> ## 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 Gemini *Learn how to set up Hugo, the Crisp AI Support Agent, as a Google Gemini-powered AI chatbot for customer support.* Hugo combines a supported **Google Gemini model** with your support content, business instructions, routing rules, and human handoff. This gives teams a fast and cost-efficient [customer support chatbot](https://crisp.chat/en/chatbot/gemini/) while keeping the complete support experience inside Crisp. [Discover Hugo](https://hugo.ai/en/) to see how the AI Agent for customer support works. ||| Gemini 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 Gemini AI chatbot for customer support) __To select a Google Gemini 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 Gemini 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 Gemini manually if using Google AI is an important part of your support configuration. ![Select a Google Gemini model in Hugo settings](https://storage.crisp.chat/users/helpdesk/website/-/8/7/a/e/87ae2703583ac800/cleanshot-2026-06-23-at-235453_upjy8w.png =1000xauto) Choosing a model is only one part of the setup. Add reliable 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 Gemini works well for customer support) In our testing, Gemini's main strengths are **speed and cost efficiency** rather than maximum reasoning horsepower. It performs well for its price and is particularly attractive to teams that already prefer or standardize on the Google AI ecosystem. __Gemini models are especially useful for:__ * **Fast replies** → keep real-time customer conversations responsive * **Cost control** → handle larger conversation volumes with lower relative credit usage * **Straightforward support** → answer common questions effectively when documentation is clear and structured * **Google AI preference** → give teams already working with Google technologies a familiar model provider * **Visual context** → analyze customer screenshots and images when image processing is enabled Lower-cost Gemini models may be less suitable when Hugo must reason across many interconnected sources or follow particularly intricate instructions. Test those situations carefully before deploying Gemini across complex support operations. --- # ${color}[#0080dd](Compare the Gemini models available in Hugo) Hugo currently supports **Gemini 3.5 Flash** and **Gemini 3 Flash Preview**. The price levels below represent relative Hugo credit usage rather than a fixed price per conversation. | Gemini model | Intelligence | Relative price | Recommended use | | ---- | | **Gemini 3.5 Flash** | High | $$ | Teams wanting the most capable Gemini option available in Hugo, with stronger reasoning while remaining relatively fast and economical | | **Gemini 3 Flash Preview** | Medium | $ | High-volume support, straightforward questions, very fast replies, and deployments focused primarily on reducing AI costs | **Gemini 3.5 Flash** is the better choice when you want to remain within the Google model family while handling more varied or demanding questions. **Gemini 3 Flash Preview** prioritizes speed and cost, making it useful for businesses with clear documentation and predictable support requests. Gemini is generally selected for its efficiency and provider ecosystem rather than for the deepest possible reasoning. For many everyday support use cases, that trade-off can provide excellent value. | 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 Gemini AI customer support chatbot) Before going live, open **AI Agent → Evaluate → Playground → Compare model options**. Test both Gemini models with the same real customer questions, including common FAQs, ambiguous requests, follow-up questions, screenshots, and cases involving several support resources. Compare **answer accuracy**, **response speed**, **source usage**, **image understanding**, **escalation behavior**, and **credit usage**. A lower-cost Gemini model may perform perfectly on everyday questions while the more capable option handles nuanced conversations more consistently. 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 Google AI or Vertex AI API key to use Gemini with Hugo?) No. Supported Gemini models are managed directly through Hugo, and you cannot connect an external Google AI or Vertex AI API key. Select the model you want from **AI Agent → Agent → Settings**. ###### ${color}[#F08820](Does Hugo support every Gemini model released by Google?) Almost. Hugo exposes a selected list of supported models rather than every Gemini 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](Why choose Gemini instead of a more powerful model?) Gemini is a strong choice when **speed**, **cost control**, or a preference for the **Google AI ecosystem** matters more than maximum reasoning power. It performs particularly well for high-volume support with clear documentation. For complex instructions or deeply interconnected resources, compare it against Claude, GPT, or Mistral using **AI Agent → Evaluate → Playground → Compare model options**.