The use case: how Retool deploys Braintrust
Retool uses Braintrust to log and analyze production traces from its AI development assistant, Assist. The team queries logs with BTQL, builds dashboards, uses Loop to find root causes of failures, and runs evals with datasets and scorers to improve a classifier and decide what to build next.
In the customer’s words
At our scale, everything would break if we just tried to do this manually without something like Braintrust. Braintrust has been the lifeblood of our ability to execute against our roadmap, both near term and long term.Other AI tools used by Retool
Other public relationships recorded on usedby.
MomenticConfirmed
WebflowConfirmed
BasetenObserved
Common RoomObserved
GreptileObserved
HightouchObservedBraintrust users in DevTools & Infrastructure
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: 23%Checked
The figure is on the page; its label is our wording.
- Retool uses BraintrustChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
Through iterative evaluation using Braintrust datasets and scoring functions, the team also drove the front-of-house classifier from 72% to 95% accuracy by analyzing misclassified queries in production logs





