← 返回首页
Use Foundry Toolkit Copilot tools for AI agent development

Documentation

Topics Overview Overview Linux macOS Windows VS Code for the Web Raspberry Pi Network Additional Components Uninstall VS Code Tutorial Copilot Quickstart User Interface Personalize VS Code Install Extensions Tips and Tricks Intro Videos Overview Setup Quickstart Overview Language Models Context Tools Agents Customization Trust & Safety Overview Agents Tutorial Agents Window Planning Memory Tools Subagents Local Agents Copilot CLI Cloud Agents Third-Party Agents Overview Chat Sessions Add Context Inline Chat Review Edits Checkpoints Artifacts Panel Debug Chat Interactions Prompt Examples Overview Instructions Prompt Files Custom Agents Agent Skills Language Models MCP Hooks Plugins Context Engineering Customize AI Test-Driven Development Edit Notebooks with AI Test with AI Test Web Apps with Browser Tools Debug with AI MCP Dev Guide OpenTelemetry Monitoring Inline Suggestions Smart Actions Best Practices Security Troubleshooting FAQ Cheat Sheet Settings Reference MCP Configuration Workspace Context Display Language Layout Keyboard Shortcuts Settings Settings Sync Extension Marketplace Extension Runtime Security Themes Profiles Overview Voice Interactions Command Line Interface Telemetry Basic Editing IntelliSense Code Navigation Refactoring Snippets Overview Multi-Root Workspaces Workspace Trust Tasks Debugging Debug Configuration Testing Port Forwarding Integrated Browser Overview Quickstart Staging & Committing Branches & Worktrees Repositories & Remotes Merge Conflicts Collaborate on GitHub Troubleshooting FAQ Getting Started Tutorial Terminal Basics Terminal Profiles Shell Integration Appearance Advanced Overview Enterprise Policies AI Settings Extensions Telemetry Updates Overview JavaScript JSON HTML Emmet CSS, SCSS and Less TypeScript Markdown PowerShell C++ Java PHP Python Julia R Ruby Rust Go T-SQL C# .NET Swift Working with JavaScript Node.js Tutorial Node.js Debugging Deploy Node.js Apps Browser Debugging Angular Tutorial React Tutorial Vue Tutorial Debugging Recipes Performance Profiling Extensions Tutorial Transpiling Editing Refactoring Debugging Quick Start Tutorial Run Python Code Editing Linting Formatting Debugging Environments Testing Python Interactive Django Tutorial FastAPI Tutorial Flask Tutorial Create Containers Deploy Python Apps Python in the Web Settings Reference Getting Started Navigate and Edit Refactoring Formatting and Linting Project Management Build Tools Run and Debug Testing Spring Boot Modernizing Java Apps Application Servers Deploy Java Apps GUI Applications Extensions FAQ Intro Videos GCC on Linux GCC on Windows GCC on Windows Subsystem for Linux Clang on macOS Microsoft C++ on Windows Build with CMake CMake Tools on Linux CMake Quick Start C++ Dev Tools for Copilot Editing and Navigating Debugging Configure Debugging Refactoring Settings Reference Configure IntelliSense Configure IntelliSense for Cross-Compiling FAQ Intro Videos Get Started Navigate and Edit IntelliCode Refactoring Formatting and Linting Project Management Build Tools Package Management Run and Debug Testing FAQ Overview Node.js Python ASP.NET Core Debug Docker Compose Registries Deploy to Azure Choose a Dev Environment Customize Develop with Kubernetes Tips and Tricks Overview Jupyter Notebooks Data Science Tutorial Python Interactive Data Wrangler Quick Start Data Wrangler PyTorch Support Azure Machine Learning Manage Jupyter Kernels Jupyter Notebooks on the Web Data Science in Microsoft Fabric Foundry Toolkit Overview Foundry Toolkit Copilot Tools Create Agents Models Playground Agent Builder Agent Inspector Evaluation Tool Catalog Fine-Tuning (Automated Setup) Fine-Tuning (Project Template) Model Conversion Tracing Profiling (Windows ML) FAQ File Structure Manual Model Conversion Manual Model Conversion on GPU Setup Environment Without Foundry Toolkit Template Project Migrating from Visualizer to Agent Inspector Overview Getting Started Resources View Deployment VS Code for the Web - Azure Containers Azure Kubernetes Service Kubernetes MongoDB Remote Debugging for Node.js Overview SSH Dev Containers Windows Subsystem for Linux GitHub Codespaces VS Code Server Tunnels SSH Tutorial WSL Tutorial Tips and Tricks FAQ Overview Tutorial Attach to Container Create Dev Container Advanced Containers devcontainer.json Dev Container CLI Tips and Tricks FAQ Default Keyboard Shortcuts Default Settings Substitution Variables Tasks Schema
Copy as Markdown

On this page there are 8 sections

Use Foundry Toolkit Copilot tools for AI agent development

The Foundry Toolkit Copilot tools help you build AI agent applications faster. These tools give you ready-made features, templates, and best practices. You can create smart applications that use AI more quickly.

Note

The Foundry Toolkit Copilot tools use the VS Code Language Model Tool API. These tools extend a large language model (LLM) with domain-specific features in chat. In agent mode, VS Code can automatically use these tools to handle user prompts and perform tasks.

The Foundry Toolkit Copilot tools include four main tools:

  • Agent Code Gen
  • AI Model Guide
  • Evaluation Code Gen
  • Tracing Code Gen

Prerequisites

  1. Visual Studio Code - Latest version to support MCP Server development.
  2. GitHub Copilot Chat Visual Studio Code extension
  3. Foundry Toolkit Visual Studio Code extension

Using Copilot tools in Foundry Toolkit

After installing the prerequisites, you can use the tools Foundry Toolkit provides when using agents in chat:

  1. Open the Chat view ⌃⌘I (Windows, Linux Ctrl+Alt+I), and select Agent from the dropdown.

  2. Select the Configure Tools... button to view the list of available tools.

    Optionally, select or deselect the tools you want to use. You can search tools by typing in the search box.

Agent Code Gen tool

The Agent Code Gen tool helps developers create agent code more easily. Use this tool to quickly make code snippets and templates that work well for AI agents. This approach makes development faster and ensures your code follows best practices for AI agent development.

Key features of Agent Code Gen tool

The Agent Code Gen tool has several important features:

  • Intelligent agent code generation: The tool creates agent code based on what you need.

  • Default framework selection: If you don't choose a framework, the tool picks Microsoft Agent Framework SDK for you.

    Example requirement:

    Create an AI app to manage travel queries, use Microsoft Foundry models.
  • Various agent framework functionality support: The tool supports many features like function calling, MCP, and streaming responses.

    Example requirement:

    Build a conditional routing workflow based on email classification: - "Email Classifier": determines if email is spam or legitimate. - "Spam Handler": processes spam emails (if spam detected). - "Email Assistant": drafts responses for legitimate emails (if not spam).

AI Model Guide tool

The AI Model Guide tool helps developers pick the best AI models for their apps. It recommends Microsoft Foundry and GitHub models, including the latest and most popular ones. The tool provides details like input types, context length, cost, and metrics (quality, speed, safety). It also explains how to connect to models, such as GitHub endpoints and tokens.

This tool supports:

  • Basic model recommendation:

    Example information prompt:

    Create a quick demo AI Chat app

    For this example, Copilot selects a model like the free GitHub GPT-4.1 for the chat app.

  • Model selection based on specific requirements:

    Example requirement prompt:

    Create an evaluation for my AI travel assistant application that assesses response accuracy and user satisfaction.
  • Example 2:

    Enable tracing for my AI travel assistant application built with the agent-framework SDK in Python.

    Foundry Skills

    The Foundry Toolkit also installs two skills that help you use GitHub Copilot chat to work with agents and other resources and generate scaffolded code.

    • microsoft-foundry-agent-framework-code-gen - Generates and modifies AI agent code using the Microsoft Agent Framework SDK for Foundry. This skill scaffolds, builds, and enhances agent-based applications for Microsoft Foundry, including adding tools, fixing issues, and implementing multi-agent workflows.
    • microsoft-foundry Deploy, evaluate, and manage AI agents and Foundry resources end-to-end. This skill handles the full lifecycle of Foundry agents—from deployment and execution to evaluation, prompt optimization, and resource management.

    To use them, you need to do nothing special. The skills are invoked whenever the context of your conversation makes it clear that you want to work with Foundry or the Microsoft Agent Framework.

    What you learned

    In this article, you learned how to:

    • Use AI tools to speed up app development.
    • Add tracing to monitor and debug your AI apps.
    • Pick the best AI models for your tasks.
    • Include evaluation and testing in your AI workflow.