←back to thread

28 points vignesh_warar | 2 comments | | HN request time: 0.4s | source

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...

1. connor11528 ◴[] No.42198332[source]
how are you harvesting all this data?
replies(1): >>42198341 #
2. vignesh_warar ◴[] No.42198341[source]
It's just the Bing search API under the hood. The process is: Query -> Crawl -> Categorize profiles.