Our seventh AI reference architecture (on the Azure Architecture Center) is written by AzureCATs Abhinav Mithal and Robert Alexander, and published by Mike Wasson.
- Enterprise-grade conversational bot
Reference architectures provide a consistent approach and best practices for a given solution. Each architecture includes recommended practices, along with considerations for scalability, availability, manageability, security, and more. The full array of reference architectures is available on the Azure Architecture Center.
Related Articles
This reference architecture describes how to build an enterprise-grade conversational bot (chatbot) using the Azure Bot Framework. Each bot is different, but there are some common patterns, workflows, and technologies to be aware of. For a bot to serve enterprise workloads, there are many design considerations to ponder beyond the core functionality. This article covers the most essential design aspects, and introduces the tools needed to build a robust, secure, and actively learning bot.
This reference architecture uses a significant number of Azure services. Your own bot may not use all of these services, or may incorporate additional services. Check out the article for additional detail on the services.
Bot logic and user experience
- Bot Framework Service (BFS)
- Azure App Service
Bot cognition and intelligence
- Language Understanding (LUIS)
- Azure Search
- QnA Maker
- Web app
Data ingestion
- Azure Data Factory
- Logic Apps
- Azure Functions
Logging and monitoring
- Application Insights
- Azure Blob Storage
- Cosmos DB
- Power BI
Security and governance
- Azure Active Directory (Azure AD)
- Azure Key Vault
Quality assurance and enhancements
- Azure DevOps
- VS Code
Topics covered include:
- Architecture
- Bot logic and user experience
- Bot cognition and intelligence
- Data ingestion
- Logging and monitoring
- Security and governance
- Quality assurance and enhancements
- Design considerations
- User message flow
- System data flow
- Building a bot
- Ingest data
- Core bot logic and UX
- Add smarts to your bot
- Quality assurance and enhancements
- Availability considerations
- Security considerations
- Manageability considerations
- Monitoring and reporting
- Automated resource deployment
- Continuous bot deployment
Head over to the Azure Architecture Center to learn more about the Enterprise-grade conversational bot reference architecture.
See also
Additional related AI reference architectures:
- Batch scoring on Azure for deep learning models
- Batch scoring of Python models on Azure
- Build a real-time recommendation API on Azure
- Distributed training of deep learning models on Azure
- Real-time scoring of Python Scikit-Learn and Deep Learning Models on Azure
- Real-time scoring of R machine learning models
Find all our reference architectures here.
AzureCAT Guidance
"Hands-on solutions, with our heads in the Cloud!"
This post first appeared on MSDN Blogs | Get The Latest Information, Insights, Announcements, And News From Microsoft Experts And Developers In The MSDN Blogs., please read the originial post: here