Braintrust

2 tools · 19 companies · 20 verified facts — receipts on every one.

Companies with Braintrust in the stack

Box Browserbase Bubble Cloudflare Coursera Dropbox Eve Fintool Graphite Loom Navan Notion Portola Pylon Replit Retool Rex Vercel Zapier

All Braintrust facts

Box · Braintrust

Runs programmatic evaluations and dataset curation for its AI agent.

High confidence

Source last verified Jul 27, 2026 View fact with receipts →
Browserbase · Braintrust

Runs benchmarks and evaluates browser-agent model performance.

High confidence

Source last verified Jul 27, 2026 View fact with receipts →
Bubble · Braintrust

Runs evals, trace triage, and model comparisons for its Agent.

High confidence

Source last verified Oct 26, 2026 View fact with receipts →
Cloudflare · Braintrust

Evaluates the dashboard agent and gates skill changes in CI/CD.

High confidence

Source last verified Aug 22, 2026 View fact with receipts →
Coursera · Braintrust

Evaluates AI features and monitors production quality.

High confidence

Source last verified Jul 27, 2026 View fact with receipts →
Dropbox · Braintrust

Builds multi-tier evaluation pipelines and detects production regressions.

High confidence

Source last verified Jul 27, 2026 View fact with receipts →
Eve · Braintrust

Measures agent quality against the Plaintiff Bench benchmark and production traffic.

High confidence

Source last verified Aug 22, 2026 View fact with receipts →
Fintool · Braintrust

Benchmarks LLM output quality with repeatable evaluation workflows.

High confidence

Source last verified Jul 27, 2026 View fact with receipts →
Graphite · Braintrust

Evaluates code-review features and compares model variants.

High confidence

Source last verified Jul 27, 2026 View fact with receipts →
Loom · Braintrust

Runs evals with custom scoring functions on AI output quality.

High confidence

Source last verified Jul 27, 2026 View fact with receipts →
Navan · Braintrust

Runs the evaluation loop for AI voice agent quality.

High confidence

Source last verified Jul 27, 2026 View fact with receipts →
Notion · Braintrust

Eval and LLM-observability platform for regression and frontier-model testing.

High confidence

Source last verified Jul 26, 2026 View fact with receipts →
Portola · Braintrust

Curates datasets and iterates on prompts for conversation quality.

High confidence

Source last verified Jul 27, 2026 View fact with receipts →
Pylon · Braintrust

Tests every prompt in CI and observes production traffic.

High confidence

Source last verified Aug 22, 2026 View fact with receipts →
Pylon · Loop

Spins up new LLM-as-a-judge scorers for bulk quality checks.

High confidence

Source last verified Aug 22, 2026 View fact with receipts →
Replit · Braintrust

Unified observability and custom evals across production AI agent sessions.

High confidence

Source last verified Nov 9, 2026 View fact with receipts →
Retool · Braintrust

Evaluates AI classifier accuracy through iterative testing.

High confidence

Source last verified Jul 27, 2026 View fact with receipts →
Rex · Braintrust

Traces agent touchpoints and runs evals for model selection.

High confidence

Source last verified Aug 31, 2026 View fact with receipts →
Vercel · Braintrust

Benchmarks new model releases and reviews production traces for quality issues.

High confidence

Source last verified Nov 9, 2026 View fact with receipts →
Zapier · Braintrust

Logs interactions, tracks feedback, and manages evaluation test sets.

High confidence

Source last verified Jul 27, 2026 View fact with receipts →