News
Custom Agents Transform Visual Studio with Built-In and DIY Options
Microsoft has unveiled a new approach to AI agent integration in Visual Studio, empowering developers with both built-in assistants and robust support for building custom agents. This marks a major transition from relying solely on general-purpose AI towards a flexible, workflow-centric automation model inside the integrated development environment.
The change, announced in a Visual Studio DevBlogs post, turns Visual Studio into a hub for AI-powered agents, allowing users to deploy curated preset agents or design their own for task-specific automation. According to Microsoft, the initiative is intended to provide developers with advanced automation and context-sensitive support throughout their coding lifecycle.
Built-In Agent Capabilities in Visual Studio
With this update, Visual Studio no longer limits users to a single, generic AI assistant. Instead, Microsoft ships a collection of preset agents "that tap into deep IDE capabilities" such as code navigation, refactoring, and profiling. These agents are curated to deliver specialized support for common development challenges, optimizing productivity and code quality by leveraging the platform's internal APIs and tools. For full details, see the announcement post.
Developers are now able to select from multiple agents, enabling a tailored experience that aligns with their project needs. The inclusion of these curated agents ensures that common tasks are streamlined and best practices promoted across development teams.
Accessed by the agent picker in the chat panel or using '@' in chat, built-in agents as of now include:
- Debugger
-- Goes beyond “read the error message.” Uses your call stacks, variable state, and diagnostic tools t
o walk through error diagnosis systematically across your solution.
- Profiler
-- Connects to Visual Studio's profiling infrastructure to identify bottlenecks and suggest targeted optimizations grounded in your codebase, not generic advice.
- Test -- (when solution is loaded) Generates unit tests tuned to your project's framework and patterns, not boilerplate that your CI will reject.
- Modernize -- (.NET and C++ only) Framework and dependency upgrades with awareness of your actual project graph. Flags breaking changes, generates migration code, and follows your existing patterns.
Building Your Own Agents: Maximum Customization
Microsoft also provides tools for developers to "create, extend, and scale -- your way," allowing for the design and deployment of custom agents to automate unique workflows. The agent framework supports both visual design and traditional coding, catering to a broad range of development backgrounds. According to official documentation, users can develop agents using the languages and tools they already know and integrate them with Visual Studio and other Microsoft environments.
These custom agents can process fine-tuned models, custom logic, and proprietary workflows. Microsoft Foundry, a component within this ecosystem, provides resources for designing, customizing, and managing AI applications and agents, ensuring that teams can scale solutions across projects and organizations.
Integration and Workflow in the IDE
Agents in Visual Studio, whether built-in or custom, are invoked contextually within the IDE and assist at various stages of development. For example, a profiling agent can provide real-time performance optimization advice, while a custom agent might automate repetitive refactoring unique to a codebase. Microsoft documents that these agents help minimize context switching, keeping developers focused and productive inside Visual Studio.
With the option to mix built-in and custom agents, developers benefit from unified workflows that combine broad capabilities with specialized automation. Access to agents is delivered seamlessly through the IDE, emphasizing Microsoft's aim for low friction and fast adoption.
Getting Started and Resources
Microsoft provides an official landing page, Build agents, your way, which introduces its agent-building tools and technologies. The site summarizes the available offerings and provides links to SDKs, getting started guides, and documentation hosted elsewhere.
These custom agents can process fine-tuned models, custom logic, and proprietary workflows. Microsoft Foundry is highlighted among the technologies linked from the landing page, directing developers to further resources for designing, customizing, and managing AI agents.
About the Author
David Ramel is an editor and writer at Converge 360.