Prepare and test your skills
Prepare and test your skills
Free sample question, answered and explained below. The Professional Cloud Architect practice bank has 2,335 more like it. Try 10 free: instant score, no account.
An enterprise is designing an automated customer support AI agent using Vertex AI Agent Builder and the Agent Development Kit (ADK) in Python. The agent must retrieve policy documents stored in Cloud Storage and structured product catalogs in BigQuery to provide grounded, contextually accurate responses.
The cloud architecture must satisfy the following technical requirements:
Which architecture and configuration should you recommend?
Deploying to Vertex AI Agent Engine without configuring identity_type=AGENT_IDENTITY defaults to standard service account authentication. This configuration relies on existing IAM service accounts rather than provisioning a unique SPIFFE principal identifier for the agent instance.
storage.legacyBucketReader), and standard best practices mandate resource-specific fine-grained IAM roles (like roles/storage.objectViewer or roles/bigquery.dataViewer).You were supporting a legacy infrastructure-as-code automation pipeline that has not yet adopted system-attested agent identities and relies strictly on existing pre-provisioned service accounts.
When creating an Agent Engine instance, specifying identity_type=types.IdentityType.AGENT_IDENTITY ensures backward compatibility is bypassed in favor of modern, per-agent SPIFFE-attested principals.
Google Kubernetes Engine (GKE) is a managed Kubernetes service designed for containerized workloads requiring fine-grained control over clusters, nodes, networking, and custom accelerators.
The workload required deep container customization, complex stateful custom sidecars, fine-grained infrastructure networking, or hosting open-source self-hosted model weights directly within a private cluster.
While GKE is a valid runtime for complex containerized systems, Google Cloud recommends Vertex AI Agent Engine for pure Python agent applications seeking serverless, fully managed operations.
Cloud Run is a fully managed serverless compute platform that runs containers directly on Google's scalable infrastructure. In this pattern, the developer manages external storage solutions such as Cloud SQL for session persistence and uses API keys for authentication.
You were building a polyglot, containerized web service or microservice that does not use Python agent frameworks and already uses Cloud SQL for relational business data.
Vertex AI Agent Engine is itself built on top of Cloud Run infrastructure, but it layers managed agent sessions, sandbox execution, and native agent identity on top to simplify agent deployments.
Vertex AI Agent Engine is a fully managed runtime within Vertex AI Agent Builder tailored for deploying, operating, and scaling Python-based agentic applications without managing underlying infrastructure. When paired with agent identity, the agent receives a unique, system-attested principal identifier based on SPIFFE standards, allowing granular Identity and Access Management (IAM) governance directly tied to the agent resource lifecycle.
identity_type=AGENT_IDENTITY creates a per-agent principal (principal://...), permitting fine-grained IAM allow policies on Cloud Storage buckets and BigQuery datasets instead of sharing broad service account credentials.This architecture leverages the purpose-built Vertex AI Agent Engine platform components to minimize development and infrastructure overhead while meeting all enterprise security and grounding requirements natively.
Answer them yourself and get your score the moment you finish. No account needed.
Full access includes
Keep the momentum going with these hand-picked practice scenarios
Last updated Validated