Enhancing VS Code extensions with GitHub Copilot
summary
Live demos show VS Code chat participants that fetch editor context, call a language model, and return actionable UI: a SQL participant reads live database schema, streams GPT-4 responses, extracts a ```SQL``` code block and adds a Run Query button that executes against the connection — built in a couple dozen lines of code and working end to end. Partners built participants (MongoDB notes 1.5 million downloads; Stripe shipped a checkout flow), with a noted GPT-4 vs GPT-3.5 latency tradeoff and APIs in Insiders, stable in July.
AI-written summary · about
chapters (8)
- 0:00GitHub Copilot in VS Code
- 7:58Extending Copilot chat
- 11:09Live SQL query chat
- 22:30Smart actions and context menu
- 26:44MongoDB Copilot showcase
- 30:16Stripe Copilot showcase
- 33:27Recap and resources
- 34:51Q&A
related talks
01h 02mLevel up with GitHub Copilot: using AI to learn, code, and build
46mPragmatic techniques to get the most out of GitHub Copilot
47mGitHub Copilot for SQL Development: Integrating the Power of AI into Database Development
34mUsing AI to build an AI Java app
40mLevel Up with Copilot
41mIf your code could speak, what would it tell you?
01h 00mTips & Tricks: Get the Most Out of GitHub CoPilot
59mUnleash the Power of Visual Studio Code