The use case: how Dropbox deploys Braintrust
Dropbox uses Braintrust to evaluate the AI features of its Dash product. It runs a multi-tier pipeline of pre-merge smoke tests, a full post-merge suite, and online LLM-as-a-judge scoring of sampled production queries, and feeds production traces back into new test sets.
More reported results
Figures published in Braintrust’s case study. They are not independently measured by usedby.
Pre-merge smoke tests (150 tests).
In the customer’s words
We can run hundreds to thousands of experiments with Braintrust.Other AI tools used by Dropbox
Other public relationships recorded on usedby.
Explore Dropbox’s AI stack
Braintrust users in DevTools & Infrastructure
Companies in the same sector, with public evidence.
See all Braintrust customers
Go 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: 10,000+Checked
Printed word for word on the page, near the name of Dropbox.
- The passage quoted aboveChecked
Copied word for word from the page, near the name of Dropbox.
- Dropbox uses BraintrustChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
Evals are how Dropbox applies this testing rigor to its AI, and with Braintrust they've built a structured, multi-tier testing pipeline: