The use case: how Replit deploys Braintrust
Replit uses Braintrust as a unified observability layer for its AI agent, streaming traces in real time and aggregating them to find patterns across many user sessions. Engineers and support staff use it to investigate issues, run custom evals to catch regressions, and fix groups of related problems.
More reported results
Figures published in Braintrust’s case study. They are not independently measured by usedby.
100s of production examples surfaced per issue
In the customer’s words
What happens if there are multiple people experiencing the same pain but not expressing it? Having this ability to go beyond a single session and see patterns across the board really helps us fix a whole family of problems.Other AI tools used by Replit
Other public relationships recorded on usedby.
CampfireConfirmed
ClaudeConfirmed
Common RoomConfirmed
MetaviewConfirmed
BasetenDeclared
EnterpretDeclaredBraintrust 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 5, 2026
Open source capture What the story claims, and what we checked
What we compared with the page.
- The figure: 5–10 mins → instantChecked
Printed word for word on the page, near the name of Replit.
- The passage quoted aboveChecked
Copied word for word from the page, near the name of Replit.
- Replit uses BraintrustChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
One of the things that really worked for us is that the Braintrust team helped us optimize the feedback loop so that instead of having to wait five or 10 minutes to see the traces, the moment the user is experiencing pain, we can see the trace immediately.