Pinned Tweet
Introducing Exa 3.0: our largest ever improvement to search quality.
Exa is now #1 on every benchmark we tested, from public evals to verticals like coding and GTM intelligence.
It's the result of multiple research breakthroughs 🧵
Exa is now #1 on every benchmark we tested, from public evals to verticals like coding and GTM intelligence.
It's the result of multiple research breakthroughs 🧵
100
172
2,233
223,757
Exa is excited to partner with @Revolut to power its finance agent!
Revolut built an agent that watches securities. When one moves, Revolut uses Exa to find the news behind it and pushes the story to over 1 million users daily.
Revolut built an agent that watches securities. When one moves, Revolut uses Exa to find the news behind it and pushes the story to over 1 million users daily.
5
4
62
3,056
Revolut benchmarked search API providers on multi-hop retrieval, semantic context, and recency. Exa came out on top for all three.
2
0
10
1,004
The biggest hurdle was multi-hop retrieval: connecting a central bank statement to a sector reaction and a company’s ticker.
Exa finds the right sources because it understands meaning.
Read how Revolut built it: exa.ai/customers/revo…
Exa finds the right sources because it understands meaning.
Read how Revolut built it: exa.ai/customers/revo…
0
0
9
629
Exa retweeted
I had fun chatting with Exa for their inclusion on the 3b1b talent page. It got me thinking about how a lot of the goals for better search end up aligning with goals of better credit assignment/attribution.
We sat down with @3blue1brown to discuss our research vision of "Attention over all the world's information."
Plus why knowledge should not live in model weights, the compression trick behind cheaper retrieval, and why we hire through work trials.
1:20 – What is “attention – A knowledge graph of the whole web
11:32 – How do you evaluate search for AI agents?
15:13 – Why not put everything in the weights?
22:55 – Why Exa hires through work trials
25:15 – The compression trick behind cheaper retrieval
27:40 – Dealing with misinformation
6
19
387
32,028
Exa retweeted
Introducing Exa 3.0: our largest ever improvement to search quality.
Exa is now #1 on every benchmark we tested, from public evals to verticals like coding and GTM intelligence.
It's the result of multiple research breakthroughs 🧵
Exa is now #1 on every benchmark we tested, from public evals to verticals like coding and GTM intelligence.
It's the result of multiple research breakthroughs 🧵
100
172
2,233
223,757
Exa 3.0 highlights make agents more accurate on search tasks, using 95% fewer tokens than full text.
Instead of extracting highlights from each page individually, our new model selects tokens across all results, giving more to the best pages and cutting repeated information.
Instead of extracting highlights from each page individually, our new model selects tokens across all results, giving more to the best pages and cutting repeated information.
4
0
50
6,304
Exa 3.0, Exa Lite, upgraded highlights, and our expanded index are available today through the API.
Read more: exa.ai/blog/exa-3
Read more: exa.ai/blog/exa-3
0
1
41
4,944
💪
Exa just passed $100m in annualized revenue.
We've grown almost exactly 10x per year for 3 years. We now handle 2 billion requests a month from 200k+ teams. And it’s still so early:
We predict agents will search 1000x more than humans by 2030.
Agents don't search like humans. x queries and want all the world's data, not just the web. We've spent 5 years building a search engine designed for them.
We now serve personal agents, AI labs, coding agents, GTM agents, really any agent. Exa gives these agents access to 100s of billions of web documents and tons of proprietary data.
Our customers are increasingly noticing that information is the bottleneck to agent performance. While the world seems close to perfect intelligence with models like Fable and Astra, we are very far from perfect information.
To our small but legendary team, thank you for getting us here, from engineering to research to GTM to ops.
To our customers, it is an honor to serve you. We have some exciting releases coming soon and can't wait to share them 🫡
7
0
81
8,146
Exa retweeted
Exa just passed $100m in annualized revenue.
We've grown almost exactly 10x per year for 3 years. We now handle 2 billion requests a month from 200k+ teams. And it’s still so early:
We predict agents will search 1000x more than humans by 2030.
Agents don't search like humans. x queries and want all the world's data, not just the web. We've spent 5 years building a search engine designed for them.
We now serve personal agents, AI labs, coding agents, GTM agents, really any agent. Exa gives these agents access to 100s of billions of web documents and tons of proprietary data.
Our customers are increasingly noticing that information is the bottleneck to agent performance. While the world seems close to perfect intelligence with models like Fable and Astra, we are very far from perfect information.
To our small but legendary team, thank you for getting us here, from engineering to research to GTM to ops.
To our customers, it is an honor to serve you. We have some exciting releases coming soon and can't wait to share them 🫡
We've grown almost exactly 10x per year for 3 years. We now handle 2 billion requests a month from 200k+ teams. And it’s still so early:
We predict agents will search 1000x more than humans by 2030.
Agents don't search like humans. x queries and want all the world's data, not just the web. We've spent 5 years building a search engine designed for them.
We now serve personal agents, AI labs, coding agents, GTM agents, really any agent. Exa gives these agents access to 100s of billions of web documents and tons of proprietary data.
Our customers are increasingly noticing that information is the bottleneck to agent performance. While the world seems close to perfect intelligence with models like Fable and Astra, we are very far from perfect information.
To our small but legendary team, thank you for getting us here, from engineering to research to GTM to ops.
To our customers, it is an honor to serve you. We have some exciting releases coming soon and can't wait to share them 🫡
225
120
2,038
452,103
We sat down with @3blue1brown to discuss our research vision of "Attention over all the world's information."
Plus why knowledge should not live in model weights, the compression trick behind cheaper retrieval, and why we hire through work trials.
1:20 – What is “attention – A knowledge graph of the whole web
11:32 – How do you evaluate search for AI agents?
15:13 – Why not put everything in the weights?
22:55 – Why Exa hires through work trials
25:15 – The compression trick behind cheaper retrieval
27:40 – Dealing with misinformation
Plus why knowledge should not live in model weights, the compression trick behind cheaper retrieval, and why we hire through work trials.
1:20 – What is “attention – A knowledge graph of the whole web
11:32 – How do you evaluate search for AI agents?
15:13 – Why not put everything in the weights?
22:55 – Why Exa hires through work trials
25:15 – The compression trick behind cheaper retrieval
27:40 – Dealing with misinformation
9
33
252
54,453
We built ATLAS, a web search benchmark for how agents actually search today.
Existing agentic search benchmarks are often outdated, contaminated, or saturated. ATLAS is designed to separate strong search from weak search.
Learn more: exa.ai/blog/atlas-ben…
Existing agentic search benchmarks are often outdated, contaminated, or saturated. ATLAS is designed to separate strong search from weak search.
Learn more: exa.ai/blog/atlas-ben…
18
36
166
23,594
ATLAS tasks require many sources to retrieve fresh or niche information.
Questions are synthetically generated through an automated pipeline based on real-world search trends, covering 20+ topic categories.
Questions are synthetically generated through an automated pipeline based on real-world search trends, covering 20+ topic categories.
1
0
12
822
Even the top search agents set to the highest effort modes cannot find 1/3 of the verified information.
Read the full research: exa.ai/blog/atlas-ben…
Read the full research: exa.ai/blog/atlas-ben…
0
0
12
713
We just added 211 million restaurants, museums, and parks to Exa's index.
Give your AI agents access to search over all the places in the world with structured data including opening hours, reviews, and phone numbers.
Give your AI agents access to search over all the places in the world with structured data including opening hours, reviews, and phone numbers.
33
29
363
81,842
Exa Places significantly improves the accuracy of personal agents that are performing tasks with local intent.
It has the highest accuracy across search providers we evaluated.
It has the highest accuracy across search providers we evaluated.
5
0
49
5,808