How to create an AI Chatbot for Customer Service with Gemini
Learn how to set up Hugo, the Crisp AI 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 while keeping the complete support experience inside Crisp. Discover Hugo to see how the AI Agent works.
How to set up a Gemini AI chatbot for customer support
To select a Google Gemini model in Hugo:
- Sign in to Crisp.
- Open AI Agent → Agent → Settings.
- Under Model, disable Choose automatically and select a supported Gemini model.
- 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.
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.
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.
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.
Test and launch your Gemini 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.
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.
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.
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.
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.
Updated on: 23/06/2026
Thank you!