Microsoft GitHub Administrator GH-600

Short on study time for the Microsoft GitHub Agentic AI Developer exam? Getcertkey condenses your preparation into 85 focused practice questions for the GH-600 exam, so even a packed schedule leaves room for steady, measurable progress.

Microsoft GH-600 Exam Overview:

Certification Vendor:	Microsoft / GitHub
Exam Name:	Exam GH-600: Developing in Agentic AI Systems
Exam Number:	GH-600
Exam Price:	USD 165
Certificate Validity Period:	2 years
Exam Format:	Performance-based tasks, Interactive items, Scenario-based, Multiple choice
Real Exam Qty:	40–60
Available Languages:	English, Portuguese (Brazil), Japanese, Spanish, Chinese (Simplified), French, German
Exam Duration:	120 minutes
Passing Score:	700
Recommended Training:	GitHub Copilot and Agentic AI Documentation Microsoft Learn - GH-600 Learning Path
Exam Registration:	Pearson VUE Registration Microsoft Learn - Schedule Exam
Sample Questions:
Exam Way:	Online proctored or onsite at test centers
Pre Condition:	No required prerequisites; recommended experience with GitHub, Copilot, SDLC, and coding practices
Official Syllabus URL:	https://learn.microsoft.com/en-us/credentials/certifications/resources/study-guides/gh-600

Microsoft GH-600 Exam Syllabus Topics:

Microsoft GitHub Agentic AI Developer Exam FAQ: What Candidates Ask Most

What is the Microsoft GH-600 exam?

The GH-600 exam is the official Microsoft / GitHub exam behind the GitHub Certified: Agentic AI Developer certification, validating the skills measured by the Microsoft GitHub Agentic AI Developer credential. It sits at the Associate level of the Microsoft / GitHub certification program.

How many questions are on the GH-600 exam, and how much time do I get?

The GH-600 exam contains 40–60 questions to be completed within 120 minutes. Before exam day, divide the available time by the question count to work out a comfortable per-question pace, and mark any item that eats into it so you can return later instead of getting stuck. Timed sessions in the Getcertkey test engines make that pacing automatic — run at least two full-length mock exams under the clock so time pressure never becomes the reason you drop points.

What score do I need to pass the GH-600 exam, and what does it cost?

The passing score for the GH-600 exam is 700, and the official registration fee is USD 165. Retakes are not discounted — every new attempt means paying the full fee again — so it pays to measure yourself before you book. Work through the 85 practice questions on Getcertkey, sit a timed practice test, and schedule your exam only when your scores are consistently comfortable. That simple habit is the cheapest exam strategy there is.

Are there any prerequisites for the GH-600 exam?

No required prerequisites; recommended experience with GitHub, Copilot, SDLC, and coding practices Requirements can change when Microsoft / GitHub revises its certification program, so confirm the current eligibility rules on the official exam page before you register.

How do I register for the GH-600 exam?

You can book the Microsoft GitHub Agentic AI Developer exam through the official registration channels below:

• Microsoft Learn - Schedule Exam
• Pearson VUE Registration

As for delivery, the exam is offered in the following format: Online proctored or onsite at test centers. Choose the option that suits you best when you book your seat.

What official training is recommended for the GH-600 exam?

Microsoft / GitHub recommends the following training resources for the Microsoft GitHub Agentic AI Developer exam:

• Microsoft Learn - GH-600 Learning Path
• GitHub Copilot and Agentic AI Documentation

Official courses build the foundation; the 85 practice questions from Getcertkey then show you how that knowledge is examined, so the two work best together.

Can I try the GH-600 practice questions before I buy?

Yes. Getcertkey provides a free GH-600 PDF demo so you can review the question style and answer quality before purchasing. Every purchase also includes 365 days of free updates — if Microsoft revises the exam during that period, the updated material reaches you at no cost. Once the free-update year ends, you can extend your update service at a 50% discount.

What if I fail the GH-600 exam, and how is my order delivered?

Every Microsoft GitHub Agentic AI Developer purchase on Getcertkey is covered by a 100% money-back guarantee with clear conditions: if you take the corresponding exam within 60 days of your purchase and do not pass, you can claim a full refund by submitting a scanned copy of your exam enrollment slip and your official score report as a PDF within two days of the exam date; claims are processed within seven days of submission. The guarantee does not apply to exams taken within three days of purchase, to material that was downloaded but never used in an exam attempt, or to free products and expired orders, and the candidate name must match the payer name. If you would rather not take a refund, you can instead exchange your purchase for two free exam preparation products of equal value and keep the update service on your original product.

Delivery is instant: your download is sent to your email within one minute of payment, with no limit on how many computers you may install the material on. If nothing arrives within two hours, check your spam folder and contact customer service for help.

What topics are covered in the GH-600 exam?

The Microsoft GitHub Agentic AI Developer exam blueprint is organized into 6 domains. The first three are:

• Prepare agent architecture and SDLC processes — 15–20% of the exam
• Manage memory, state, and execution — 10–15% of the exam
• Implement guardrails and accountability — 10–15% of the exam

For the complete domain-by-domain breakdown, scroll up to the full exam topics outline above and use it to plan how you distribute your study time.

Microsoft GitHub Agentic AI Developer Sample Questions:

Question 1

Case Study 2
Existing Environment
GitHub Environment
The GitHub environment contains the following:
- Three repositories named product-api, billing-service, and infra-terraform.
- Branch protection on the main branch in all repositories that requires at least one pull request review before merging
- GitHub Actions runners used across all workflows
- A GitHub team named SG_Dev that contains developers
- A GitHub team named SG_Review that contains senior engineers and a security team
- A .github/copilot-instructions.md file that includes general coding conventions for all features Agent environment The product-api repository uses a GitHub Copilot coding agent named agent1 that has the following configurations:
- No custom agent profile is defined.
- A Model Context Protocol (MCP) server named MCP1 is deployed to
https://mcp.litwareinc.internal and provides access to internal ticketing and deployment APIs.
MCP1 requires an API key for authentication.
A second Copilot coding agent named agent2 handles changes in infra-terraform and runs in parallel with agent1 when both agents have open assigned issues.
Copilot memory is NOT enabled for the organization.
Problem Statements
Litware identifies the following issues:
- During two recent sessions, agent1 accessed files in billing-service, which is outside the agent's intended scope.
- agent1 makes code changes immediately after receiving a task.
- A developer named Ben, who is on the SG_Dev team, reports that agent1 completed a session with a successful status and opened a pull request, but the pull request contains no file changes.
Other developers report this intermittently as well.
- Both agent1 and agent2 modified shared/config.yaml in a parallel test run, generating conflicting outputs.
agent1 consistently uses raw try-catch blocks for error handling, which violates the defined implementation guidelines of SG_Dev.
Requirements
Planned Changes
Litware plans to make the following changes:
- Ensure that agent1 can access all the tools in the environment.
- Provide product-api with specific instructions to agent1 without affecting Copilot Chat or Copilot code review.
- Configure MCP1 as a tool for agent1 by modifying the product-api repository MCP configuration.
- Ensure that Copilot retains details that it has learned and uses that knowledge for future work.
This must be applied to all licensed members of the organization.
Implementation guidelines
The development team at Litware identifies the following implementation guidelines:
- Agent workflows must be able to run in parallel.
- Application error handling must use the repository ErrorHandler class.
- agent1 and agent2 must run on isolated branches during parallel execution. File-level conflicts must be detected before merges, and both agents must be able to run concurrently.
Security requirements
Litware identifies the following security requirements:
- Only the members of SG_Review must be able to approve agent1 plan outputs.
- All API keys must be stored and accessed securely.
- The developers must NOT be able to self-approve.
Agent configuration

Drag and Drop Question
You need to implement the security requirements for agent1.
Which three actions should you perform in sequence? To answer, move the appropriate actions from the list of actions to the answer area and arrange them in the correct order.

Question 2

You have a GitHub repository.
Developers use the GitHub Copilot CLI and repository-scoped hooks under .github/hooks/*.json.
You need to allow the Copilot CLI to automatically run low-risk Bash commands. The solution must prevent the autonomous execution of high-risk commands, such as sudo, rm -rf /, and curl ... | bash.
What should you do?

A. Configure a sessionStart hook that prints a policy banner.
B. Configure a preToolUse hook that returns permissionDecision: "deny".
C. Add .github/hooks/logs/ to .gitignore.
D. Configure a userPromptSubmitted hook that logs prompts and exits nonzero.

Question 3

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?

A. A .copilotignore file
B. A agents.yml workflow file
C. A copilot-instructions.md file in .github/
D. A CODEOWNERS file

Question 4

A pull request created by the Copilot coding agent needs to be automatically closed if it fails to pass required checks after three retry attempts, per your organization's governance policy. What should you configure?

A. .copilotignore
B. A repository ruleset with agent-specific merge conditions and CI enforcement
C. agents.md
D. /compact

Question 5

During a Copilot CLI session, an MCP tool call fails because the external service requires re- authentication. What is the most likely resolution path?

A. Run /compact to clear context
B. Run /diff to inspect changes
C. Re-authenticate the MCP server connector
D. Switch to plan mode

Solutions: