microsoft/customer-chatbot-solution-accelerator

microsoft/customer-chatbot-solution-accelerator

Description: Customer Chatbot Solution Accelerator empowers organizations to build intelligent, conversational customer service experiences by leveraging Microsoft Foundry's agent framework.

Language: Python

License: MIT

Stars: 37

Forks: 33

Open issues: 24

Created: 2025-09-08T20:36:12Z

Pushed: 2026-06-10T13:30:09Z

Default branch: main

Fork: no

Archived: no

README:

Customer Chatbot Solution Accelerator

This solution accelerator empowers organizations to build intelligent, conversational customer service experiences by leveraging Microsoft Foundry's Agent Framework. With seamless integration of specialized AI agents, and enterprise-grade data services, teams can create chatbots that provide personalized product recommendations, answer policy questions, and deliver exceptional customer support. The solution combines a modern e-commerce frontend with an intelligent backend that uses an orchestrator agent to route customer queries to specialized agents (Product Lookup and Policy/Knowledge), ensuring accurate, contextual responses grounded in product catalogs and policy documents. By unifying AI capabilities with scalable cloud infrastructure, organizations can deliver 24/7 customer support that understands context, maintains conversation history, and provides actionable insights to improve customer satisfaction and operational efficiency.

---

[SOLUTION OVERVIEW](#solution-overview) \| [QUICK DEPLOY](#quick-deploy) \| [BUSINESS SCENARIO](#business-scenario) \| [SUPPORTING DOCUMENTATION](#supporting-documentation)

---

Solution overview

Leverages Microsoft Foundry's Agent Framework, Foundry IQ, and Azure Cosmos DB to create an intelligent customer chatbot with specialized agents for product lookup and knowledge management. The solution features a modern React-based e-commerce frontend with integrated chat interface, enabling customers to browse products, get personalized recommendations, and receive support through natural language conversations. An orchestrator agent intelligently routes queries to specialized agents (Product Lookup and Policy/Knowledge), which use hybrid search across product catalogs and policy documents to ensure accurate, contextual answers.

Solution architecture

The solution consists of:

|| |---|

Additional resources

For detailed technical information, see the component READMEs:

[Technical Architecture](./documents/TechnicalArchitecture.md)

---

Features

Key features

Click to learn more about the key features this solution enables

• Intelligent agent orchestration using Microsoft Agent Framework

Leverage Microsoft Foundry's Agent Framework with an orchestrator agent that uses automatic tool selection to route customer queries to specialized agents (Product Lookup and Policy/Knowledge). The orchestrator analyzes user intent and automatically invokes the appropriate specialist agent as a tool, ensuring queries are handled by the most capable agent for each task.

• Hybrid search capabilities

Foundry IQ provides fast, accurate product discovery and policy document retrieval using semantic and keyword search, enabling natural language queries across product catalogs and knowledge bases. Specialized agents access search indexes to retrieve relevant information from product catalogs and policy documents.

• Natural language interaction

Microsoft Foundry's Agent Framework orchestrates multi-agent workflows using GPT-4.1-mini to deliver conversational, context-aware responses that understand customer intent. The framework maintains conversation threads and context across sessions, enabling natural, flowing conversations with specialized agents.

• Modern e-commerce experience

React-based frontend with dual-panel layout featuring product browsing and integrated AI chat assistant for seamless shopping and support experiences

• Scalable data architecture

Azure Cosmos DB stores product catalogs, customer orders, and chat history with high availability and global distribution, ensuring fast access to customer and product data

---

Getting Started

Quick deploy

How to install or deploy

Follow the quick deploy steps on the deployment guide to deploy this solution to your own Azure subscription.

[Click here to launch the deployment guide](./documents/DeploymentGuide.md)

|---|---|---|

> Note: Some tenants may have additional security restrictions that run periodically and could impact the application (e.g., blocking public network access). If you experience issues or the application stops working, check if these restrictions are the cause. In such cases, consider deploying the WAF-supported version to ensure compliance. To configure, [Click here](./documents/DeploymentGuide.md#31-choose-deployment-type-optional).

> ⚠️ Important: Check Azure OpenAI Quota Availability > To ensure sufficient quota is available in your subscription, please follow [quota check instructions guide](./documents/QuotaCheck.md) before you deploy the solution.

Guidance

Prerequisites and costs

To deploy this solution accelerator, ensure you have access to an Azure subscription with the necessary permissions to create resource groups, resources, app registrations, and assign roles at the resource group level. This should include Contributor role at the subscription level and Role Based Access Control role on the subscription and/or resource group level.

Here are some example regions where the services are available: East US, East US2, Australia East, UK South, France Central.

Check the Azure Products by Region page and select a region where the following services are available.

Pricing varies by region and usage, so it isn't possible to predict exact costs for your usage. The majority of Azure resources used in this infrastructure are on usage-based pricing tiers. However, some services—such as Azure Container Registry, which has a fixed cost per registry per day, and others like Azure Cosmos DB or App Service when provisioned—may incur baseline charges regardless of actual usage.

Use the Azure pricing calculator to calculate the cost of this solution in your…