← back
Collaborating with Agents in your Software Dev Workflow - Jon Peck & Christopher Harrison, Microsoft
Takeaway
Treat GitHub Copilot as a pair programmer reading your code — better naming, comments, and explicit intent are still the highest-leverage prompt-engineering for it.
Summary
- GitHub DevRel hands-on lab on Copilot's workflow spectrum: completions, single-shot chat, multi-file edits, agent mode (IDE-side autonomy), and Copilot coding agent (asynchronous, like Devin).
- Context is the lever — Copilot is an 'AI pair programmer' reading your code, so readable naming, comments, and project structure materially improve outputs; new users tend to over-terse prompts like old chatbots.
- Be explicit about intent: don't be 'passive-aggressive with Copilot' — if a constraint matters, say it, and use specificity to control behavior.
- Agent mode iterates within the IDE; coding agent operates async on issues/PRs at the project level. Lab uses real GitHub Copilot enterprise environments with personal handles.
github-copilotcoding-agentsprompt-engineering
Original description
GitHub Copilot's agentic capabilities enhance its ability to act as a peer programmer. From the IDE to the repository, Copilot can generate code, run tests, and perform tasks like creating pull requests using Model Context Protocol (MCP). This instructor-led lab will guide you through using agent capabilities on both the client and the server: Key takeaways include: Understanding how to bring agents into your software development workflow Identifying scenarios where agents can be most impactful, as well as tips and tricks to provide the right context to lead to success Discovering how Model Context Protocol provides access to an additional set of external tools and capabilities that the agent can use Recommended practices to accelerate your development while maintaining code quality. About Jon Peck An Enterprise Advocate (and occasional manager) at GitHub, Jon Peck meets daily with maintainers, startups, and F500 executives to familiarize them with industry best practices, policy suggestions, and product capabilities across DevOps and AI. With 25+ years of experience as a fullstack developer, architect, and advocate, he aims to to bring engaging, real-world learnings to both boardrooms and global conferences. - Speaker (conferences): Dev Exec World 2025, STARWEST 2024, InnerSource Summit 2023, GitHub Galaxy 2023, DevWeek Management 2023, Startup Grind 2022, GitHub InFocus 2022, DeveloperWeek 2018-20, SeattleJS, Global AI Conf 2018-19, AI Next 2019-20, MLOps World, Data Innovation Summit, Nordic APIs 2018-19 (keynote), ODSC East+West, API World, O'Reilly AI, OSCON - Speaker (tech schools): Galvanize, CodeFellows, Metis, Epicodus, Alchemy - Organizer: Seattle Building Intelligent Applications Meetup - Educator: Cascadia College, Seattle C&W, consultant - Lead Developer: Empower Engine, Giftstarter, Mass General Hospital, Cornell University - Technical Advocate: Algorithmia, GitHub 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