Skip to main content
Skip to main content

🧠 GH-600 - GitHub Certified: Agentic AI Developer

GH-600 is GitHub's certification for engineers who don't just chat with AI, but actually run agents inside a real software development lifecycle - wiring up tools, managing state, evaluating output, orchestrating multiple agents, and putting guardrails around all of it, with GitHub as the control plane.

If GH-300 was about using GitHub Copilot, GH-600 is about operating and governing the agents that come after it.

This page is the home for a new video series on agentic AI, built on Microsoft Learn's GH-600 material and shown through real work on a real repository rather than slides. Episodes are added here as they're published - bookmark it and check back.

Coming from GH-300?

Start with the GitHub Copilot series (GH-300) for the fundamentals, then come back here for the agentic layer.


📋 Exam at a Glance

Exam codeGH-600
CertificationGitHub Certified: Agentic AI Developer
LevelIntermediate
Duration120 minutes
Passing score700 / 1000
DeliveryProctored, via Pearson VUE
PrerequisitesNone formally required

Assumed experience: the SDLC, GitHub workflows and repository controls, code quality/security/review practices, and real hands-on time with coding agents - GitHub Copilot, MCP servers, and agent customisation such as custom instructions.

note

Exam details can change, especially while a certification is new. Always confirm against the official Microsoft Learn certification page and its study guide before you book.


🎯 Skills Measured

The exam is organised into six domains:

#DomainWeight
1Prepare agent architecture and SDLC processes15-20%
2Implement tool use and environment interaction20-25%
3Manage memory, state and execution10-15%
4Perform evaluation, error analysis and tuning15-20%
5Orchestrate multi-agent coordination15-20%
6Implement guardrails and accountability10-15%

Domain 2 - tool use, MCP servers and environment interaction - carries the heaviest weighting, so that's where the deepest hands-on practice pays off.


🎬 Video Series

1. Chatbots vs Agentic Systems

What changes when AI can act on a task instead of just explaining it? This opener contrasts text-only chatbot responses with goal-directed agent workflows, using a recipe book vs chef analogy that makes the distinction stick: a recipe book hands you instructions, a chef goes and cooks - checking, tasting and adjusting along the way.

From there it gets practical - prompts, tasks, tools, permissions and retries - and ends with a real demo rather than a diagram. I ask a GitHub agent to add a video to this website, correct the title while it's still working, then review the pull request it produced, merge it myself, and check the change live.

Enjoyed this video?

Chapters

TimeTopic
00:00Series introduction and GH-600 learning resources
01:08Three topics in the series
02:03Chatbots vs agentic systems
04:45Text-only chatbot demonstration
05:38Comparing the ChatGPT response
06:26Recipe book vs chef analogy
07:43Prompts, tasks, tools, and retries
10:05Dependency-update example
10:51GitHub demo: asking an agent to update my website
12:36Goals, tool calls, permissions, and iteration
13:34Why human review still matters
15:06Reviewing the PR and correcting the video title
16:27Human merge and deployment
17:39Checking the live website update
Worth sitting with

The most important stretch is 13:34 onwards - why human review still matters. The agent did the work, but a person read the diff, caught a wrong title, and made the call to merge. That review gate is exactly what Domain 6 (guardrails and accountability) is asking about.


More episodes on the way

This series is in progress - agent loops and guardrails are up next.

Subscribe on YouTube to get each episode as it drops.

A question to sit with while you wait: what task would you hand to an AI agent, and what would you personally review before approving it? That second half is the one people skip.


🧭 How to Prepare

  1. Get the distinction straight - chatbot vs agent, as covered in episode 1 above. Most exam scenarios hinge on it.
  2. Use agents for real work. Run GitHub Copilot's agent mode on an actual repository, not a toy project. The exam is scenario-based and rewards people who've hit the real failure modes.
  3. Go deep on MCP. It's the highest-weighted domain. Connect a server, give an agent tools, then watch what happens when a tool call fails.
  4. Practise custom instructions and other agent customisation in a repository you control.
  5. Think about governance, not just capability - permissions, audit trails, review gates, and what an agent should not be allowed to do.
  6. Read the official study guide on Microsoft Learn and map each bullet to something you've actually done.


🤝 Connect & Learn More


GH-600 is where AI stops being an autocomplete and starts being a teammate you're accountable for. This series works through what that actually takes.