Explore how agentic AI changes the developer role from only writing code to guiding, reviewing, and validating systems that can take action across the SDLC. Understand GitHub's role as the system of record and control plane for safe, traceable agent workflows.
By the end of this module, you will be able to:
- Define agentic AI in the SDLC and distinguish agents from assistants
- Explain and apply the plan → act → evaluate lifecycle in agent workflows
- Describe how GitHub functions as the system of record and control plane for agent activity
- Identify responsibilities, risks, anti-patterns, and traceability requirements in agent systems
- Apply the contributor model to evaluate agent-generated work
Illustration showing how agentic systems use GitHub workflows such as branches, pull requests, checks, and repository rules to safely build and maintain software.
By the end of this module, you will be able to:
- Map agent responsibilities to SDLC stages and define architectural boundaries
- Define structured agent tasks using inputs, outputs, and success criteria
- Separate planning, reasoning, and execution to create inspectable and reliable workflows
- Implement pull request-based governance using templates, checks, CODEOWNERS, rules, and environments
- Design reliable workflows using outputs, contexts, triggers, and cross-job handoffs
- Operate agent systems safely using observability, tool governance, secrets boundaries, hooks, and reliability patterns
This module introduces how modern software agents interact with tools, APIs, and execution environments to perform meaningful tasks. It covers the role of Model Context Protocol (MCP), GitHub Actions, and agentic workflows in enabling scalable and controlled agent execution. You will also learn how GitHub ensures security and governance through defined execution boundaries and safeguards.
By the end of this module, you will:
- Understand how agents use tools and APIs to perform actions
- Explain the role of MCP servers in extending agent capabilities
- Configure execution environments using GitHub Actions and GitHub Agentic workflows
- Define execution boundaries such as repository, branch, and workflow scope
- Identify limits and protections that govern agent execution, including branch restrictions, pull request review, and environment safeguards

Syllabus

Foundations of Agentic AI in GitHub
- Introduction
- Define agentic AI in the SDLC
- Explain the agent lifecycle - plan, act, evaluate
- Describe GitHub as the system of record and control plane
- Identify responsibilities, risks, anti-patterns, and traceability needs
- Apply the contributor model to agent-generated work
- Knowledge Check
- Summary
Designing Agent Architecture and SDLC Integration
- Introduction
- Map agent responsibilities to the SDLC
- Define inputs, outputs, and success criteria
- Separate planning, reasoning, and execution
- Examples of implementing PR governance with templates, checks, CODEOWNERS, rules, and environment gates
- Build reliable workflows - outputs, contexts, triggers, and cross-job handoffs
- Control and operate agents - observability, tools, MCP, secrets, hooks, and reliability
- Knowledge Check
- Summary
Tooling, MCP, and Agent Execution Environments
- Introduction
- How agents interact with GitHub APIs and workflows
- Model Context Protocol (MCP) servers, registries, and allow lists
- Execution context and boundaries
- Agent execution limits and protections
- Module assessment
- Summary