Skip to Scheduled Dates
Course Overview
This course is designed to build practical skills in developing, deploying, and managing agentic AI systems within GitHub-based software development workflows. The course explores how to integrate AI agents into the software development lifecycle (SDLC), including designing agent architectures, configuring tools and environments, and managing agent memory, state, and execution. Students will learn how to evaluate and optimize agent performance, implement governance and guardrails, and coordinate multi-agent systems to ensure safe, reliable, and efficient outcomes. Through hands-on learning, participants will gain the skills needed to operate, supervise, and govern AI agents in production environments using GitHub as the control plane.
Who Should Attend
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
Course Outline
1 - Foundations of Agentic AI in GitHub
- 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
2 - Designing Agent Architecture and SDLC Integration
- 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
3 - Tooling, MCP, and Agent Execution Environments
- 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
4 - Multi-Agent Systems and Orchestration
- Define multi-agent responsibilities in the SDLC
- Orchestrate agents using GitHub workflows
- Isolate execution - branches, workflows, permissions, and concurrency
- Detect and resolve conflicts using GitHub-native arbitration
- Make the system observable - attribution, evidence, and handoffs
- Operate reliably at scale - diagnose failures and recover safely
5 - Memory, State, and Evaluation
- Implement agent memory strategies
- Persist agent state and manage context drift
- Ensure continuity of agent memory and state across tools and environments
- Define evaluation signals and enforce quality gates
- Analyze agent failures and improve behavior
6 - Governance, guardrails, and operations
- Define risk-based autonomy and action boundaries
- Enforce governance with GitHub controls
- Design human-in-the-loop workflows
- Control agent capabilities using least privilege
- Make actions observable, traceable, and auditable
- Maintain governance and operational reliability