How to Connect Google AI to DAVE

Summary

The steps

1. 1

   Get your Google AI API key

   Before you configure anything in DAVE, you need an active Google AI API key. Google AI API keys are issued through Google AI Studio at aistudio.google.com. Log in, navigate to Get API key, and create a new key for your project. Copy it immediately and store it securely.

   Keep this key secure. You will paste it into DAVE's Providers screen in the next step. Once stored, it is encrypted at rest with AES-256-GCM authenticated encryption and will never be returned in plain text through the API.

   Do this

   • Log in to aistudio.google.com.
   • Navigate to Get API key and create a new key, associating it with the correct Google Cloud project.
   • Copy the key value and store it temporarily in a secure location such as a password manager.
   • Note which Gemini models are available to your account. You will select from these when building the model catalog in DAVE.
   • Optionally, set quota limits in the Google Cloud Console to cap usage during development and testing.

   Example

   A Google AI API key is a short alphanumeric string, typically beginning with AIza. If your key does not match that pattern, double-check that you are copying from the correct project and key type in Google AI Studio.

   Best practice

   • Create a dedicated API key for DAVE rather than reusing a key shared with other tools or team members. This makes it straightforward to rotate or revoke DAVE's access independently.
   • Associate the key with a Google Cloud project that has appropriate quota and billing configured. Keys without a billing-enabled project may hit free-tier rate limits quickly in production workflows.
   • Never paste your API key into a workflow prompt, a node label, or any visible text field. Use the DAVE credential vault exclusively.
2. 2

   Navigate to Admin > API Management > Providers

   In your DAVE workspace, navigate to Admin → API Management → Providers. This screen lists every AI provider configured for your tenant and is where you create, edit, and delete provider records.

   Access to this screen is restricted to the Admin role. DAVE ships with six default tenant roles (Admin, Create, Curate, Use, Reporting, and Financial), and only Admin can view or manage providers. If you do not see the Providers option in the menu, ask your workspace Admin to grant you the appropriate role.

   The Providers page displays a card for each configured provider, showing its name, provider type badge, model count, and base URI. If this is a new workspace, the list will be empty.

   Do this

   • Sign in to your DAVE workspace.
   • Open the Admin section from the main navigation.
   • Select API Management, then Providers.
   • Review any existing providers. You can have multiple providers active simultaneously and route different workflow nodes to different providers.
   • Click Add Provider in the top-right corner to open the create form.

   Example

   If your workspace already has an OpenAI or Anthropic provider configured, you will see those cards listed here. Adding Google AI creates a separate provider entry alongside them. Each provider is independent: editing or deleting one does not affect the others.

   Best practice

   • Use a descriptive name that reflects the provider's purpose and environment, for example Google AI Production or Google AI Dev. This name appears in agent configuration dropdowns, so clarity here saves confusion later.
   • Providers are scoped per tenant. If you manage multiple tenants in DAVE, you will need to add a Google AI provider separately in each tenant where you want to use it.
3. 3

   Create the Google AI provider record

   With the create form open, fill in the required fields to register Google AI as a provider in your tenant.

   Select Google AI from the Provider Type dropdown. Selecting this type automatically pre-fills the Base URI field with Google's default API endpoint: https://generativelanguage.googleapis.com/v1beta. You do not need to change this value for a standard Google AI account.

   Paste your Google AI API key into the API Key field. The field is masked by default; click the eye icon to toggle visibility if you need to verify the value before saving. The key is encrypted at rest with AES-256-GCM authenticated encryption and is never returned in plain text through the API once saved.

   Do this

   • In the Name field, enter a descriptive label such as Google AI Production.
   • Set Provider Type to Google AI. The Base URI auto-fills to https://generativelanguage.googleapis.com/v1beta.
   • Paste your Google AI API key into the API Key field.
   • Proceed to configure the model catalog before clicking Create Provider (see Step 4).

   Example

   A completed Google AI provider form will show: Name = Google AI Production, Provider Type = Google AI, Base URI = https://generativelanguage.googleapis.com/v1beta, and a masked API key. The model catalog section below the key field will be empty until you fetch models in the next step.

   Best practice

   • Do not change the pre-filled Base URI unless you have a specific reason to. The default https://generativelanguage.googleapis.com/v1beta is correct for standard Google AI accounts using API keys from Google AI Studio.
   • If you are accessing Google AI through a different endpoint or a compatible proxy, consider whether the OpenAI-Compatible provider type is more appropriate for your setup, since that type requires you to supply the endpoint manually.
4. 4

   Build the model catalog

   Before saving, configure the model catalog: the list of Google AI models that will be available to agents in your workflows. DAVE offers two ways to populate this catalog.

   Fetch from API (recommended): Click the Fetch Models button. DAVE calls the Google AI models endpoint using the API key you just entered and returns the list of models your account can access. Use the search box to filter by name, then check the models you want to include. Use the All or None buttons to bulk-select. A successful fetch also confirms that your API key and base URI are valid before you save the provider.

   JSON mode: If you prefer to specify models manually, click the JSON button and paste a JSON array of model objects. This is useful if you want to restrict the catalog to a specific subset of models regardless of what the API returns, or if the fetch returns models you do not have quota for.

   Once your catalog is configured, click Create Provider to save the record.

   Do this

   • In the model catalog section, click Fetch Models.
   • Wait for DAVE to retrieve the model list from https://generativelanguage.googleapis.com/v1beta.
   • Use the search box to filter models if needed.
   • Check the models you want to include in the catalog. Uncheck any you do not need.
   • Click Create Provider to save.
   • Confirm the new provider card appears in the Providers list with the correct model count.

   Example

   After fetching, you may see a range of Gemini model variants in the list. Select only the models your team will actively use. A focused catalog makes model selection faster when configuring agents and reduces the chance of accidentally targeting a model your account does not have quota for.

   Best practice

   • Always use Fetch from API rather than manually entering model IDs in JSON mode. Fetching avoids typos in model identifiers and ensures you see the latest models available to your account.
   • Keep the catalog lean. Include only the models your workflows actually need. You can always edit the provider later to add more.
   • After saving, click the chevron on the provider card to expand it and verify the model list looks correct before wiring up agents.
   • If the fetch fails with a "Failed to fetch models" error, verify that the API key is correct and that the Google Cloud project associated with the key has the Generative Language API enabled.
5. 5

   Use Google AI in a workflow node

   With the Google AI provider saved and its model catalog populated, it is immediately available to any workflow node that calls an AI model. In DAVE's workflow runtime, nodes that invoke AI models, such as an Agent Interaction node, let you select a provider and a specific model from that provider's catalog.

   Agents are the bridge between workflow nodes and providers. When you configure an agent, you select the Google AI provider you just created and choose a Gemini model from its catalog. The agent uses the provider's stored API key and base URI at runtime. When the node executes, DAVE calls Google AI directly using your key. No request is proxied through DAVE's infrastructure for billing purposes: the call goes from DAVE to Google AI, and the usage appears on your Google Cloud invoice.

   Every provider call made during workflow execution is recorded in DAVE's full audit log, giving you a complete trace of which provider was called, by which agent, in which workflow, and when.

   Do this

   • Navigate to the Agents section of your workspace and create or edit an agent.
   • In the agent configuration, select your new Google AI provider from the provider dropdown.
   • Choose the Gemini model appropriate for the agent's task.
   • Save the agent.
   • Open or create a workflow and add an Agent Interaction node that references this agent.
   • Run a test execution to confirm the node calls Google AI successfully and returns the expected output.
   • Check the audit log to verify the call was recorded correctly.

   Example

   A common pattern is to use a Gemini model for a long-context or multimodal step in a multi-step workflow, while routing a different step to another provider. DAVE's orchestration layer handles the routing: you configure the provider per agent, and the platform manages the rest. Because all providers are centralised in DAVE, rotating your Google AI key in one place updates every agent that references this provider simultaneously.

   Best practice

   • Start with a simple single-node test workflow before wiring Google AI into a complex multi-step pipeline. Confirm the connection, response format, and latency before building on top of it.
   • If an agent fails with an authentication or invalid API key error, navigate to Admin → API Management → Providers, edit the Google AI provider, enter a fresh API key, and click Fetch Models to verify the new key works before saving.
   • If the provider does not appear in the agent configuration dropdown, confirm you are in the correct tenant and that the provider record still exists in Admin → API Management → Providers.
   • If you are building workflows for regulated industries or multi-client environments, review DAVE's SOC 2 and GDPR compliance modes, which govern how execution data, including AI provider responses, is handled and retained across your tenant.

What this guide covers

Before you start

What to check once it is connected

FAQ