Collaborating with Agents in your Software Dev Workflow
summary
Hands-on lab demonstrates GitHub Copilot acting as an agent inside the IDE and on github.com using Model Context Protocol (MCP) to call external tools; agents generate code, run unit tests, create a branch and create draft pull request, and can self-heal by re-running in GitHub Actions. Agents run in ephemeral Actions runners with no internet by default, require approved workflow runs, and cannot merge or review their own work. Lab uses Codespaces for setup, offers exercises via an octo-hol repo, and notes Copilot pricing ($39.99 enterprise, $19.99 business).
AI-written summary · about
chapters (8)
- 0:00Introduction and setup
- 3:27Understanding context with Copilot
- 8:43Copilot workloads overview
- 15:50Starting the hands-on lab
- 30:13Coding agent deep dive
- 43:48MCP servers and context files
- 53:27DevOps flow with AI
- 1:00:00Q&A and closing
related talks
45mAgentic AI for Maintainers: Getting the Most From GitHub Copilot Enterprise
25mA Unified Agent Experience
51mYou Will Never Program the Same Again: Unleash GitHub Copilot with Agent Mode and MCP Servers
24mGitHub Copilot Agents + Sonar | The Blueprint for Agentic Development
40mUnlocking Productivity with GitHub Copilot Best Practices and Tips
57mPut an Agent Inside Your App in 10 Minutes or Less with the GitHub Copilot SDK
01h 05mThe Next Generation of Developer Productivity with GitHub Copilot & Visual Studio
01h 20mGithub Copilot - The World's Most Widely Adopted AI Developer Tool