Skip to content
GitHub Copilot Train-the-Trainer
Agentic Development

Track: Agentic Development

Target Audience: Teams adopting agentic AI workflows Duration: 36 hours (12 sessions × 3 hrs) Difficulty: Beginner → Advanced Recommended Delivery: 4–6 days (2–3 sessions per day)


Description

The comprehensive path from Copilot fundamentals through full agentic workflows. This track covers everything from basic suggestions to building custom agents, MCP servers, agent skills, and cloud-based autonomous coding. Designed for teams that want to adopt the agent paradigm — where AI doesn't just suggest, it plans, executes, and iterates autonomously.

Prerequisites

  • Solid software development experience (1+ years)
  • GitHub Copilot Enterprise Cloud access; verify the customer’s enabled features before the lab
  • VS Code installed with GitHub Copilot extension
  • Git proficiency (branching, PRs, merging)
  • Node.js or Python installed (for MCP server development in Sessions 10–12)

Sessions

Order Session # Title Difficulty Duration
1 01 Introduction to GitHub Copilot Beginner 3 hrs
2 02 Copilot Chat & Inline Suggestions Beginner 3 hrs
3 03 Prompt Engineering Fundamentals Beginner 3 hrs
4 04 GitHub Copilot in the CLI Intermediate 3 hrs
5 05 Agent Mode in the IDE Intermediate 3 hrs
6 06 Copilot Spaces & Context Management Intermediate 3 hrs
7 07 Copilot for Code Review & Pull Requests Intermediate 3 hrs
8 08 Copilot App, Plugins & Canvas Extensions Advanced 3 hrs
9 09 Copilot Cloud Agent Advanced 3 hrs
10 10 MCP Servers & Custom Tool Integration Advanced 3 hrs
11 11 Custom Agents & Agent Profiles Advanced 3 hrs
12 12 Agent Skills & the Copilot Ecosystem Advanced 3 hrs

4-Day Intensive

Day Sessions Focus
Day 1 Sessions 01, 02, 03 Foundations
Day 2 Sessions 04, 05, 06 Intermediate workflows
Day 3 Sessions 07, 08, 09 App canvases + cloud agent
Day 4 Sessions 10, 11, 12 Full agentic stack

6-Day Standard

Day Sessions Focus
Day 1 Sessions 01, 02 Setup and Chat
Day 2 Sessions 03, 04 Prompting + CLI
Day 3 Sessions 05, 06 Agent mode + context
Day 4 Sessions 07, 08 Code review + app canvases
Day 5 Sessions 09, 10 Cloud agent + MCP
Day 6 Sessions 11, 12 Custom agents + skills

Learning Outcomes

By completing this track, trainees will be able to:

  1. Use all Copilot surfaces — inline, Chat, CLI, agent mode, Copilot App, and cloud agent
  2. Build and configure Copilot Spaces for team context management
  3. Use the cloud agent for issue-driven autonomous development
  4. Build canvases that let people and agents work from the same artifact
  5. Build custom MCP servers that extend Copilot's capabilities
  6. Create custom agent profiles with specialized instructions and tools
  7. Develop and share agent skills for team workflows
  8. Design end-to-end agentic workflows: issue → agent → PR → review → merge
  9. Evaluate third-party coding agents (Claude, Codex) alongside Copilot
  10. Architect an agent strategy for a development team

Next Steps

  • DevOps & Automation — Apply Copilot and agent mode to CI/CD pipelines and infrastructure
  • Enterprise Rollout — Govern and scale agentic workflows across the organization
  • Full Mastery — Add DevOps, Squad orchestration, enterprise governance, and capstone