The use case: how Bubble deploys Braintrust
Bubble's AI team uses Braintrust to run evals on its app-building Agent, scoring quality, latency and cost against datasets and comparing experiments when changing code or swapping models. They also use the Braintrust CLI with coding agents to triage production traces and open fixes and tickets automatically.
In the customer’s words
In the couple of weeks leading up to this launch, we were plugging in new models very regularly. Braintrust has given us the ability to make those decisions with confidence, about which model to move forward with.Other AI tools used by Bubble
Other public relationships recorded on usedby.
Explore Bubble’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
- Oct 25, 2026
Open source capture What the story claims, and what we checked
What we compared with the page.
- The figure: 1.5xChecked
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 Bubble.
- Bubble uses BraintrustChecked
Confirmed line.
- The result itselfNot checked
We quote it; we did not measure it.
Bubble recently launched Agent 2, a completely new version of its core app-building Agent. It's 1.5 times more accurate than its predecessor at visually representing user prompts, while also performing faster and more cost efficiently.