# mcs-labs

**Repository Path**: mirrors_microsoft/mcs-labs

## Basic Information

- **Project Name**: mcs-labs
- **Description**: No description available
- **Primary Language**: Unknown
- **License**: MIT
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-06-12
- **Last Updated**: 2025-08-09

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# 🤖 Microsoft Copilot Studio Labs 🧪

| Title | URL | Overview |
|-------|-----|----------|
| Create your own web-based AI assistant with agent builder | [agent-builder-web](./labs/agent-builder-web) | In this lab, you'll create a Copilot agent in Microsoft 365 Copilot Chat with Microsoft Copilot Studio agent builder. This agent will be designed to assist users with questions about Copilot agents. The agent will act as a learning companion or teacher, grounded in official Microsoft documentation. |
| Create your own enterprise data-based AI assistant with agent builder | [agent-builder-sharepoint](./labs/agent-builder-sharepoint) | In this lab, you'll create a SharePoint-integrated AI assistant using Microsoft Copilot Studio agent builder. Designed to support sales operations, the agent can analyze Excel data from SharePoint, reference policy documents, and deliver insights through dynamic charts and images. Leveraging advanced capabilities like code interpreter and image generation, the Sales Admin Assistant transforms static content into interactive, intelligent responses—making sales trend tracking and policy compliance faster and easier. |
| Set yourself up for success & discover ALM best practices | [setup-for-success](./labs/setup-for-success) | Set yourself up for success by learning ALM best practices in Microsoft Copilot Studio—because building great agents isn't enough if you can't deploy, update, or collaborate with confidence. This lab shows you how to avoid common pitfalls like manual rework, overwritten changes, and fragile deployments by structuring your solutions, managing configurations, and enabling Git-based source control from the start. |
| Give your public website chatbot a brain and make it an agent | [public-website-agent](./labs/public-website-agent) | Learn how to build and publish a Copilot Studio agent that delivers rich, contextual answers by combining your content with real-time data—no coding required. This lab guides you through creating a branded assistant that handles multi-part questions, reflects your organization's tone, reduces support load, and can be deployed to a public demo website for instant testing and feedback. |
| Create an MBR Agent and Deploy to SharePoint | [mbr-prep-sharepoint-agent](./labs/mbr-prep-sharepoint-agent) | In this lab, you'll build a conversational MBR (Monthly Business Review) agent using Microsoft Copilot Studio and SharePoint. The agent streamlines MBR preparation by extracting key insights, surfacing trends, and answering questions directly from uploaded decks—helping leaders focus on strategy instead of manual review. You'll configure knowledge sources, test the agent, and deploy it to SharePoint for easy access by your team. |
| Create an 'Ask me anything' agent for your employees | [ask-me-anything](./labs/ask-me-anything) | In this hands-on lab, you'll build a multi-agent IT Support solution using Microsoft Copilot Studio. Your primary "Ask me anything" agent will intelligently route queries to specialized sub-agents—like one for ServiceNow knowledge and incidents—delivering fast, accurate answers across systems like SharePoint, ServiceNow, and custom sources. You'll configure contextual routing, deploy into Microsoft 365 Copilot, and streamline workflows with AI-driven analysis and human-in-the-loop review. |
| Create an autonomous support agent and unlock new levels of productivity with AI automation | [autonomous-support-agent](./labs/autonomous-support-agent) | Create an intelligent autonomous support agent that automatically responds to user emails, retrieves real-time ticket updates from ServiceNow, and answers questions using your knowledge base—all without human intervention. In just 20 minutes, you'll learn how to configure triggers, connect tools, and build end-to-end automation that transforms repetitive support requests into instant, accurate responses. |
| Build an autonomous agent that uses Computer Use to retrieve data from legacy systems that lack API connectivity  | [autonomous-cua](./labs/autonomous-cua) | This lab guides participants through building an autonomous agent in Microsoft Copilot Studio that retrieves financial portfolio data from legacy systems without API access by simulating human interaction using the Computer use tool. It also integrates Microsoft 365 Outlook to automate email-based data requests and responses, streamlining workflows and improving decision-making efficiency. |
| Build an Autonomous Account News Assistant Agent | [autonomous-account-news](./labs/autonomous-account-news) | In this hands-on lab, you'll build an autonomous Account News Assistant agent using Microsoft Copilot Studio to keep sellers informed with timely insights. The agent scans Salesforce on a recurring schedule for high-value opportunities, searches the web for related industry news, and uses Deep Reasoning to evaluate relevance. It then compiles curated summaries into a structured HTML report and sends it via Microsoft 365 Outlook—all without user interaction. By the end of the 60-minute lab, participants will have configured triggers, tools, topics, variables, and report templates to create a fully operational, proactive assistant that enhances account intelligence and helps sales teams stay ahead of key developments. |
| Source control and deploy your agents | [pipelines-and-source-control](./labs/pipelines-and-source-control) | Deploy Copilot Studio agents with confidence using Power Platform pipelines. In this hands-on lab, you'll learn how to automate and govern your deployment process across DEV, TEST, and PROD environments. From creating robust pipelines to handling post-deployment configuration and source control, you'll gain practical skills to implement repeatable ALM workflows with built-in validation, managed environments, and Git integration—ensuring every deployment is consistent, secure, and production-ready. |
| Copilot Studio Kit | [copilot-studio-kit](./labs/copilot-studio-kit) | Automate quality assurance for your Copilot Studio agents with the Copilot Studio Kit. In this lab, you'll configure and run automated test scenarios, validate agent behavior using multiple test types, and gain actionable insights through analytics. You'll also explore advanced tools like conversation KPIs, UI customization, and governance dashboards—equipping you to ship high-quality, secure, and scalable AI agents with confidence. |
| Model Context Protocol (MCP) & Copilot Studio | [mcsmcp](https://aka.ms/mcsmcp) | In this lab, you will learn how to deploy an MCP Server and integrate it with Microsoft Copilot Studio. You’ll explore how to set up the MCP Server, enabling context-aware agents, and then how to add it into Copilot Studio for streamlined deployment and management.  |