Cooking with Agents in VS Code — Liam Hampton, Microsoft

AI Engineer · Intermediate ·🤖 AI Agents & Automation ·1h ago
One codebase, three problems, three agents running at the same time. Liam Hampton from Microsoft demos the full loop in VS Code: a local agent with Claude Opus writing and fixing unit tests with him in the loop, a background agent using a git work tree to build a front end from a GitHub issue without him touching it, and a cloud agent running in GitHub Actions to make the repo open source friendly. The talk is a framework for knowing which agent path to pick and why. Local when you want hands on iteration. Background when the task is big and you can tolerate being half in half out. Cloud when you genuinely do not care how it gets done. VS Code handles all three from one interface, with Copilot, Claude, and third party agents accessible from the same control plane. Speaker info: - https://x.com/liamchampton - https://www.linkedin.com/in/liam-conroy-hampton/ - https://github.com/liamchampton
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Related AI Lessons

How to Detect Fraud in Documents Using AI in PHP
Detect fraudulent documents using AI in PHP to prevent financial losses and ensure authenticity
Medium · AI
Why I Built My Own AI: The Case for Self-Hosted Domain Agents (Kulvex)
Learn how to build a self-hosted AI platform with domain agents for home automation, messaging, and more, and why it's a viable alternative to paid services like OpenAI
Dev.to · GaltRanch
The Harness Flywheel: How Reviews Become Rules
Learn how to harness the power of reviews to create rules for agent-augmented teams, reducing failure modes and improving overall performance
Dev.to · Ian Johnson
I Built a Revenue-Generating API That Charges AI Agents Per Call — 67-100% Margin on Autopilot
Learn how to build a revenue-generating API that charges AI agents per call with 67-100% margin on autopilot
Dev.to AI
Up next
Building agents with real-world reasoning
Google for Developers
Watch →