Skip to the operations

AI

Google Gemini in a decision flow.

4 Google Gemini operations a decision flow can call directly, with the credentials your own contract issued. The response is data the rest of the flow reads, branches on, and keeps in the trace.

Category
AI
Type
Integration
Authentication
API key
Test environment
Production host only

Who they are

Google's family of multimodal large language models.

Gemini is Google DeepMind's line of large language models, sold through the Gemini Developer API and through Google Cloud's Vertex AI. The models read text, images, audio and video, and the larger context windows suit long documents that do not fit elsewhere. Access through the developer API needs only a key, where Vertex AI needs a Google Cloud project.

What a flow can call

4 operations, each one a step you can place on the canvas.

  1. POST/v1beta/models/$data.gemini_model:generateContent

    Ask a model

    One request, one answer. The model id is part of the path — bind it rather than pinning it, so a flow can move from gemini-2.5-flash to a larger model without a new node.

  2. POST/v1beta/models/$data.gemini_model:generateContent

    Extract structured JSON

    The same endpoint constrained to a schema, so the reply parses without a regex.

  3. POST/v1beta/models/$data.gemini_model:countTokens

    Count tokens before sending

    Returns the input token count for a request without running it.

  4. GET/v1beta/models

    List available models

    Model ids, context windows and supported methods as the key can see them.

Where it sits in the decision

AI calls have a natural place in a flow.

A model call is for the judgment a table cannot express — reading a document, summarising a file, weighing a narrative. Because the output is not deterministic, a flow constrains it with a schema and keeps the prompt and the response in the trace, so the reasoning behind a referral stays as inspectable as a rule.

Whatever Google Gemini returns is part of the run, so it is part of the record. When someone asks months later why an applicant was declined, the answer cites what came back at the time rather than re-fetching from a service whose answer has since changed.

  • 01Add Google Gemini as a connection authenticating with an API key.
  • 02Google Gemini has one host for both environments, so guard test runs with your own credentials and limits.
  • 03Place a Connection node and pick an operation — “Ask a model” is usually the first one a flow needs.
  • 04Map the response into the fields your rules read, then test the whole path before it carries live traffic.

Common questions

Using Google Gemini in a flow.

How do I connect Google Gemini to a decision flow?

Add Google Gemini as a connection in your workspace authenticating with an API key, with the credentials your own contract issued — ArboRule calls the provider as you, and never holds a contract on your behalf. Once the connection exists, any flow in the workspace can place a Connection node and choose one of its operations. The credentials live on the connection, not in the flow, so a policy owner can use Google Gemini in a decision without ever seeing the secret.

Can I test Google Gemini without touching production?

Google Gemini exposes one host for both environments, so there is no separate sandbox to point at. Test runs still execute in Sandbox and are recorded separately in decision history, but the call goes to the same place as production — so guard it with your own test credentials, rate limits, or data.

What can a flow call on Google Gemini?

4 operations, including “Ask a model”, “Extract structured JSON”, “Count tokens before sending”. Each one is a step you place on the canvas and map into the fields your rules read, and most flows start with “Ask a model”. The list comes from the same manifest the engine uses to make the call, so this page cannot describe an operation the product does not have.

Where in a decision should Google Gemini be called?

A model call is for the judgment a table cannot express — reading a document, summarising a file, weighing a narrative. Because the output is not deterministic, a flow constrains it with a schema and keeps the prompt and the response in the trace, so the reasoning behind a referral stays as inspectable as a rule.

Also in AI

Ready when you are

Wire Google Gemini into a real decision.

Build the flow in Sandbox, connect your account, and watch the decision pull what it needs before it answers.

Read the docs