All Docs

Extension Docs

Topics Overview 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 Hosted Agents (Preview) Evaluation Tool Catalog Fine-Tuning (Automated Setup) Fine-Tuning (Project Template) Model Conversion Tracing Profiling (Windows ML) FAQ Reference File Structure Manual Model Conversion Manual Model Conversion on GPU Setup Environment Without Foundry Toolkit Update Project 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 Tutorial Attach to Container Create Dev Container Advanced Containers devcontainer.json Dev Container CLI Tips and Tricks FAQ

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

Visual Studio Code - Latest version to support MCP Server development.
GitHub Copilot Chat Visual Studio Code extension
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:

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

[Screenshot showing the Chat view in Visual Studio Code with Agent mode selected. The Tools button is highlighted, displaying a list of available tools including Agent Code Gen, AI Model Guide, Evaluation Code Gen, and Tracing Code Gen.]

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 agentsfrom 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.
10/28/2025