Classes AI/ML
GH-600T00 Microsoft Technical Partner Delivered
GH-600T00: Developing in Agentic AI Systems
- 1 days
- 0 upcoming dates
- May qualify for CEU/PDU credit
Upcoming dates
No public dates scheduled right now
This class runs as a private cohort on dates that suit your team, at your site or delivered live online. Tell us roughly when and how many people, and we'll come back with dates and a total.
Private delivery is usually faster and works out better per seat once you're past four or five people.
Request private datesOr leave your details and we will email you the moment a public date is scheduled.
One email when a date is set. Nothing else, and no list.
About this class
GH-600T00: Developing in Agentic AI Systems is not on the public schedule at the moment, and runs as a private cohort on dates you choose. Seats are $695 each over 1 day, courseware included. Tell us your dates and headcount and a quote comes back the same business day. Purchase orders welcome.
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.
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
Who this is for
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
How reserving works. Your card is authorized, not charged. We confirm the seat with the training center, usually within one business day, and take payment only once it is held. If the class turns out to be full we release the authorization and you are not charged.
Request a quote
Tell us how many people and roughly when. We'll come back with dates, seat price, and a total by the end of the next business day.