Online Access Free Professional-Agentic-Architect Practice Test
| Exam Code: | Professional-Agentic-Architect |
| Exam Name: | Google Cloud Certified - Professional Agentic Architect |
| Certification Provider: | |
| Free Question Number: | 77 |
| Posted: | Nov 15, 2026 |
Your organization requires a scanner that checks for secrets and API keys to run before Antigravity writes to any file in a repository. You added an Antigravity workspace rule instructing the agent to run the scanner first.
However, you find some commits where the scanner did not run. You need to ensure the scanner runs before every file write, regardless of what the agent considers relevant.
What should you do?
You are designing a secure, multiagent framework on Gemini Enterprise Agent Platform. An administrative assistant agent needs access to internal corporate wikis and external communication APIs to synthesize daily updates and draft emails.
You need to establish a security architecture integrated with Agent Gateway to protect against indirect prompt injections and data exfiltration. You want the framework to scan user input prompts and retrieved message content in real time, while enforcing an explicit authorization boundary for critical, state-modifying operations.
What should you do?
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?
You are deploying an autonomous coding agent on Google Kubernetes Engine (GKE) to run user-requested Python scripts. To isolate untrusted code execution, you enabled GKE Agent Sandbox with gVisor to intercept container system calls in user space. During a security audit, you find that an untrusted Python script generated by a prompt injection attack successfully fetched IAM identity tokens by sending an HTTP request to the link-local instance metadata server at 169.254.169.254.
You need to prevent sandboxed code from exfiltrating metadata tokens while maintaining container kernel isolation.
What should you do?
You are building a custom coding assistant agent with Agent Development Kit (ADK). The agent must recall user preferences, past architectural decisions, and previous debugging steps across completely independent interactive sessions over multiple weeks. You need to complete these tasks without continually growing the LLM context window and inflating inference costs, and you want the simplest solution.
How should you build the agent?