> For the complete documentation index, see [llms.txt](https://docs.distro.so/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.distro.so/integrations/gemini.md). # Google Gemini Use Google Gemini in an **AI Prompt** workflow step with your own provider credentials. ## Connect An admin opens **Settings → Integrations → Google Gemini** and enters the **Gemini API key** from the intended Google AI Studio account or project. Saving lists available models to verify the key. It does not send a prompt. Live prompts use your provider account and billing. ## Configure an AI Prompt Choose the provider and a model available to your account. Write the task, map only the lead fields it needs and define the output structure offered by the editor. For example, ask the model to classify an enquiry as Sales, Support or Other, with a short reason. Add conditions for each useful result and a fallback for missing or unexpected output. Use [Web Research](/integrations/parallel.md) when the task needs evidence from web sources. A prompt does not itself guarantee current web research. ## Check the result Simulate the branch wiring, then make a controlled live call with non-sensitive sample data. Inspect the response and mapped fields. If verification succeeds but a prompt fails, check model access, provider quota, input size and output format. Do not interpret an API error as a negative classification. See [AI and web research](/data-and-integrations/ai.md) for guidance on deciding which step to use. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.distro.so/integrations/gemini.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `build a script that syncs our docs to a CMS` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.