# How Ardian uses Mistral

**2X**: “2X increase in weekly active users”

As published on [mistral.ai](https://mistral.ai/customers/ardian/), April 2026. Captured by usedby on 2026-10-02.

- Company: [Ardian](https://www.usedby.ai/companies/ardian.md)
- Tool: [Mistral](https://www.usedby.ai/tools/mistral.md)
- Industry: [Investment & VC](https://www.usedby.ai/companies/industry/investment-vc.md)
- Teams: Investment teams

## What the story says

Ardian built GAIA, an internal generative AI platform with Artefact that includes Mistral models alongside others. Investment teams upload documents and query them in natural language for first-pass analysis and summarization, including French-language documents, to support due diligence and deal analysis.

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

> The adoption of GAIA has exceeded expectations, with over 500 weekly active users. The platform has processed 18,000+ documents since inception and generated more than 280,000 user requests

- **2X**: “2X growth in documents processed”
- **200K+**: “200K+ AI-powered queries generated”
- **18,000+**: “The platform has processed 18,000+ documents since inception”
- **280,000**: “generated more than 280,000 user requests”

> We realized we couldn't rely solely on OpenAI. We needed model flexibility—so we added Mistral models, which turned out to be very efficient, especially with French documents and summarization tasks,
>
> Arthur Garnier, Senior Data Scientist and IT Chief of Staff at Ardian

## What usedby checked

We compared the story with its live page on 2026-10-03.

- Checked: the figure 2X is printed word for word on the page, near the name of Ardian.
- Checked: the passage quoted above is copied word for word from the page, near the name of Ardian.
- Checked: the publication date is read from the page’s own metadata, never guessed.
- Checked: Ardian uses Mistral. Confirmed line. Latest check across sources: 2026-10-02.
- Not checked: the result itself. We quote it; we did not measure it.

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