GH-600T00: Developing in Agentic AI Systems
Design, integrate and govern AI agents inside the software development lifecycle with GitHub.
About this course
Design, integrate and govern AI agents inside the software development lifecycle with GitHub. You will cover agent architecture, tooling and MCP, multi-agent orchestration, memory and evaluation, and the guardrails needed to run agents safely in production.
Curriculum
- 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
- 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
- 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
- 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
- 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
- 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
Who it's for
Experienced developers, platform engineers and DevOps leads introducing agents into delivery pipelines.
Before you start
No formal prerequisites. Bring curiosity and a willingness to practise.
Related courses
More in AI & Machine Learning →Accelerated Delivery Using AI
AI & Machine Learning
View course →Accelerating Data Engineering Pipelines
AI & Machine Learning
View course →Agentic Fundamentals for Business Professionals
AI & Machine Learning
View course →AI Agents with Google's ADK Bootcamp: Build with Gemini, Protocols, & AgentOps
AI & Machine Learning
View course →AI Driven Road Management
AI & Machine Learning
View course →AI Ethical Use and Responsibility - Beginner
AI & Machine Learning
View course →Let's plan your next step together.
Tell us the course or certification you have in mind and we'll send the outline, upcoming dates, fees and private-team options.