Show HN: Exa (YC S21) – embeddings search agent with >20x recall than Google
websets.exa.aiHey HN! I'm Will, founder of Exa (YC21 - https://exa.ai). Today we're opening up Websets, a search engine that finds massive lists of correct results given complex queries.
For example, you can search for:
- “software engineers in the Bay Area, with experience in startups and big tech, who know Rust and have published technical content”: https://websets.exa.ai/cm7ax5bl8003276q689v0dde5
- “US based healthcare companies, with over 100 employees and a technical founder": https://websets.exa.ai/cm6lc0dlk004ilecmzej76qx2
- "research paper about ways to avoid the O(n^2) attention problem in transformers, where one of the first author's first name starts with "A","B", "S", or"T", and it was written between 2018 and 2022”: https://websets.exa.ai/cm7dpml8c001ylnymum4sp11h
We built Websets because the web is humanity’s grand collection of all knowledge, and yet it’s totally unorganized. So much valuable content is too hard to find.
Traditional search engines, like Google, were built to handle simple keyword queries over the web, not arbitrarily complex SQL. While agentic tools like Deep Research help a bit, they rely on traditional search under the hood and so are similarly bottlenecked.
Websets works well because under the hood it uses our in-house embedding-based search engine, trained specifically to handle complex natural language queries. Crucially, Websets uses LLMs to agentically verify each result to ensure correctness. Websets is therefore a test-time compute search engine – it might take minutes or even hours to run. We believe this is a worthwhile sacrifice for high value searches.
It’s hard to eval these things, but we did our best and measured that Websets found 20x more results than Google on a set of complex queries and 10x more than Deep Research. These numbers could be arbitrarily higher with more compute per query. Blog post here: https://exa.ai/blog/websets-evals
While Websets isn’t perfect search yet, it’s a significant first step, and we’re excited to share the first version of the product with you all. We have a free limited tier, and we set up a special HN code for Pro plans. Use PERFECTSEARCH for a two-week free trial of Pro.
Can try it here: websets.exa.ai
Initial launch video here: https://x.com/ExaAILabs/status/1864013080944062567
Would love to hear thoughts, feedback, and suggestions! I know HN thinks about search sometimes :) This is cool. Is it more meant for perfect recall or perfect precision of results? Hey Paulista, Cofounder Jeff here. Both! Very cool, congrats on the launch! amazing. f1 score = 1