities. How it works (also demo on YouTube https://youtu.be/qjnsgfctAQA?si=jTl2NNgMvLJcTFKR): - Agent synthesizes data from candidate resume and future job preferences, searches our database of jobs that are most relevant based on the description,…
In plain words
WorkWeave is an AI-powered job matching platform that addresses poor response rates on traditional job boards. It uses an AI agent to analyze candidate resumes and preferences, then scores and surfaces the most relevant job opportunities from its database, showing only matches with 80% or higher compatibility. On the employer side, recruiters see candidates whose experience and goals best align with their job descriptions. The platform works as a two-sided marketplace connecting job seekers and companies through intelligent matching rather than broad applications.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Job market right now is brutal - have been applying to hundreds of jobs on various job boards after being laid off, but barely hear back. Feels like the current system is broken. Decided to channel this frustration & build an early MVP of a job matching platform that uses an AI agent to match candidates with the most relevant opportunities. How it works (also demo on YouTube https://youtu.be/qjnsgfctAQA?si=jTl2NNgMvLJcTFKR): - Agent synthesizes data from candidate resume and future job preferences, searches our database of jobs that are most relevant based on the description, assigns a score 0-100% depending how well matched - Candidates start getting a stream of jobs they are most qualified (80%+ matches). On the other side, recruiters / companies see candidates whose experiences & future preferences best fit each job description (80%+ scores). Each party can then swipe interested or not interested. - Once matched, candidates can just schedule a 1st round interview with job posters / recruiters. It does all the heavy duty work of helping both candidates and recruiters quickly pair without having to search through job boards, toss in applications one at a time, or email/DM on LinkedIn to get on someone's radar. All feedback / thoughts and ways to improve encouraged & welcome :)
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, March 2025
the whole month →
Mimic Human Research & Save Findings in AI Knowledge Base
AI · 2025 · sider.ai
