A People Search Engine with Face Recognition
Hey there HN! I'm Vignesh, and I'm excited to launch Introthem.com — a people search engine that uses facial recognition to provide in-depth, accurate summaries of individuals, assist with HR screening, research prospects, and analyze brands. The Problem: Researching individuals - whether for hiring or personalizing outreach - is a time-consuming challenge. While RAG-based search engines can help summarize someone's online presence, they have significant limitations. When multiple people share the same name, these engines often mix their information together, creating inaccurate profiles.…
In plain words
Introthem is a people search engine that uses facial recognition to create detailed summaries of individuals. It helps with HR screening, prospect research, and brand analysis by accurately distinguishing between people who share the same name or resemble public figures. The tool addresses the challenge of researching individuals online by organizing information correctly rather than mixing profiles together, making it useful for hiring teams and professionals conducting background research.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey there HN! I'm Vignesh, and I'm excited to launch Introthem.com — a people search engine that uses facial recognition to provide in-depth, accurate summaries of individuals, assist with HR screening, research prospects, and analyze brands. The Problem: Researching individuals - whether for hiring or personalizing outreach - is a time-consuming challenge. While RAG-based search engines can help summarize someone's online presence, they have significant limitations. When multiple people share the same name, these engines often mix their information together, creating inaccurate profiles. Even worse, if someone shares a name with a celebrity or public figure, meaningful research becomes nearly impossible as the well-known person's results overshadow everything else. The Solution: Introthem solves this using facial recognition to accurately classify and organize information by individual. Simply select the specific person you're interested in, and our engine will generate a comprehensive profile. But that's not all – remember how we typically perform multiple queries to look up someone? For example, if a person founded a company, we then look up how that company is doing. Introthem handles this in-depth research automatically. It generates additional queries based on the first summary the engine produces – what I internally call Content-aware query generation. This helps you conduct thorough research about someone just by their name. Try it now at https://introthem.com Would love to hear your feedback, HN! Demo: Link 1: https://introthem.com/search?uuid=51d6bc6a-08ad-464e-b4f1-16... Link 2: https://introthem.com/search?uuid=9f3ad850-1c72-4e8c-ad36-07... Link 3: https://introthem.com/search?uuid=3f31072e-bf74-4ff2-b1ef-ee...
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 · 26d ago · cactuscompute.com
Launched alongside, November 2024
the whole month →
- IB
I wasn't quite sure if this qualified as "Show HN" given you can't really download it and try it out. However, dang said[0]: > If it's hardware or something that's not so easy to try out over the internet, find a different way to show how it actually works—a video, for example, or a detailed post with photos. Hopefully I did that? Additionally, I've put code and a detailed guide for the netboot computer management setup on GitHub: https://github.com/kentonv/lanparty Anyway, if this shouldn't have been Show HN, I apologize! [0]…
Dev tools · 2024 · lanparty.house
