# How Hebbia uses Braintrust

**\<24 hours**: “\<24 hours to eval and deploy new models”

As published on [braintrust.dev](https://www.braintrust.dev/customers/hebbia). Captured by usedby on 2026-11-21.

- Company: [Hebbia](https://www.usedby.ai/companies/hebbia.md)
- Tool: [Braintrust](https://www.usedby.ai/tools/braintrust.md)
- Industry: [Artificial Intelligence](https://www.usedby.ai/companies/industry/artificial-intelligence.md)
- Teams: Applied AI

## The use case: how Hebbia deploys Braintrust

Hebbia, an AI research and diligence platform for finance teams, uses Braintrust to trace and evaluate its long-horizon agents. It feeds traces into an automated eval loop that tests new models and tunes prompts and tools, and it runs Braintrust in a BYOC deployment for regulated customers.

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

> Where the team previously spent a week or two to reach a calculation of where an agent was, where it could be, and what savings that represented, they can now do that on virtually day one with Braintrust.

> Braintrust helps us stop focusing on the minutiae of infrastructure associated with evaluations and just focus on the results that we care about.
>
> Adithya Ramanathan, Head of Applied AI

Source: [braintrust.dev](https://www.braintrust.dev/customers/hebbia), captured 2026-11-21.

## Other AI tools used by Hebbia

- [Baseten](https://www.usedby.ai/tools/baseten.md) — Confirmed
- [Claude](https://www.usedby.ai/tools/claude.md) — Confirmed
- [Gemini](https://www.usedby.ai/tools/gemini.md) — Confirmed
- [Cerebras](https://www.usedby.ai/tools/cerebras.md) — Declared by the company
- [Datadog](https://www.usedby.ai/tools/datadog.md) — Declared by the company
- [Fireworks AI](https://www.usedby.ai/tools/fireworks-ai.md) — Declared by the company

## Braintrust users in Artificial Intelligence

- [Rex](https://www.usedby.ai/companies/rex.md) — Confirmed
- [Tolan](https://www.usedby.ai/companies/tolan.md) — Confirmed
- [Granola](https://www.usedby.ai/companies/granola.md) — Observed
- [Lovable](https://www.usedby.ai/companies/lovable.md) — Observed
- [Suno](https://www.usedby.ai/companies/suno.md) — Observed

## What usedby checked

We compared the story with its live page on 2026-11-21.

- Checked: the figure \<24 hours is printed word for word on the page, near the name of Hebbia.
- Checked: the passage quoted above is copied word for word from the page, near the name of Hebbia.
- Checked: Hebbia uses Braintrust. Confirmed line. Latest check across sources: 2026-11-21.
- Not checked: the result itself. We quote it; we did not measure it.

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