Google Vertex Agent
End-to-end walkthrough for onboarding a Google Vertex Agent via the Trusted Agent Huddle to the gallery using the AI Refinery runtime.
This walkthrough shows how to add the Google Vertex Agent via the Trusted Agent Huddle, upload its runtime definition, configure credentials, and run validation queries inside the Agent Gallery.
1. Create the Google Vertex Agent
From the Agent Gallery toolbar select Add Agent, pick the owning organisation, and fill out the metadata (identifier, display name, description, licence, and type) for the Google Vertex Agent.
Click Create Agent to provision the new entry and advance to its overview page.
2. Upload the runtime YAML
Remember to give your service account the right IAM roles
Follow the documentation on the Creating a Google Vertex Agent and configure the service account with sufficient permissions. Export your creds.json.
Use Edit → Runtime, confirm the runtime type matches your Google Vertex integration, and upload exampl-trends.yaml with the agent definition below. Configure the resource name accordingly.
orchestrator:
agent_list:
- agent_name: "Google Trends Agent"
utility_agents:
- agent_class: GoogleAgent
agent_name: "Google Trends Agent"
agent_description: "The Google Trends Agent uses the Google Search tool to find trending terms from Google Trends website."
config:
resource_name: "projects/my_project_id/locations/my_project_location/resources/my_resource_type/ my_resource_id" # Required: The resource name of the agent in the Google Cloud Platform
contexts: # Optional: Additional context that may be provided to the agent
- "date"
- "chat_history"
You should see in the build status that the runtime is successfully uploaded.
3. Register configuration values
Open the Config tab, choose Add Configuration, and register each Google Vertex environment variable referenced in the YAML. Capture the JSON credentials exactly as provided by your Google Cloud service account.
| Environment Variable | Type | Required | Description |
|---|---|---|---|
API_KEY | String | Yes | Your AI Refinery API key. |
GOOGLE_APPLICATION_CREDENTIALS | Json | Yes | Google Cloud service account credentials exported from GCP. |
These variables will be requested before each run.
4. Launch a validation run
Return to the agent overview and select Run. Choose the hardware preset, populate the configuration fields with your Google Vertex credentials (upload the creds.json), and run the agent.
5. Issue starter queries and wrap up
Use the chat input to send starter questions that confirm the Vertex AI integration responds correctly—for example, ask Can you list some recent trending news headlines? to test the trends agent. When validation is complete, shut down the run to release compute resources.