Build with AI: Agent Mode in Visual Studio Code

Agent Mode in Visual Studio Code marks a shift in how developers work with AI from asking questions to delegating real, multi‑step tasks directly in the codebase. While many developers use AI chat in editors, fewer understand when agents are more effective, how they differ from chat, or how to apply them to everyday workflows such as scaffolding, documentation, debugging, and source control. This course moves beyond demos to hands‑on practice. Learners compare Agent Mode with Chat, build features end to end using agents, create custom agents and prompts, connect MCP servers, and evaluate models. By the end, developers can confidently apply agents where they add value, enforce team standards, and automate repetitive work to improve productivity and code quality in Visual Studio Code.

Learning objectives
Use agents to understand an existing codebase, scaffold new features, and iteratively build and refine functionality within a real project.
Create custom agents with defined roles, constraints, and behaviors, and design effective prompts that produce consistent, high‑quality results.
Connect agents to external tools and data sources using MCP servers and apply those capabilities to extract structured insights from their codebase.
Assess real development problems, decide when Agent Mode is the right approach, and apply agents selectively to maximize productivity and minimize risk.