Skip to main content
usedby
Search tools, companies

How Cloudflare uses Braintrust

As published on braintrust.dev. Captured by usedby on Oct 6, 2026.

What happened

Cloudflare's Agent Experience team uses Braintrust to evaluate its dashboard agent, running an LLM-as-a-judge over whole conversations to score resolution, gating skill, prompt and recipe changes in CI/CD, and benchmarking sub-agents against models of varying capacity.

Summary written by usedby from the source page, in English. The figures are those of Braintrust and Cloudflare, not ours.

The dashboard agent's behavior lives in skills, recipes, and prompts, and every change runs through evals in CI/CD. Cloudflare built a shared component, now used across platform internals, that measures skill performance before and after a change.

From the page. braintrust.dev, captured Oct 6, 2026

Instead of shipping changes, measuring them in production, and going back to the drawing board, we get to iterate directly in development, see how it performs, and then ship it to production.

Kylie Czajkowski, Agent Experience Manager, Cloudflare. Source, captured Oct 6, 2026

What the story claims, and what we checked

We compared the story with its live page on Oct 6, 2026.

  • The passage quoted aboveCheckedCopied word for word from the page, near the name of Cloudflare.
  • Cloudflare uses BraintrustCheckedConfirmed line. Latest check across sources: Oct 6, 2026.
  • The result itselfNot checkedWe quote it; we did not measure it.

Same company, same tool or same industry.

80%+Score threshold for internal releaseBox uses Braintrust. Another customer of Braintrust>0.9Eval system macro F1 scoreNavan uses Braintrust. Another customer of Braintrust75 percent“75 percent reduction in incident investigation time”Zscaler uses Resolve. Same industry: Cybersecurity