# LearnAI-CustomerServiceAgents **Repository Path**: mirrors_Azure/LearnAI-CustomerServiceAgents ## Basic Information - **Project Name**: LearnAI-CustomerServiceAgents - **Description**: No description available - **Primary Language**: Unknown - **License**: MIT - **Default Branch**: master - **Homepage**: None - **GVP Project**: No ## Statistics - **Stars**: 0 - **Forks**: 0 - **Created**: 2020-08-08 - **Last Updated**: 2026-04-04 ## Categories & Tags **Categories**: Uncategorized **Tags**: None ## README #### About this course Building an enterprise scale customer service agent presents multiple challenges like the need to integrate with an enterprise’s Active Directory for Agent authentication, need for a voice conversation in addition to chat assistance and ability to support multiple cognitive service models. This course will teach you how to address these and build a customer service agent for an online retailer that can have voice conversations with the end user using the Microsoft Speech API, understand the context of the conversation using LUIS API, manage state of a conversation leveraging dispatch API and provide relevant product recommendation using a previously built recommendation model. This course focusses on designing for a retail use case, integration with the multiple cognitive services, especially the Speech API, and scaling for enterprises. Previous LearnAI bootcamps on Microsoft’s Prebuilt AI services covered how to design, architect and build intelligent agents. This course expands those prior learnings and experiences. In this course, you will learn to 1. Design and architect an agent that integrates Speech and LUIS cognitive services to enable voice conversation and extract user request and contextual feedback data from the voice conversation. 2. Enable the agent to provide relevant product recommendations to the customer by integrating a prebuilt Azure ML based recommendation model. 3. Add supporting technologies to make the agent enterprise grade by integrating Azure Active Directory for the agent authentication and Q&A maker with Dispatch API for conversation state management. 4. Extrapolate learnings and patterns for use within other industry use cases. #### Architecture ![Architecture](CSArchitecture.png) #### Technologies Used ![Technology](CSTechnologyMap.png) #### Pre-requisites • Familiarity with [Azure Bot Services/Microsoft Bot Framework](https://docs.microsoft.com/en-us/azure/bot-service/dotnet/bot-builder-dotnet-sdk-quickstart?view=azure-bot-service-4.0) • Understanding of the various [Cognitive Services](https://docs.microsoft.com/en-us/azure/cognitive-services/) and Capabilities • Familiarity with [LUIS](https://docs.microsoft.com/en-us/azure/cognitive-services/luis/what-is-luis) #### Pre-setup before you attend this course 1. You need a Microsoft Azure account to create the services we use in our solution. You can create a [free account](https://azure.microsoft.com/en-us/free/), use your [MSDN account](https://azure.microsoft.com/en-us/pricing/member-offers/credit-for-visual-studio-subscribers/) or use any other subscription where you have permission to create services 2. Install [Visual Studio 2017](https://visualstudio.microsoft.com/downloads/?utm_medium=microsoft&utm_source=docs.microsoft.com&utm_campaign=button+cta&utm_content=download+vs2017) version 15.5 or later, including the Azure development workload. #### Course Details Primary Audience: Azure AI Developers, Architects Secondary Audience: Data Scientists and Business Intelligence Professionals #### Level This is designed as an advanced level course for AI architects and developers #### Type This course in its full form is designed to be taught in-class, but you can also use the materials in a self-paced fashion. There are assignments, and multiple reference links throughout the materials that support the concepts and skills you will learn. Length Full Course Class room training: 12 hours  #### Course Modules This course is organized in following modules 1. AI Ethics ~ 20 min 2. Case Study: AdventureWorks Digital Transformation Dreams ~ 1.5 hrs 3. Envisioning and Designing the customer agent solution ~ 2 hrs 4. Building an Azure Bot and integrate LUIS and Speech service ~ 6 hrs 5. Integrating a custom Azure ML recommendation model ~ 1 hr 6. Handoff and Learnings ~ 1 hr #### Related LearnAI Courses The following courses serve as useful prerequisite materials • [Designing and Architecting Intelligent Agents](https://azure.github.io/LearnAI-DesigningandArchitectingIntelligentAgents/) • [Building and Implementing Intelligent Agents and Apps](https://azure.github.io/LearnAI-Bootcamp/) • [Logging and Testing with Azure Bot Service](https://azure.github.io/learnAnalytics-AdvancedFeaturesforMicrosoftBotFramework) # Contributing This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.microsoft.com. When you submit a pull request, a CLA-bot will automatically determine whether you need to provide a CLA and decorate the PR appropriately (e.g., label, comment). Simply follow the instructions provided by the bot. You will only need to do this once across all repos using our CLA. This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/). For more information see the [Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/) or contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with any additional questions or comments.