AI & Machine Learning
Vertex AI AI agent integration
Vertex AI integration for predictions, models, endpoints, datasets, training pipelines, batch predictions, and custom jobs
Category
AI & Machine Learning
Authentication
OAuth 2.0
Protocol
MCP-compatible
What you can do with the Vertex AI integration
Give your AI agents authenticated access to Vertex AI so they can read, act, and update records on your behalf — inside a governed, observable workflow.
- Let agents read data from Vertex AI as part of a workflow.
- Let agents take typed actions inside Vertex AI with allow/deny policies.
- Combine Vertex AI with other tools to automate cross-system workflows.
- Audit every tool call in Monitor — agent, action, input, response, latency, cost.
How to connect Vertex AI
Connect via a one-click OAuth flow. Dezifi never stores your password; tokens are scoped and refreshable.
- 1
Open Integrations in your workspace
Navigate to Integrations from the left sidebar. The catalog opens to all available tools. - 2
Find Vertex AI
Search the catalog or filter to the AI & Machine Learning category. Click the Vertex AI card. - 3
Connect your account
Click Connect. Connect via a one-click OAuth flow. Dezifi never stores your password; tokens are scoped and refreshable. - 4
Test the connection
Run the built-in connection test. Dezifi calls a low-impact endpoint and confirms the credential works. - 5
Grant access to an agent
Open an agent in the builder, go to Tool Selection, check Vertex AI, save. The agent can now invoke Vertex AI actions during runs.
Governance and safety
Vertex AI is a tool like any other in Dezifi — its actions are governed by your policies, inspected by guardrails, and recorded in every run trace.
- Tool allow / deny — restrict which agents can invoke which actions.
- Approval gates — require human sign-off before destructive operations.
- Rate limits — cap how often an agent can call the integration.
- Audit trail — every call, input, response, and identity is logged.
Frequently asked questions
- How do I connect Vertex AI to Dezifi?
- Open Integrations in your workspace, search for Vertex AI, click Connect, and follow the oauth 2.0 flow. Once connected, the integration becomes available as a tool for any agent.
- Which AI agents can use the Vertex AI integration?
- Any agent in your Dezifi workspace can be granted access to Vertex AI. You scope which agents see it via tool allow-lists on policies.
- Is the Vertex AI integration secure?
- Yes. Credentials are encrypted at rest, scoped to your workspace, and never shared across tenants. Every tool call is logged in the run trace.
- Can I limit what the agent can do in Vertex AI?
- Yes. Policies let you allow or deny specific actions and require human approval for high-risk operations. The principle of least privilege is enforced at runtime.
Other AI & Machine Learning integrations
Integration
Anthropic
Anthropic integration for messages, models, token counting, and batch operations
Integration
Azure OpenAI
Azure OpenAI integration for completions, chat, embeddings, deployments, models, images, transcription, and translation
Integration
Hugging Face
Hugging Face integration for models, datasets, spaces, inference, repos, and user operations
Integration
OpenAI
OpenAI integration for completions, chat, embeddings, models, images, files, fine-tuning, moderation, and assistants