Software development
Artificial Intelligence
Cloud
View all courses
Learn
Connect
Blog
Resource hub
Featured resource
2025 Tech Upskilling Playbook
Tech Upskilling Playbook

Build future-ready tech teams and hit key business milestones with seven proven plays from industry leaders.

Check it out

Build AI Agents with GitHub Copilot

Course Summary

This course focuses on advanced, real-world GitHub Copilot workflows for developers. Participants will deepen their use of GitHub Copilot inside VS Code and apply repository-level customization and context engineering. Microsoft Copilot and broader context-engineering concepts are covered briefly and purposefully, primarily to support developer workflows such as incident response, meeting summaries, and email triage.

Prerequisites:

In order to succeed in this course, you will need: 

  • Intermediate coding skills in Java
  • Familiarity with GitHub, Git workflows, and VS Code
  • A GitHub Copilot-enabled account
  • Access to Microsoft Copilot
Purpose
Advance the use of GitHub Copilot inside VS Code
Audience
Engineers and developers moving to autonomous agentic workflows and standardized AI context engineering
Role
Software Developers | Java Programmers } Technical Managers
Skill level
Intermediate
Style
Lecture | Hands-on Activities | Labs
Duration
2 days
Related technologies
Gen AI | Microsoft Copilot | Github | VS Code | Java

 

Learning  objectives
  • Use GitHub Copilot in VS Code with advanced capabilities, including agent mode and multi-step task delegation
  • Design agent-ready repositories using repository-specific custom instructions to standardize AI behavior across teams
  • Shape GitHub issues and tasks so they can be safely and effectively executed by autonomous coding agents
  • Assign work to the GitHub Copilot coding agent, review agent-generated pull requests, and iterate through feedback loops
  • Create and use custom agents in VS Code to act as specialized teammates
  • Apply prompting patterns as task specifications in agentic workflows
  • Integrate Microsoft Copilot selectively into developer workflows using Outlook and Teams
  • Engineer durable context artifacts that improve agent reliability and reduce prompt sprawl
  • Apply agent governance practices, including CI enforcement, code review strategies, and verification-first workflows
  • Combine multiple AI tools intentionally to improve code quality, delivery velocity, and long-term maintainability without over-automation

What you'll learn:

In this Build AI Agents with GitHub Copilot course, you'll learn:

From Assistive AI to Agentic Development

  • Evolution of developer AI
  • What agentic means in a software development context
  • Human and agent collaboration models
  • Capabilities and limits of autonomous coding
  • Safety, trust, and verification as first-class concerns

Agent-Ready Repositories

  • Why repository structure determines agent success
  • Using .github/copilot-instructions.md
  • Encoding architectural conventions and technical standards
  • Writing instructions that guide both humans and agents
  • Add or modify custom instructions to observe changes in agent behavior

Agent Context & Guardrails

  • Why agents.md exists
  • Why prompts and issues are too ephemeral for durable system context
  • Providing agents the same shared understanding that humans have
  • What belongs in agents.md and what does not belong
  • Create or refine an agents.md

Designing Work for Agents

  • Why vague tasks fail with autonomous agents
  • Creating workable, autonomous-friendly slices
  • Agent-ready GitHub issue structure
  • Deciding when work should be agent-only, human-only, or collaborative
  • Refactor an existing issue into an agent-ready issue and validate against an agent success checklist

Build AI Agents with GitHub Copilot

real world content

Real-World Content

Project-focused demos and labs using your tool stack and environment, not some canned "training room" lab.
expert practitioners

Expert Practitioners

Industry experts that bring their battle scars into the classroom.
experiential learning

Experiential Learning

More coding than lecture, coupled with architectural and design discussions.
fully customized

Tailored Outlines

Once-size-fits-all doesn't apply to training teams. That's where we come in!

Dive in and learn more

When transforming your workforce, it’s important to have expert advice and tailored solutions. We can help. Tell us your unique needs and we'll explore ways to address them.

Let's chat

By clicking submit, you agree to our Privacy Policy and Terms of Use, and consent to receive marketing emails from Pluralsight.
Related Pages