The use case: how IBM deploys Tavily
IBM's Software Innovations Lab uses Tavily as the web search tool for CUGA, its open-source configurable generalist agent. It replaced custom page scraping, and a shared Tavily-backed search server serves the gallery of apps built on CUGA.
In the customer’s words
...we were able to customize our agent built on CUGA with the help of Tavily. CUGA was our orchestrator, and of course it has an LLM built in it, but Tavily was our tool.Other AI tools used by IBM
Other public relationships recorded on usedby.
Adobe FireflyConfirmed
CoreWeaveConfirmed
CrewAIConfirmed
SlackConfirmed
Weights & BiasesConfirmed
BlipObservedOther companies using Tavily
Customers across industries, with public evidence.
See all Tavily customers
Go straight to the source
Based on Tavily’s published case study. We check the public evidence; the results are reported by the vendor.
tavily.com- Last checked
- Nov 12, 2026
Open source capture What the story claims, and what we checked
What we compared with the page.
- The figure: 24+ appsChecked
Printed word for word on the page, near the name of IBM.
- The passage quoted aboveChecked
Copied word for word from the page, near the name of IBM.
- IBM uses TavilyChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
The IBM Software Innovation Lab team was impressed with Tavily because it removed the scraping layer: Playwright, the DOM, and the job of working out which part of a page was the relevant content.