> ## Knowledge Base Index
> Fetch the complete knowledge base index at: https://help.crisp.chat/sitemap.xml
> Use this file to discover available pages before exploring further.
> Pure-Markdown content can be obtained by appending a '.md' suffix to the content URLs listed in the sitemap (without the trailing slash).

# How to create an AI Chatbot for Customer Service with Mistral

*Learn how to set up Hugo, the Crisp AI Agent for customer support, as a Mistral-powered AI chatbot for customer support.*

Hugo combines a supported **Mistral AI model** with your support content, business instructions, routing rules, and human handoff. This gives businesses a natural, multilingual [customer support chatbot](https://crisp.chat/en/chatbot/mistral/) powered by a European model provider. [Discover Hugo](https://hugo.ai/en/) to see how the AI Agent works.

||| Mistral model availability evolves over time. Always check **AI Agent → Agent → Settings** for the current options in your workspace.

---

# ${color}[#0080dd](How to set up a Mistral AI chatbot for customer support)

__To select a Mistral model in Hugo:__
1. Sign in to [**Crisp**](https://app.crisp.chat).
2. Open **AI Agent → Agent → Settings**.
3. Under **Model**, disable **Choose automatically** and select a supported Mistral model.
4. Review **Region**, **Enable Hugo's built-in fallback model**, **Allow agent to process images**, and **Allow agent to transcribe audio messages** when those options are available.

When **Choose automatically** is enabled, Hugo may use a model from another provider. Select Mistral manually if working with a European AI provider is important to your organization.

![Select a Mistral model in Hugo settings](https://storage.crisp.chat/users/helpdesk/website/-/8/7/a/e/87ae2703583ac800/cleanshot-2026-06-23-at-235517_1nfto82.png =1000xauto)

Choosing a model is only one part of the setup. Add accurate support resources from **AI Agent → Train**, define Hugo's behavior from **AI Agent → Guidance → Instructions**, and configure escalation or routing rules from **AI Agent → Guidance → Routing**.

---

# ${color}[#0080dd](Why Mistral works well for customer support)

In our testing, Mistral is particularly good at analyzing support resources and carrying natural, human-sounding conversations. It can move smoothly between customer questions and follow-ups, making it a strong option for businesses that want capable AI support without making conversations feel mechanical.

__Mistral models are especially useful for:__
* **Source analysis** → identify and assemble relevant information from articles, documents, and other training resources
* **Natural dialogue** → respond conversationally and move smoothly between related questions
* **Multilingual support** → handle customer conversations across different languages and markets
* **European provider preference** → give EU-focused businesses the option to work with a European AI model provider

Choosing a European provider does not automatically determine where every request is processed. If data location is important to your organization, review the available **Region** option separately from the selected model.

---

# ${color}[#0080dd](Compare the Mistral models available in Hugo)

Hugo currently supports **Mistral Large** and **Mistral Medium**. The price levels below represent relative Hugo credit usage rather than a fixed price per conversation.

| Mistral model | Intelligence | Relative price | Recommended use |
| ---- |
| **Mistral Large** | High | $$ | Complex support questions, deeper source analysis, nuanced conversations, and cases requiring stronger reasoning |
| **Mistral Medium** | Medium | $ | Clear documentation, standard customer questions, natural high-volume conversations, and cost-conscious deployments |

**Mistral Large** provides more reasoning power when Hugo must combine several resources or interpret a complicated request. **Mistral Medium** is a strong starting point for businesses with structured documentation and relatively straightforward support needs.

Both models are particularly effective when the goal is to provide helpful answers while preserving a conversational, human-sounding tone.

| See [which AI models Hugo supports and how to configure them](https://help.crisp.chat/en/article/how-to-choose-and-configure-hugos-ai-model-1m4mm57/) for the latest model, region, and relative pricing options.

---

# ${color}[#0080dd](Test and launch your Mistral customer support chatbot)

Before going live, open **AI Agent → Evaluate → Playground → Compare model options**. Test both Mistral models with the same real customer questions, including common FAQs, multilingual requests, longer exchanges, questions involving several support resources, and situations that should be escalated.

Compare **answer accuracy**, **source usage**, **conversation quality**, **reasoning**, **response speed**, and **credit usage**. Pay particular attention to whether the model interprets your resources correctly and maintains a natural tone throughout follow-up questions.

Once you have selected the right configuration, deploy Hugo from **AI Agent → Agent → Activation**. For the complete training, guidance, testing, and activation process, follow [Getting started with Hugo AI Agent](https://help.crisp.chat/en/article/getting-started-with-hugo-ai-agent-w6gbux/).

---

# ${color}[#0080dd](Frequently Asked Questions)

*Still have questions which were not covered in this article? Here is a collection of the most frequently asked questions on this topic.*

###### ${color}[#F08820](Do I need a Mistral API key to use Mistral with Hugo?)

No. Supported Mistral models are managed directly through Hugo, and you cannot connect an external Mistral API key. Select the model you want from **AI Agent → Agent → Settings**.

###### ${color}[#F08820](Does Hugo support every model released by Mistral AI?)

Almost. Hugo exposes a selected list of supported models rather than every Mistral release. The models displayed under **AI Agent → Agent → Settings** are the source of truth for your workspace.

At Crisp, we regularly evaluate and implement new model releases so Hugo continues to offer modern and competitive options.

###### ${color}[#F08820](Does selecting Mistral guarantee that my data stays in Europe?)

Not by itself. Mistral is a European model provider, but provider origin and request-processing location are separate considerations. Check the **Region** options available for your selected model under **AI Agent → Agent → Settings**, and validate the configuration against your organization's legal, security, and data-processing requirements.