Gemini Enterprise Agent Platform (formerly Vertex AI) is a machine learning (ML) platform that lets you train and deploy ML models and AI applications, and customize large language models (LLMs) for use in your AI-powered applications. When you integrate Gemini Enterprise Agent Platform, you integrate the metadata of ML models from Gemini Enterprise Agent Platform to Collibra Platform. The resulting assets represent the Gemini Enterprise Agent Platform assets.
The Gemini Enterprise Agent Platform integration currently only ingests AI agents hosted on Agent Runtime. This includes ADK agents hosted on Agent Runtime and more generally any agent deployed on Agent Runtime regardless of framework. An AI Agent Version asset is only created for agents deployed using a source-code-based method.
Employee-made agents built with Workflow Builder, Google-made agents such as Core Assistant or Deep Research, Dialogflow agents, or Agent2Agent (A2A) agents that are only registered through the Agent Registry without an underlying Agent Runtime resource are currently out of scope.
For AI agents, the Gemini Enterprise Agent Platform integration also collects operational trust metrics from Google Cloud Monitoring.
-
You can configure Edge connections and capabilities without an active AI Governance license. However, AI Governance must be enabled to harvest AI model and agent metadata, ingest corresponding AI assets in Data Catalog, and access the dashboards and features necessary to visualize and govern your AI landscape.
- We only ingest the latest metrics from Gemini Enterprise Agent Platform models that have been evaluated and added to the model registry in Gemini Enterprise Agent Platform.
- You can integrate Gemini Enterprise Agent Platform only via Edge.
For information about Gemini Enterprise Agent Platform, go to the Gemini Enterprise Agent Platform documentation.
Helpful resources
Check out the A human-centered intro to AI integrations course in Collibra University.