The use case: how Navan deploys Braintrust
Navan built Miles, an AI voice agent that calls hotels to confirm bookings and provide payment details, and uses Braintrust to log every call and run automated LLM-judge evaluations that classify call outcomes. Braintrust also supports debugging the judge prompts and gives the operations team a filtered dashboard of calls needing human follow-up.
In the customer’s words
Eval-driven development is the new test-driven development. Any projects that we take up, the first step is identifying the eval set.Other AI tools used by Navan
Other public relationships recorded on usedby.
ThoughtSpotConfirmed
BasetenObserved
BrightHireObserved
CyberhavenObserved
FrontObserved
MetaviewObservedBraintrust users in Travel & Hospitality
Companies in the same sector, with public evidence.
See all Braintrust customersGo straight to the source
Based on Braintrust’s published case study. We check the public evidence; the results are reported by the vendor.
braintrust.dev- Last checked
- Nov 10, 2026
Open source capture What the story claims, and what we checked
What we compared with the page.
- The figure: 0.56 → 0.89Checked
The figure is on the page; its label is our wording.
- The passage quoted aboveChecked
Copied word for word from the page, near the name of Navan.
- Navan uses BraintrustChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
Every call is logged in Braintrust, instrumented with agent behavior, reasoning steps, and intermediate data.

