最新的Microsoft Developing in Agentic AI Systems - GH-600免費考試真題
In Microsoft Visual Studio Code, you use GitHub Copilot agent mode for a repository. The GitHub Model Context Protocol (MCP) server is enabled.
Your team maintains an internal orchestrator script that creates independent Copilot SDK sessions to process operational events from webhooks.
You discover that the agent sometimes mixes context between unrelated webhook deliveries. Additionally, in some cases, the agent starts running tools before a human reviews the proposed steps.
You need to ensure that the script meets the following business requirements:
Planning must be kept separate from executing.
Each plan must be captured without calling any tools.
Each webhook event must create a new independent session.
Once the plan is complete, tool calls must be enabled within the same event-specific session for follow-up.
Your team maintains an internal orchestrator script that creates independent Copilot SDK sessions to process operational events from webhooks.
You discover that the agent sometimes mixes context between unrelated webhook deliveries. Additionally, in some cases, the agent starts running tools before a human reviews the proposed steps.
You need to ensure that the script meets the following business requirements:
Planning must be kept separate from executing.
Each plan must be captured without calling any tools.
Each webhook event must create a new independent session.
Once the plan is complete, tool calls must be enabled within the same event-specific session for follow-up.
正確答案:
You have a GitHub Copilot coding agent named Orchestrator that runs a multi-phase workflow by using the following subagents:
Explorer gathers context by using read-only tools.
Modifier applies focused edits.
You are adding a new agent named Summarizer that generates a concise summary after modifications are complete. Summarizer includes the following YAML frontmatter:
---
name: Summarizer
description: Produce a concise summary of recent changes
tools: ['fetch']
user-invocable: false
disable-model-invocation: true
---
The Orchestrator agent lists all three agents in its agents property.
After adding the Summarizer agent, Orchestrator successfully runs Explorer and Modifier but fails to run Summarizer.
What is a possible cause of the failure?
Explorer gathers context by using read-only tools.
Modifier applies focused edits.
You are adding a new agent named Summarizer that generates a concise summary after modifications are complete. Summarizer includes the following YAML frontmatter:
---
name: Summarizer
description: Produce a concise summary of recent changes
tools: ['fetch']
user-invocable: false
disable-model-invocation: true
---
The Orchestrator agent lists all three agents in its agents property.
After adding the Summarizer agent, Orchestrator successfully runs Explorer and Modifier but fails to run Summarizer.
What is a possible cause of the failure?
正確答案: A
說明：（僅 Fast2test 成員可見）
You have a GitHub repository that uses the GitHub Copilot coding agent to run agent plans for assigned issues.
You discover that some issues contain ambiguous implementation steps.
You need to reduce the likelihood that Copilot executes plans based on ambiguous implementation steps.
What should you do?
You discover that some issues contain ambiguous implementation steps.
You need to reduce the likelihood that Copilot executes plans based on ambiguous implementation steps.
What should you do?
正確答案: C
說明：（僅 Fast2test 成員可見）
You have a GitHub Enterprise organization that uses GitHub Copilot.
You discover that GitHub Copilot Chat responses in Microsoft Visual Studio Code are influenced by earlier, unrelated troubleshooting prompts from the same conversation.
You need to ensure that the Copilot Chat conversation context is limited to information relevant to the current work item. The solution must minimize effort.
What should you do? To answer, select the appropriate options in the answer area.
You discover that GitHub Copilot Chat responses in Microsoft Visual Studio Code are influenced by earlier, unrelated troubleshooting prompts from the same conversation.
You need to ensure that the Copilot Chat conversation context is limited to information relevant to the current work item. The solution must minimize effort.
What should you do? To answer, select the appropriate options in the answer area.
正確答案:
You have a GitHub Enterprise Cloud organization that has Copilot agents enabled.
You discover activity in a repository.
You need to identify whether the activity was initiated by an agent.
Which two audit log fields can you use? Each correct answer presents a complete solution.
You discover activity in a repository.
You need to identify whether the activity was initiated by an agent.
Which two audit log fields can you use? Each correct answer presents a complete solution.
正確答案: B,D
A team assigns an issue to the GitHub Copilot coding agent by using the following one-line description: Fix the login bug.
Copilot creates a pull request, but the pull request is missing changes and has an incorrect scope.
How should you resolve the issue?
Copilot creates a pull request, but the pull request is missing changes and has an incorrect scope.
How should you resolve the issue?
正確答案: C
說明：（僅 Fast2test 成員可見）
You have a GitHub Enterprise Cloud organization that uses GitHub Actions for CI/CD.
You plan to enable an agent to update and deploy workflows that access production environment secrets.
You need to select an autonomy level for a compliance-sensitive workflow.
Which autonomy level should you select?
You plan to enable an agent to update and deploy workflows that access production environment secrets.
You need to select an autonomy level for a compliance-sensitive workflow.
Which autonomy level should you select?
正確答案: D
說明：（僅 Fast2test 成員可見）
You have a GitHub Enterprise Cloud organization that uses a custom coding agent to run GitHub Actions workflows that create branches, open pull requests, and merge changes after required checks pass.
You need to log all agent-initiated actions and ensure that the logs are retained for two years.
What should you do?
You need to log all agent-initiated actions and ensure that the logs are retained for two years.
What should you do?
正確答案: C
說明：（僅 Fast2test 成員可見）
You have a GitHub Copilot Enterprise subscription. Developers use Microsoft Visual Studio Code and GitHub Copilot.
The developers want to share a custom agent that can review code changes but cannot modify files.
You need to prevent the agent from modifying repository content and appearing in the agents dropdown.
How should you configure the YAML frontmatter for the agent? To answer, drag the appropriate values to the correct targets. Each value may be used once, more than once, or not at all. You may need to drag the split bar between panes or scroll to view content.
NOTE: Each correct selection is worth one point.
The developers want to share a custom agent that can review code changes but cannot modify files.
You need to prevent the agent from modifying repository content and appearing in the agents dropdown.
How should you configure the YAML frontmatter for the agent? To answer, drag the appropriate values to the correct targets. Each value may be used once, more than once, or not at all. You may need to drag the split bar between panes or scroll to view content.
NOTE: Each correct selection is worth one point.
正確答案:
You want the GitHub Copilot coding agent to follow project-specific conventions (coding style, testing requirements, folder structure) on every task it performs in a repository. What should you create?
正確答案: C
說明：（僅 Fast2test 成員可見）