support@Free-Braindumps.com
Register Login
Cisco
CompTIA
ISC
EC-Council
EXIN
Fortinet
ITIL
Juniper
Microsoft
VMware
Avaya
SAP
Google
NVIDIA
Salesforce
Amazon
Palo Alto Networks
ISC2
Splunk
ServiceNow
All Vendors
  1. Home
  2. Exams
  3. Microsoft
  4. GH-600

Microsoft GH-600 Exam Prep
Developing in Agentic AI Systems (Page 3 )

Updated On: 31-Aug-2026
Page 2 of 9
PDF with 58 Questions
View Related Case Study

HOTSPOT (Drag and Drop is not supported)
You need to implement agent2 to meet the technical requirements.
How should you complete the YAML configuration? 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.
Hot Area:

  1. See Explanation section for answer.

Answer(s): A

Explanation:


Box 1: 'search', Search allows the agent to look for specific keywords, classes, or patterns across your repository to understand the current structure and code requirements.
Box 2: 'read' Read grants the agent read-only permission to examine the full contents of the codebase files without having the capability to alter them.


Reference:

https://github.com/github/copilot-cli/issues/1663



View Related Case Study

Before App1 is upgraded, you need to verify each individual upgrade step and whether all tests have passed.
Which file should you use?

  1. assessment.md
  2. plan.md
  3. agent.md
  4. tasks.md

Answer(s): A

Explanation:

To analyze a legacy application using GitHub Copilot modernization agents before executing a .NET 10 upgrade, you must use the assessment.md file
Scenario: Contoso has a second repository named repo2 that contains a legacy .NET application named App1 built by using .NET 6. repo2 has a multi-agent workflow for modernization tasks.
Technical Requirements App1 must be upgraded to .NET 10. A previous upgrade attempt was started by using the Copilot modernization agent, but the attempt was never finalized. You plan to retry the upgrade. You must first analyze App1 by using AI, and then generate a report that contains breaking changes and deprecated patterns before retrying the upgrade.


Reference:

https://learn.microsoft.com/en-us/dotnet/core/porting/github-copilot-app-modernization/overview



DRAG DROP (Drag and Drop is not supported)
You have a GitHub repository that has a GitHub Actions workflow. The workflow runs an AI agent.
You need to ensure that the default GITHUB_TOKEN permissions are read-only, and write access is granted to only the job that performs repository write operations. The workflow must be able to create and approve pull requests only when explicitly enabled.
How should you complete the workflow? 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.
Select and Place:

  1. See Explanation section for answer.

Answer(s): A

Explanation:




How should you complete the workflow?
Box 1: contents: read Set Global Read-Only Permissions To enforce the principle of least privilege, the top-level permissions block must strip all default write capabilities from the GITHUB_TOKEN. Setting contents: read allows the workflow to fetch the code but prevents any accidental repository modifications.
Box 2: contents: write Grant Job-Level Write Access
Only the specific job responsible for modifying the repository should receive write access. The update_artifacts job requires permission to push code modifications back to the repository.
Box 3: pull-requests: write To successfully create and approve pull requests, you must explicitly enable this capability in your GitHub repository settings:


Reference:

https://docs.github.com/en/organizations/managing-organization-settings/disabling-or-limiting-github-actions-for-your-organization



DRAG DROP (Drag and Drop is not supported)
You have a GitHub repository that uses the GitHub Copilot coding agent to resolve issues and create draft pull requests. The repository uses GitHub Actions for CI, and reviewers rely on pull request timelines and workflow artifacts to understand what the agent did.
During long-running agent tasks, the reviewers lose track of decisions and validation steps, which causes repeated questions and reworks when context drifts between iterations.
You need to persist task progress and decisions as durable artifacts and ensure that the reviewers can verify what the agent did during and after execution by using GitHub as the system of record.
What should you do for each requirement? To answer, drag the appropriate actions to the correct requirements. Each action 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.
Select and Place:

  1. See Explanation section for answer.

Answer(s): A

Explanation:




Box 1: Use the upload-artifact action and configure artifact retention in the CI workflow To meet this requirement you should use the actions/upload-artifact action and configure the retention-days property in your GitHub Actions CI workflow.
By default, GitHub retains workflow artifacts for a maximum of 90 days for public and private repositories (customizable down to 1 day). Utilizing these configurations ensures that human reviewers can download and inspect the agent's background outputs long after the initial execution concludes.
Box 2: Assign an issue and wait for the agent to view. The best action is to assign an issue and wait for the agent to view.
Assigning a GitHub issue to the Copilot coding agent triggers it to autonomously start working on the background task.
While investigating code and implementing the required fixes, it provides real-time, human-reviewable progress updates directly within the issue or pull request timeline (such as showing a "Copilot has started work" event, or tracking its steps inside the agent workflow). This completely satisfies the requirement for ongoing, transparent signaling for reviewers.
Box 3: Select View session to stream live agent logs You should select "View session" (or navigate to the Agents tab) on GitHub to stream live agent logs.
When using the GitHub Copilot cloud agent asynchronously to resolve issues and generate draft pull requests, the process occurs entirely in a GitHub-hosted background environment.
While automated status summaries eventually populate the pull request timeline, real-time auditing during an active run requires looking directly at the active session stream.


Reference:

https://docs.github.com/en/organizations/managing-organization-settings/configuring-the-retention-period-for-github-actions-artifacts-and-logs-in-your-organization https://docs.github.com/en/copilot/how-tos/use-copilot-agents/cloud-agent/troubleshoot-cloud-agent



DRAG DROP (Drag and Drop is not supported)
You have a GitHub Enterprise Cloud Organization that uses the GitHub Copilot coding agent to resolve issues asynchronously.
When an issue is assigned to GitHub Copilot, the agent creates a draft pull request, but your team cannot always tell whether the agent is actively working, has completed its session, or is awaiting workflow approval.
Which execution context does each signal indicate? To answer, drag the appropriate context to the correct signals. Each signal 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.
Select and Place:

  1. See Explanation section for answer.

Answer(s): A

Explanation:




Box 1: The agent acknowledges the assignment and will create the draft pull request.
When an issue is assigned to the GitHub Copilot coding agent, the eyes emoji reaction indicates that the agent has acknowledged the task and is actively starting work in the background.
Box 2: The agent session is actively running and generating live logs. The signal indicating that "the pull request timeline shows Copilot started work" means that the agent session is actively running and generating live logs.
When a pull request timeline shows that Copilot started work, it indicates that the execution context is actively working.
Actively working: Indicated when the pull request timeline explicitly logs that Copilot started work or updates the PR body with a list of in-progress sub-tasks.
Box 3: A human must manually approve and run the workflow.
When a draft pull request exists but GitHub Actions checks are not running, it indicates that the execution context is awaiting workflow approval.


Reference:

https://docs.github.com/en/copilot/how-tos/copilot-on-github/use-copilot-agents/kick-off-a-task



You have a repository that uses the GitHub Copilot coding agent and supports hooks stored under .github/ hooks.
You need a Shell command to run automatically whenever an agent execution fails.
Which type of hook should you use?

  1. postToolUse
  2. sessionEnd
  3. errorOccurred
  4. agentStop

Answer(s): C

Explanation:

To automatically run a Shell command whenever a GitHub Copilot coding agent execution fails, you should use the errorOccurred (also referred to as onErrorOccurred) hook.
Hook Mechanics & ConfigurationGitHub Copilot agent hooks are defined using JSON configuration files placed in the .github/hooks/ directory.
Event Type: errorOccurred (or onErrorOccurred depending on your specific environment and version).
Execution Behavior: When an execution fails, the agent stops, triggers this hook, and passes detailed error metrics and session context as a JSON payload to the script's standard input (stdin).
Incorrect: [Not B] sessionEnd - Agent session completes or is terminated.


Reference:

https://awesome-copilot.github.com/learning-hub/automating-with-hooks/



You are about to start a complex refactoring task in the GitHub Copilot CLI.
Before Copilot makes any changes, you need to review and agree on the approach.
What should you do first?

  1. Start the Copilot CLI and specify the --agent=Task parameter.
  2. Start the Copilot CLI and specify the --allow-all parameter.
  3. From the Copilot CLI, switch to plan mode.
  4. From the Copilot CLI, run the /compact command.

Answer(s): C

Explanation:

The first action you should take is to switch to Agent mode or use the Plan agent to review, edit, and approve a detailed step-by-step Markdown plan before any code is modified.
Use the Plan Agent: If available in your environment, trigger the plan phase so Copilot scans your codebase in a read-only state to outline its entire approach first.
Review the Proposed Plan: Carefully inspect the resulting Markdown structure to catch any architectural issues or wrong directions before the "doing" phase begins.
Utilize edit Mode Intentionally: Alternatively, if you prefer granular control over file adjustments rather than a fully autonomous agent workflow, opt for edit mode. This allows you to specifically select the target files and describe the natural language updates manually.


Reference:

https://aidevme.com/think-before-you-build-github-copilots-plan-agent-in-visual-studio-structured-ai-assisted-development/



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?

  1. Enable Copilot memory.
  2. Update the Model Context Protocol (MCP) server rate limits.
  3. Add a clear description of the problem to the issue.
  4. Allocate more resources to copilot-setup-steps.yml.

Answer(s): C

Explanation:

Adding a clear description of the problem to the issue will directly remedy this problem.Coding agents like GitHub Copilot rely heavily on the context, details, and constraints provided in the issue to understand what needs to be fixed. A one-line description like "Fix the login bug" is too vague, leading to guesswork, incorrect scope, and incomplete code changes.
Defines Scope: Explicitly stating what is broken prevents the agent from changing unrelated files.
Identifies the Root Cause: Providing error logs or steps to reproduce guides the agent to the exact lines of code that need fixing.
Sets Expectations: Specifying the expected correct behavior ensures the agent generates all the necessary changes, preventing missing code.


Reference:

https://docs.github.com/en/copilot/how-tos/use-copilot-agents/cloud-agent/troubleshoot-cloud-agent



  PDF
Viewing page 3 of 9
Viewing questions 17 - 24 out of 58 questions


Post your Comments and Discuss Microsoft GH-600 exam prep with other Community members:

AI Tutor AI Tutor 👋 I’m here to help!