Skip to main content
Agentic Software Engineering using GitHub Copilot

Agentic Software Engineering using GitHub Copilot

Class Details

May, 2026 - Last Updated: Jul, 2026 · 4 Days
GitHub Copilot Agentic Software Engineering Intermediate

This four-day workshop takes you from GitHub Copilot fundamentals to full agentic software engineering. Across nine modules you will build expertise across the complete Copilot ecosystem, covering artifacts and tools, agent sessions, the Agents Window, agentic coding, the Copilot CLI and SDK, the Copilot desktop app, agentic DevOps, governance, cost, observability, and spec-driven delivery. Every concept is grounded in hands-on practice with real tools and real scenarios.

The way software gets built is changing fast. AI agents are no longer just productivity tricks; they are becoming core members of the engineering team. This course is designed for developers who want to lead that shift rather than catch up to it. You will learn to delegate the repetitive, the predictable, and the mechanical to agents so that you can focus your own attention on decisions that require judgment, context, and creativity.

You will start by mastering GitHub Copilot as a true development partner, then move through artifact design, agent sessions with the Agents Window, agentic coding with multi-agent orchestration, and automation with the CLI and SDK. Advanced modules cover the Copilot desktop app for session-based issue delivery, agentic DevOps for infrastructure and pipelines, governance and cost management, and spec-driven delivery that ties everything together. By the end you will have a working mental model for agentic systems, a set of reusable patterns you can bring back to your team, and the confidence to apply them immediately.

Audience

  • Software engineers interested in leveraging AI agents to enhance coding productivity and capabilities
  • Software architects looking to integrate and manage AI agents within the software development lifecycle
  • Team leads and managers exploring how AI agents optimize team workflows and project outcomes

Prerequisites

  • Experience with software development at a professional level
  • A GitHub Copilot license with a credit allowance, or a configured bring-your-own-key (BYOK) endpoint; usage-based billing makes this a required setup step

Curriculum

Module 1: GitHub Copilot Fundamentals

  • Introduction & Copilot Vision
  • Selecting & Configuring Models
  • AI Assisted Coding
  • Slash Commands
  • Context Variables
  • Pull Requests & Code Reviews
  • Management and Settings
  • Working in the Terminal

Module 2: GitHub Copilot Artifacts & Tools

  • Copilot Instructions
  • Prompt Files
  • Model Context Protocol & MCP Registry
  • Custom Agents (Overview, Repository Agents, Claude Agents)
  • Agent Skills
  • Agent Plugins
  • Copilot Memory
  • Shaping the Context Window
  • GitHub Copilot Hooks

Module 3: Agent Sessions & Agents Window

  • The Agents Window
  • Agent Host Protocol (AHP vs ACP)
  • Remote Agent Sessions over SSH & Dev Tunnels
  • Session Management
  • Session Persistence & /chronicle
  • Subagents
  • Deep Research with /research
  • Troubleshooting Agent Sessions

Module 4: Implementing Agentic Coding

  • Using Local Agents and Agent Mode
  • Delegating Tasks to Cloud Agents
  • Multi-Agent Orchestration
  • Using Anthropic Claude Code Agents
  • Agentic Browser Automation
  • Upgrading & Modernization

Module 5: GitHub Copilot CLI & SDK

  • GitHub Copilot CLI
  • Business Case: HR Document Updates Automation
  • GitHub Agentic Workflows
  • GitHub Copilot SDK
  • Copilot SDK Demos
  • Implementing & Using MCP Apps

Module 6: GitHub Copilot App

  • Overview
  • Sessions from Issues, Prompts & Pull Requests
  • The Validation Loop
  • Scheduled Automations
  • Syncing Skills & MCP Servers

Module 7: Agentic DevOps

  • Automation using Azure CLI
  • Infrastructure as Code (azd, Bicep & Terraform)
  • Azure DevOps Pipelines & GitHub Actions
  • Testing using Copilot
  • Documentation using Copilot

Module 8: Governance, Cost & Observability

  • Trust, Safety & the Permission Model
  • Cost Model & AI Credits
  • Enterprise Policy & Managed Settings
  • Observability with OpenTelemetry

Module 9: Spec-Driven Development & Delivery

  • Spec Driven Development
  • Spec-Driven Workflow
  • Constitution, Specification and Technical Plan
  • Tasks & Implementation
  • Getting Started with GitHub Spec Kit
  • Sample Case: Implement a Product Feature

Class Logistics

Delivery Price 4.800 €
Max Users 12
Infrastructure (per user) 100 €
Lab Requirements GitHub Codespaces / DevContainer
AI Coder Bring your own

All prices are net B2B prices and subject to 20% VAT or Reverse Charge in the EU.