GH-600試験無料問題集「Microsoft GitHub Agentic AI Developer 認定」

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.

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?

解説: (GoShiken メンバーにのみ表示されます)
You have a GitHub repository that uses the GitHub Copilot coding agent.
Your company restricts GitHub Actions secrets.
Developers need the Copilot coding agent to call an internal dependency-scanning API during its run. The API requires an access token.
You need to ensure that the Copilot coding agent can use the token during execution without accessing the repository's Actions secrets and variables. The solution must prevent exposing the token in plaintext.
What should you do?

解説: (GoShiken メンバーにのみ表示されます)
An enterprise administrator wants to audit which repositories have had Copilot coding agent- created pull requests over the last 30 days. Where should the administrator look?

解説: (GoShiken メンバーにのみ表示されます)
You need finer control, selecting specific files and describing precise natural-language changes to apply, rather than letting the agent decide the full scope of changes. Which Copilot Chat mode should you use?

解説: (GoShiken メンバーにのみ表示されます)
You want a reusable, shareable set of instructions that defines a specific persona/workflow (e.g.,
"security reviewer") that developers can invoke on demand in Copilot Chat, rather than instructions applied globally to every session. What should you create?

解説: (GoShiken メンバーにのみ表示されます)
You are architecting an agentic AI system and need the agent's tool-calling behavior to be constrained so it can only call a specific allow-listed set of MCP tools, never arbitrary ones. What should you configure?

解説: (GoShiken メンバーにのみ表示されます)
You have a multi-agent GitHub Actions workflow that uploads review artifacts for each run.
You discover that some workflow run artifacts are being deleted manually.
You need to use your organization's audit log data to identify which user deleted the artifacts.
Which audit log search filter should you use?

解説: (GoShiken メンバーにのみ表示されます)
An agent working through the Copilot coding agent in GitHub Actions needs additional build dependencies installed before it can run tests. Where should you define this setup?

解説: (GoShiken メンバーにのみ表示されます)
After several long agentic sessions, you notice degraded response quality and want the agent to retain a concise summary of prior progress rather than the full raw history, while continuing without interruption. Which approach addresses this?

解説: (GoShiken メンバーにのみ表示されます)