Google Cloud Professional Agentic Architect practice questions, page 2 of 3, with answer review and explanations.
Question 6
You are developing an enterprise customer support agent in Customer Experience Agent Studio (CX Agent Studio). The agent manages an order cancellation workflow that requires verifying customer identity before invoking an external payment refund tool. During testing, when end users provide 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 each workflow step. What should you do?
Define global instructions in CX Agent Studio’s advanced application settings with broad behavioral constraints to apply to every conversational turn.
Restructure in-console system instructions in CX Agent Studio into XML tags.
Attach a Model Armor security template to the endpoint to sanitize user conversational inputs.
Configure a backward handoff rule on the agent node using a boolean variable check condition to handle transfer errors.
Question 7
You are establishing team-wide engineering guidelines in an Antigravity workspace for a cloud-native Go project. You want the agent to automatically enforce a set of enterprise architecture conventions on every interaction, while providing an on-demand database migration workflow that developers can invoke when needed. You need to structure these customizations using native Antigravity configuration files. What should you do?
Define migration workflows in GEMINI.md rules, and embed architecture directives in a skill folder.
Configure architecture directives and migration workflows as raw shell scripts inside the skills directory.
Define architecture directives in GEMINI.md rules, and create an on-demand migration workflow in a skill folder.
Question 8
You are building a multiagent workflow in Antigravity where a primary coordinator agent delegates code editing and testing tasks to concurrent subagents. During initial execution, subagents edit files in the shared workspace at the same time, causing write conflicts and filling the main chat history with verbose build logs. You want to eliminate file modification conflicts and prevent context rot in the primary coordinator agent. What should you do?
Instantiate subagents programmatically with a canary batch cap of three concurrent workers, and store context logs in BigQuery.
Configure subagents to use inherited workspace contexts for code edits, and deploy a PreToolUse hook to upload context logs to a Cloud Storage bucket. Use the stored context for additional prompts.
Configure subagents to use branched workspace isolation for code edits, and offload build execution to isolated worker context sessions.
Define PreToolUse hooks to restrict subagent file write tools, and route build traces to Cloud Logging. Retrieve the stored logs for additional prompts.
Question 9
You are establishing an automated unit testing pipeline where Antigravity generates and executes test scripts for third-party Python packages. Your organization’s security requirements state that dynamic test suites generated by the LLM must never access local host credentials, private developer files, or unapproved internal network services. You need to configure a secure execution runtime for the coding agent. What should you do?
Configure a .antigravityrules markdown file in the repository instructing the agent to never generate code that reads host files or connects to external domains.
Assign a Google Cloud service account with restricted, least-privilege IAM roles to the pipeline execution host.
Execute agent-generated test scripts inside isolated, containerized execution sandboxes.
Configure a VPC Service Controls perimeter around the pipeline’s execution subnet.
Question 10
You are implementing a custom skill in the Antigravity CLI to automate service deployments. When executing tasks in Agent Mode, the CLI fails to detect the skill and bypasses user confirmation before running deployment commands. You want to enable effective skill discovery globally while ensuring that human approvals are required for high-risk actions. What should you do?
Verify that a SKILL.md file containing valid YAML metadata is present in the ~/.gemini/antigravity-cli/skills/ directory, and execute the Agents CLI without auto-approval flags.
Upload the deployment script to Cloud Deploy as an agent extension, and run the agents-cli setup command with the -- force flag.
Verify that a SKILL.md file containing valid YAML metadata is present in the .agents/skills directory, and execute the Agents CLI without auto-approval flags.
Register the skill as an MCP server inside the .agents/skills/ directory for each deployment, and launch the Agents CLI using the -y flag.