Professional-Agentic-Architect 試験問題を無料オンラインアクセス

You are deploying an agent on Gemini Enterprise Agent Platform in Project-A, a dedicated runtime Google Cloud project. The agent needs to retrieve database API credentials from Secret Manager in Project-B, a centralized governance project, and query an Agent Search data store also hosted in Project-B. You are using Agent Identity to govern the agent's permissions across projects. You need to grant the minimum required cross-project IAM access while following the principle of least privilege.
What should you do?
Choose two

• A.Grant the roles/discoveryengine.viewer IAM role to the agent's identity scoped to the target Agent Search data store resource in Project-B.
• B.Grant the roles/discoveryengine.editor IAM role to Project-A's agent identity at the Project-B project level.
• C.Grant the roles/secretmanager.secretAccessor IAM role to the agent's identity scoped to the database resource in Project-B.
• D.Grant the roles/secretmanager.user IAM role to the agent's identity at the Project-B project level.
• E.Grant the roles/iam.serviceAccountTokenCreator IAM role to Project-B's agent identity to allow cross- project impersonation.

You are troubleshooting a hierarchical multiagent architecture built with Agent Development Kit (ADK), in which a primary orchestrator delegates complex search tasks to specialized subagents. Execution traces show that subagents append their full tool execution histories to the orchestrator's context window across multiturn exchanges, causing rapid context window bloat, agent drift, and severe tool invocation latency. You need to isolate subagent execution history and prevent context pollution in the orchestrator.
What should you do?

• A.Increase the maximum iterations limit on the orchestrator's looping agent definition, and configure Cloud Trace sampling to automatically drop duplicate tool payload traces.
• B.Configure a Pub/Sub topic to decouple subagent events from the orchestrator, and configure the orchestrator agent in Agent Runtime to prevent transferring control back to a parent agent.
• C.Deploy subagents inside a sequential pipeline, and enable summarization compaction on the orchestrator's Cloud Storage log bucket in Agent Designer.
• D.Wrap subagents using agent tool encapsulation, configure the subagent LLM settings to exclude previous conversation contents, and persist subagent findings to the session state.

You are developing an enterprise customer support agent in Customer Experience Agent Studio (CX Agent Studio). The agent handles an order cancellation workflow that requires customer identity verification before invoking an external payment refund tool. During testing, when end users submit complex, multi-sentence requests, the agent frequently skips the intermediate identity verification step and calls the refund tool prematurely.
You need to configure the agent's behavior to enforce strict, sequential execution of every workflow step.
What should you do?

• A.Define global instructions in CX Agent Studio's advanced application settings with broad behavioral constraints to apply to every conversational turn.
• B.Attach a Model Armor security template to the endpoint to sanitize user conversational inputs.
• C.Restructure in-console system instructions in CX Agent Studio into XML tags.
• D.Configure a backward handoff rule on the agent node using a boolean variable check condition to handle transfer errors.

You are the lead architect at an organization where multiple engineering teams are building conversational agents. The teams frequently need their agents to query operational telemetry in BigQuery and inspect Cloud Logging logs. Currently, teams duplicate effort by writing custom API wrapper scripts and separate credential management logic for each agent tool.
You need to establish an enterprise-wide tool integration architecture that provides ready-to-use cloud capability connectors and a shared governance directory for team capabilities, without writing bespoke wrapper code.
What should you do?

• A.Configure Dialogflow conversational fulfillment webhooks to route all agent capability requests through a central proxy service.
• B.Configure Agent Platform Feature Store to store key-value client profile attributes, and execute a custom feature retrieval API call during agent prompt construction to inject historical facts.
• C.Deploy serverless Cloud Run functions for each cloud service API, and configure direct HTTP webhooks inside each agent prompt.
• D.Connect the agents to Google Cloud MCP servers, and register shared tools in Agent Registry.

You are configuring enterprise agents that must dynamically discover and invoke capabilities across managed databases, third-party SaaS tools, and Google Cloud services. Your architecture hosts custom MCP servers on Cloud Run alongside pre-built Google Cloud MCP servers. Your operations team requires a centralized catalog to govern access controls, register JSON tool specifications, and manage IAM identities across all remote HTTP transport endpoints.
You need to maximize operational efficiency and maintain strict governance by establishing a single point of discovery and access control for both native and custom agent capabilities.
What should you do?

• A.Register custom Cloud Run MCP servers as Service resources within Agent Registry, upload their JSON tool specifications, and enable built-in Google Cloud MCP servers to centralize agent capability discovery and IAM access governance.
• B.Store local client configuration files containing remote HTTP endpoints in Secret Manager, and mount them across agent execution environments to handle tool discovery and endpoint authentication.
• C.Configure custom MCP servers on Cloud Run, and grant granular IAM roles to extension service accounts to manage agent access controls within defined VPC Service Controls perimeters.
• D.Deploy OpenAPI specifications for custom Cloud Run MCP servers using Cloud Endpoints, and register these endpoints in Service Directory to enable dynamic agent service discovery and endpoint- level IAM security.