← back
The Agent Awakens: Collaborative Development with Copilot - Christopher Harrison, GitHub
Takeaway
Treat GitHub Copilot like an AI pair programmer — clear code, clear intent, and pick the right mode from completions to autonomous coding agent.
Summary
- GitHub advocate covers Copilot's workload spectrum: code completions → chat → multi-file edits → agent mode (in-IDE) → Copilot Coding Agent (cloud-based).
- Context is more than prompts — good variable names, comments, and project structure materially help Copilot navigate the codebase like a human pair programmer.
- Be explicit in prompts ('don't be passive aggressive with Copilot'); provide intent specifically rather than using terse chatbot-style commands.
- Coding Agent runs cloud-based, can be assigned to issues like a developer, opens PRs, runs CI, and iterates on test failures.
- Hands-on lab format with hard dependency on Wi-Fi — fallback is letting attendees finish the lab over the next few days.
copilotcode-generationagents
Original description
About Christopher Harrison Christopher is a long-time geek who's spent the bulk of his career training, supporting and upskilling developers. He's a web developer at heart with passions which span from Python to DevOps to TypeScript to AI. In his current role as an Enterprise Advocate for GitHub he seeks to help organizations improve their DevOps process and culture. When not found writing code he can be found running, playing Civilization, or spending time with his partner and their four-legged child (a rescue mutt). Recorded at the AI Engineer World's Fair in San Francisco. Stay up to date on our upcoming events and content by joining our newsletter here: https://www.ai.engineer/newsletter