ms-foundry

Create GenAI agents with Microsoft Foundry SDK and azure-ai-projects in Python.

Updated Aug 27, 2026

Search Tags:#python #agents #tools #foundry #azure-ai-projects #azure-foundry

Ready to run

npx skills add https://github.com/pascalvanderheiden/my-agent-skills --skill ms-foundry

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ms-foundry
Source: https://github.com/pascalvanderheiden/my-agent-skills/tree/main/skills/ms-foundry
Command: npx skills add https://github.com/pascalvanderheiden/my-agent-skills --skill ms-foundry

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires azure-ai-projects, azure-identity, and includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enables developers to rapidly build GenAI applications by leveraging the Microsoft Foundry SDK to orchestrate agents, threads, runs, and tool integrations with minimal boilerplate.

Core Features & Use Cases

Create agents with built-in tools (Code Interpreter, File Search, Bing Grounding, Azure AI Search)
Manage conversations through threads and messages, with deterministic runs and tool outputs
Interact with OpenAI-compatible endpoints and deploy AI projects using the Foundry SDK in Python

Quick Start

Install the Foundry SDK and azure-identity, configure your Foundry project endpoint, create an agent with desired tools, start a thread, send a user message, and read the agent's response.

Frequently Asked Questions about ms-foundry

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I create AI agents with built-in tools using the Microsoft Foundry SDK in Python?▼

You create AI agents with built-in tools in Python by installing the azure-ai-projects and azure-identity packages, configuring your Foundry project endpoint, and initializing agents with Code Interpreter, File Search, or Bing Grounding capabilities.

What is the best way to manage conversation threads and messages with the Foundry SDK?▼

Managing conversation threads and messages with the Foundry SDK involves creating a thread, sending user messages to it, and executing deterministic runs to process tool outputs and retrieve the agent's response with minimal boilerplate.

Do I need azure-identity to authenticate GenAI applications using azure-ai-projects?▼

Yes, you need the azure-identity package to authenticate GenAI applications using azure-ai-projects. It provides the required credential handling to access OpenAI-compatible endpoints within the Foundry SDK environment.

Can I integrate Azure AI Search and Bing Grounding with Foundry SDK agents?▼

Yes, you can integrate Azure AI Search and Bing Grounding with Foundry SDK agents. The azure-ai-projects package supports configuring these tools directly during agent creation to ground responses in external data.

How do I deploy AI projects and interact with OpenAI-compatible endpoints using azure-ai-projects?▼

You deploy AI projects and interact with OpenAI-compatible endpoints using azure-ai-projects by configuring the Foundry project endpoint, authenticating via azure-identity, and orchestrating agent runs through the Python SDK.