Cooking with Agents in VS Code
summary
Demo shows one codebase, three agents solving three concrete problems: a local agent (Claude Opus) writing and iterating unit tests with human in the loop, a background agent using a Git worktree to build a front end, and a cloud agent running in GitHub Actions to add README and contribution files. Presenter demonstrates the loop in VS Code with Copilot and Autopilot, all three agents run simultaneously and the tests and PRs actually complete.
AI-written summary · about
chapters (11)
- 0:00Introduction
- 1:20AI agent ROI in dev
- 2:49Agent types: local vs cloud
- 4:56Choosing agent types
- 5:58Demo: frontend with background agent
- 7:21Demo: repo with cloud agent
- 8:03Demo: tests with local agent
- 11:54Cloud agents: safety
- 13:37Customizing agents
- 15:21Extending agent features
- 16:44Q&A
related talks
25mA Unified Agent Experience
06h 22mUsing AI to Enhance Developer Productivity
01h 04mCollaborating with Agents in your Software Dev Workflow
29mBoost your coding productivity with Github Copilot Agent
39mAgents for the Sake of Happiness
35mGoing Beyond Copilot with AI Agents
16mBeyond the IDE: The Future of Developing Software With Agents
24mGitHub Copilot Agents + Sonar | The Blueprint for Agentic Development
