Course Format and Delivery

Delivery Method: LiveOnline
Schedule: 3 sessions of 4.5 hour
Cost: $1,495 USD

All sessions are delivered live by an expert instructor in a fully interactive online environment.

*20% off for group bookings when booking 3 or more attendees from the same organization on the same course dates in the same transaction.

About this course

This prospectus defines a three-session, 14-contact-hour training engagement for engineering teams already using GitHub Copilot or comparable AI-assisted coding tools. The program moves beyond introductory feature awareness into disciplined, repeatable engineering workflows that improve productivity while preserving quality, security, and human oversight.

The training is positioned as an applied engineering enablement program, not a basic Copilot orientation. Participants will practice concrete workflows and leave with shared understanding for when and how to use AI coding assistance responsibly.

In this course you will learn

• Understand the fit of AI into modern development workflows and processes.
• Understand the changing role of the developer with respect to AI.
• Grow confidence in managing AI tools and flows.
• Understand AI tradeoffs, challenges and when AI is not a good solution.
• Understand where Copilot fits in the AI ecosystem.
• Select the right Copilot mode for a given engineering task.
• Write prompts that include scope, context, constraints, examples, and acceptance criteria.
• Use Copilot to understand unfamiliar repositories and generate onboarding documentation.
• Generate and improve tests, identify edge cases, and validate AI-assisted changes.
• Use Plan mode and Agent mode with appropriate supervision and approvals.
• Configure repo-wide and path-specific custom instructions.
• Understand where AGENTS.md, prompt files, skills, custom agents, MCP servers, and CLI hooks fit.
• Apply guardrails for sensitive data, dependency changes, testing, code review, and rollback.
• Optional: Create a shared team working agreement for AI-assisted coding.
  
  

Current Copilot Feature Areas Reflected

• Repository custom instructions: .github/copilot-instructions.md
• Path-specific instructions: .github/instructions/**/*.instructions.md
• Agent instructions including standard AGENTS.md
• Reusable prompt files: .github/prompts/*.prompt.md
• Agent skills: SKILL.md packaged under project or personal skills folders
• Custom agents: .github/agents/*.agent.md where supported
• Copilot CLI
• MCP servers for tool and data-source access
• Copilot on GitHub.com for repo, issue, PR, and line-level workflows
• Cloud/background/agentic workflows where enabled by plan and policy
  
  

Expected Deliverables

• Slide PDFs
• Step-by-step hands-on labs
• Prompt pattern handout
• AI-assisted coding guardrails checklist
• Team working agreement template
  
  

What you will need

• GitHub Copilot Access
• Basic working knowledge of Copilot
• Software development experience
• Ability to attend all sessions
  
  

This course is great for

• Software engineers actively using or evaluating Copilot
• Technical leads who need strategic approaches for AI-assisted development
• Teams seeking practical improvements in code generation, refactoring, tests, debugging, documentation, and review workflows
  
  

Topics Covered

Improve Productivity - Practice Copilot workflows for accelerating planning, code implementation, codebase understanding, test creation, refactoring, debugging, cross-function documentation generation, and deployment enablement. Focus on productive use of AI features and options.  

Prepare for future engineering roles - Introduce agentic workflows, MCP/tool integration, Copilot CLI, custom instructions, AGENTS.md, prompt files, skills, and custom agents. Explain how these technologies and similar ones correlate to industry AI directions and current and future AI roles. 

Build hands-on experience -  Use guided labs and practice with tools that will be used in production. All labs are designed to be completed within a reasonable period of time and focus on understanding how to use the AI technology and incorporate best practices vs coding exercises. Lab environments are preconfigured to allow students to immediately dive-in.

Increase confidence -  Develop comfort level with managing AI as a tool. Share practices and techniques to apply with AI in general for getting best results. Understand how to approach and recover from AI failures. Teach when to use Ask, Plan, Agent, GitHub.com, CLI, MCP, custom instructions, and human review. Understand how to incorporate these approaches into an SDLC.

Apply tools to real problems - Use realistic issue-driven workflows, repository onboarding, testing, PR summaries, and code review activities. 

Improve quality and consistency -  Initiate a team playbook, guardrails checklist, and starter customization files.