The use case: how Aaru deploys Exa
Aaru builds simulations of human behavior for companies and uses Exa Search for web search data in those simulations. It also uses Exa Snapshot, a cached time-indexed web index, to cut off data after a given date so backtested simulations and evaluations are not contaminated by later information.
More reported results
Figures published in Exa’s case study. They are not independently measured by usedby.
In this evaluation, Exa won on all five criteria while returning results with 7x lower latency.
Across 10,000 tested queries, Exa’s results were preferred over the competitor’s 81% of the time.
In the customer’s words
The general pattern with good developer tooling is that it enables engineers to focus on what they do best. We’re glad that Exa has allowed us to concentrate on advancing human simulations rather than search indexes.Other companies using Exa
Customers across industries, with public evidence.
See all Exa customersGo straight to the source
Based on Exa’s published case study. We check the public evidence; the results are reported by the vendor.
exa.ai- Last checked
- Nov 21, 2026
Open source capture What the story claims, and what we checked
What we compared with the page.
- The figure: 5xChecked
Printed word for word on the page, near the name of Aaru.
- The passage quoted aboveChecked
Copied word for word from the page, near the name of Aaru.
- Aaru uses ExaChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
Snapshot drove a 5x decrease in LLM spend within the filtering component of the pipeline by removing the need to verify all inputs as contamination-free.






