Developing in Agentic AI Systems

Learners should have subject matter expertise in operating, integrating, supervising, and governing AI agents inside production-grade SDLC workflows and development environments, ensuring reliability, safety, and velocity using GitHub as the system of record and control plane. Learners work closely with architects, platform engineers, DevOps engineers, application developers, product managers, and security engineers to develop, deploy, operate, and manage agents that operate within the GitHub platform. Learners should have experience with the software development lifecycle (SDLC), workflows in GitHub and controls, and code quality, security, and review practices. You should also have experience with coding agents including GitHub Copilot, MCP servers and agent customization such as custom instructions, custom agents, tools, and Copilot setup Responsibilities for this role include:

- Operating agent workflows inside the SDLC

- Supervising autonomous behavior with GitHub controls

- Evaluating and tuning agent outputs using scans and artifacts

- Configuring custom agents

- Coordinating multi-agent execution safely

After this course participants should be able to:

• Prepare agent architecture and SDLC processes.
• Implement tool use and environment interaction.
• Manage memory, state, and execution.
• Perform evaluation and tuning of AI agents.
• Orchestrate multi-agent coordination.
• Implement guardrails and accountability for agentic AI systems.

Module 1: Developing in Agentic AI Systems Part 1 of 2

• Foundations of Agentic AI in GitHub
• Designing Agent Architecture and SDLC Integration
• Tooling, MCP, and Agent Execution Environments

Module 2: Developing in agentic AI systems part 2 of 2

• Multi-Agent Systems and Orchestration
• Memory, State, and Evaluation
• Governance, guardrails, and operations

• Understanding of the Software Development Lifecycle (SDLC).
• Hands-on experience with GitHub workflows, repositories, pull requests, and code reviews.
• Familiarity with GitHub Copilot and AI-assisted development.
• Basic knowledge of AI agents, prompt engineering, and agent orchestration concepts.
• Experience with DevOps practices, CI/CD pipelines, and software development environments.
• Understanding of security, governance, and code quality practices within GitHub.

• Developing in Agentic AI Systems M-GH600

Based on the skills covered in GH-600, the following certifications are logical next steps:

• M-AI103 - Develop AI apps and agents on Azure (AI-103)
• M-AI200 - Develop AI cloud solutions on Azure (AI-200)
• M-AZ305 - Design Microsoft Azure Infrastructure Solutions (AZ-305)
• M-AZ400 - Design and Implement Microsoft DevOps solutions (AZ-400)
• M-SC500 - Implement end-to-end security controls for cloud and AI workloads