willbryk

Google is the most well known search engine, but there is very little research on how other search providers affect RL outcomes. Turns out Exa reached higher performance with 70% less training compute.

exa-d is our internal data processing framework that stores the web in S3. It helps deal with the complexity of data at (web) scale using specific design decisions like declarative typed dependencies and enabling sparse updates.

stay tuned!

Thanks Artem! That makes sense to specialize for the biggest customers. Yes, a lot of problems in the world would be improved by better search, including dating.

This might be possible if you specify geospatial location as an enriched column. The visualization of it as a map though is not supported in the UI, but can be built by giving an LLM access to the Websets API

Because Google makes money from ads, they're not actually optimized to build the best general search engine in the world, they're optimized to build the search engine that makes the most from ads, which is correlated with being a good search engine but not perfectly aligned. Our business model (paying directly for the search) incentivizes us to try to return the highest quality results, without any bias toward making money from ads. It also enables us to do things like pour a ton of compute/resources into a query to get the best possible results we can find, because someone would pay us a lot for that, and that's hard to do under an ads-based model.

There aren't currently any vision LLMs involved. But if you asked for image links, it'd probably find you something!

Thanks for letting us know - made a Linear ticket

Mission of Exa has always been to build much better web search. The evolution has been:

- 2022: Consumer-facing embeddings search (back when we were known as Metaphor)

- 2023: Web search for AIs - once the AI ecosystem heated up, we made a business out of web search + crawling API. This is still our primary business.

- Now: Websets, a useful product built on top of our search tech

If you're curious, our company right now is fully devoted to:

1. Dramatically improving Websets quality

2. Building the best general search engine in the world

Thanks for the support - we're getting hug of death though so please bear with us while we scale up!

Yup exactly! And we expose this as a regular search API as well as in the Websets product.

Thanks for the feedback!

Yeah we'd love to make the product as accessible and cheap as possible, but as of state of AI costs of 2025, it's a very expensive product to run and so we have it login gated. If you're willing to log in though, you'll find a lot of the features that you're mentioning :)

Hm! I'll try this out. Sometimes info like price are hard to parse out because the data may be on ecommerce-style websites that have many crawling protections

ty!

Thanks! Let us know how you find it :)

By cruft cleaner, do you mean cleaning the HTML well? Right now, we do 2 things to help with that, a pretty robust parsing stack as well as a "summaries" feature that returns an LLM-generated query-biased text output for every webpage returned.

If something else though, curious.

Thanks!

Not a pivot - Websets is just a new product!

Mission of Exa has always been to build much better web search. The evolution has been:

- 2022: Consumer-facing embeddings search (back when we were known as Metaphor)

- 2023: Web search for AIs - once the AI ecosystem heated up, we made a business out of web search + crawling API. This is still our primary business.

- Now: Websets, a useful product built on top of our search tech

If you're curious, our company right now is fully devoted to:

1. Dramatically improving Websets quality

2. Building the best general search engine in the world

We're a startup, so most of our resources go towards use cases that our users care most about. So the search should work best for - people, companies, papers, high quality written content (e.g., blogs, news). It should work well at more than just those (try Github repo search, it's quite good :D), but those are the best supported.

Types of searches Websets doesn't currently do well at: - products (e.g., ecommerce sites) - Content that requires authentication/permissions to access - non-English content

Some of the above are on our roadmap, and let us know if there's some type of data you'd like us to support!

We render JS and then parse pages, but that process will definitely parse out Adobe Analytics tags unfortunately.

Noting this though!