After this course you can build the back-end side of AI applications on Azure. You run services in containers on Container Apps or AKS, store embeddings in Cosmos DB, PostgreSQL with pgvector or Azure Managed Redis and query them with vector search, connect components through Service Bus, Event Grid and Azure Functions, and keep secrets, configuration and monitoring under control. The content follows the skill areas of exam AI-200. The course suits developers with Python and Azure experience who want to build scalable, observable AI solutions.
What you’ll take away.
- Manage container images with Azure Container Registry and deploy applications to App Service, Container Apps and AKS
- Store embeddings in Cosmos DB for NoSQL, Azure Database for PostgreSQL with pgvector and Azure Managed Redis, and query them with vector search
- Build event- and message-driven workflows with Service Bus, Event Grid and Azure Functions
- Manage secrets with Key Vault and settings with App Configuration securely
- Trace distributed applications with OpenTelemetry and analyse logs and metrics with KQL
Your training in detail
- Who is it for?
- Back-end and cloud developers who build AI-driven applications on Azure and need practical skills in containers, data services for AI, event-driven workflows, security and monitoring.
- Prerequisites
- Good Python skills, experience with Azure SDKs, and a grounding in containers, databases and messaging. A basic understanding of embeddings and vector databases helps.
- Format & planning
- Standard length: 5 training days. A different length can be arranged for companies.
Agenda: from understanding to application
Our independently developed agenda proposal. Focus areas, lab environment and scope are agreed before booking.
Container hosting: Azure Container Registry, ACR Tasks and App Service with environment variables and secrets
Orchestration: Container Apps with revisions and KEDA scaling, AKS with manifests
Cosmos DB for NoSQL: SDK, indexing policies, Request Units, vector search and change feed
Azure Database for PostgreSQL: schema, indexes, pgvector and RAG with metadata filters
Azure Managed Redis: caching, expiry, invalidation and vector indexes
Integration: Service Bus with dead-letter queues, Event Grid and serverless APIs with Azure Functions
Security and operations: Key Vault, App Configuration, OpenTelemetry and KQL
You build a small AI back end: a container app accepts documents, an Azure Function processes them via a Service Bus message and stores embeddings in PostgreSQL with pgvector, and you trace a request through every service with OpenTelemetry.
Exams, licences & credentials
The course prepares you for exam AI-200 for Microsoft Certified: Azure AI Cloud Developer Associate. The exam and its fee are included only if the offer confirms this explicitly. Microsoft issues the certificate once you pass. It is not an official Microsoft course unless the offer says so explicitly.
Vendor references & review date
Sources checked on 2026-11-10. These sources describe the technology or external exam requirements. They do not imply a partnership with NextNowa.
Your learning content
These objectives describe the training topic. The specific syllabus, dates and trainer are agreed before booking; the written offer is binding.
Frequently asked questions
Which programming language is used?
Microsoft expects Python skills for the certification, so the exercises are designed for Python.
How long is the AI-200 exam?
According to Microsoft you have 120 minutes. You need a score of at least 700 to pass.
Does AI-200 Develop AI cloud solutions on Azure: building back ends for AI applications include a certificate?
The course prepares you for exam AI-200 for Microsoft Certified: Azure AI Cloud Developer Associate. The exam and its fee are included only if the offer confirms this explicitly. Microsoft issues the certificate once you pass. It is not an official Microsoft course unless the offer says so explicitly.