Agentic AI Private

Developing in Agentic AI Systems (GH-600T00)

1 day
Agentic AIGitHub

Develop, deploy, and govern agentic AI systems in GitHub workflows, with practical skills in orchestration, evaluation, guardrails, and production operations.

Talk to a Learning ConsultantRequest a Private Class

Register or Request Training

  • Private class for your team
  • Live expert instructor
  • Online or on‑location
  • Customizable agenda
  • Proposal responses same day as request
Request Proposal

Course Overview

Build practical skills for developing, deploying, and managing agentic AI systems in GitHub-based software development workflows. Learn to design agent architectures, configure tools and execution environments, manage memory and state, evaluate performance, coordinate multi-agent systems, and implement effective governance and guardrails.

Through hands-on learning, you will prepare to operate, supervise, and govern reliable AI agents in production environments using GitHub as the system of record and control plane.

Course Benefits

  • Explain agentic AI concepts, lifecycles, responsibilities, and risks within the SDLC.
  • Design agent architectures and integrate agents into GitHub-based development workflows.
  • Configure tools, MCP servers, execution environments, permissions, and protections.
  • Orchestrate multi-agent systems and manage execution conflicts, evidence, and handoffs.
  • Implement strategies for agent memory, state persistence, evaluation, and quality gates.
  • Apply governance, least-privilege controls, human oversight, and operational guardrails.
  • Improve the reliability, traceability, and auditability of production agent workflows.

Delivery Methods

Private Class
Delivered for your team at your site or online.

Microsoft Certified Partner

Webucator is a Microsoft Certified Partner. This class uses official Microsoft courseware and will be delivered by a Microsoft Certified Trainer (MCT).

Microsoft Certified Partner

Course Outline

  1. Foundations of Agentic AI in GitHub
    1. Define agentic AI in the SDLC
    2. Explain the agent lifecycle: plan, act, and evaluate
    3. Describe GitHub as the system of record and control plane
    4. Identify responsibilities, risks, anti-patterns, and traceability needs
    5. Apply the contributor model to agent-generated work
  2. Designing Agent Architecture and SDLC Integration
    1. Map agent responsibilities to the SDLC
    2. Define inputs, outputs, and success criteria
    3. Separate planning, reasoning, and execution
    4. Implement pull request governance with templates, checks, CODEOWNERS, rules, and environment gates
    5. Build reliable workflows with outputs, contexts, triggers, and cross-job handoffs
    6. Control and operate agents using observability, tools, MCP, secrets, hooks, and reliability practices
  3. Tooling, MCP, and Agent Execution Environments
    1. Understand how agents interact with GitHub APIs and workflows
    2. Use Model Context Protocol servers, registries, and allow lists
    3. Define execution context and boundaries
    4. Apply agent execution limits and protections
    5. Module assessment
  4. Multi-Agent Systems and Orchestration
    1. Define multi-agent responsibilities in the SDLC
    2. Orchestrate agents using GitHub workflows
    3. Isolate execution through branches, workflows, permissions, and concurrency controls
    4. Detect and resolve conflicts using GitHub-native arbitration
    5. Make the system observable through attribution, evidence, and handoffs
    6. Diagnose failures and recover safely at scale
  5. Memory, State, and Evaluation
    1. Implement agent memory strategies
    2. Persist agent state and manage context drift
    3. Maintain memory and state across tools and environments
    4. Define evaluation signals and enforce quality gates
    5. Analyze agent failures and improve behavior
  6. Governance, Guardrails, and Operations
    1. Define risk-based autonomy and action boundaries
    2. Enforce governance with GitHub controls
    3. Design human-in-the-loop workflows
    4. Control agent capabilities using least privilege
    5. Make actions observable, traceable, and auditable
    6. Maintain governance and operational reliability

Class Materials

Each student receives a comprehensive set of materials, including course notes and all class examples.

Class Prerequisites

Experience in the following is required for this Agentic AI class:

  • Experience with the software development lifecycle and GitHub workflows and controls
  • Experience with code quality, security, and review practices
  • Experience using coding agents such as GitHub Copilot
  • Experience with MCP servers and agent customization, including custom instructions, custom agents, tools, and Copilot setup

Have questions about this course?

We can help with curriculum details, delivery options, pricing, or anything else. Reach out and we’ll point you in the right direction.

Talk to a Learning Consultant