# How Eve uses Braintrust

**over 400** plaintiff law tasks in the Plaintiff Bench

As published on [braintrust.dev](https://www.braintrust.dev/customers/eve). Captured by usedby on 2026-10-06.

- Company: [Eve](https://www.usedby.ai/companies/eve.md)
- Tool: [Braintrust](https://www.usedby.ai/tools/braintrust.md)
- Industry: [Legal & Compliance](https://www.usedby.ai/companies/industry/legal-compliance-legaltech.md)

## The use case: how Eve deploys Braintrust

Eve, a legal AI company for plaintiff law firms, uses Braintrust to run evals on its legal agents against an expert-graded benchmark, with failures tagged by type. It also uses Braintrust to test new models, turn production mistakes into test cases, score production behavior, and let coding agents iterate on metrics through the CLI.

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

> Because Braintrust automatically preserves all the context used to generate a given output, failures are reproducible by default.

- **five**: “At any given time he has around five agents running in parallel, reviewing their work as pull requests.”
- **40+**: “The benchmark is now the largest dataset of its kind, with over 400 plaintiff law tasks across 40+ states and a wide distribution across task types and failure modes.”

> I gave it a task: "Your task is to improve these metrics." It can create hypotheses, implement them, run experiments using the Braintrust CLI, see the results, and go for hours. When I came back, I had a report with the experiment outputs and the best approaches.
>
> Mauricio Wulfovich, Staff Machine Learning Engineer

Source: [braintrust.dev](https://www.braintrust.dev/customers/eve), captured 2026-10-06.

## Other AI tools used by Eve

- [Labelbox](https://www.usedby.ai/tools/labelbox.md) — Observed
- [Retell AI](https://www.usedby.ai/tools/retell-ai.md) — Observed

## Other companies using Braintrust

- [Box](https://www.usedby.ai/companies/box.md) — Confirmed
- [Browserbase](https://www.usedby.ai/companies/browserbase.md) — Confirmed
- [Cloudflare](https://www.usedby.ai/companies/cloudflare.md) — Confirmed
- [Coursera](https://www.usedby.ai/companies/coursera.md) — Confirmed
- [Dropbox](https://www.usedby.ai/companies/dropbox.md) — Confirmed
- [Graphite](https://www.usedby.ai/companies/graphite.md) — Confirmed

## What usedby checked

We compared the story with its live page on 2026-10-06.

- Checked: the figure over 400 is on the page; its label is our wording.
- Checked: the passage quoted above is copied word for word from the page, near the name of Eve.
- Checked: Eve uses Braintrust. Confirmed line. Latest check across sources: 2026-10-19.
- Not checked: the result itself. We quote it; we did not measure it.

---
Source: https://www.usedby.ai/case-studies/eve-braintrust · How we check: https://www.usedby.ai/methodology