Skip to main content
Ace Skills Consulting
Microsoft logoIntermediate

AI-200: Azure AI Cloud Developer

Build cloud-native Azure applications that use AI models safely, scale on demand and are ready for production — and prepare for AI-200.

  • 40 hours of live, code-along sessions
  • Builds one application end to end across the five days
  • App Service, Functions, Container Apps, Cosmos DB and AI models
  • Managed identities and Key Vault used from Day 1
  • Successor path for developers who planned to take AZ-204
Aligned to Microsoft exam AI-200
Duration
5 Days | 40 Hrs
Next batch
Batches on request
Delivery
Live Online · Onsite · Corporate
Level
Intermediate
Exam
AI-200
Language
English

Why learn AI-200 with Ace Skills

  • AI features done properly

    Prompts, embeddings and RAG are built into a real application with filtering, evaluation and cost awareness — not a standalone demo.

  • Choose the right compute

    You run the same API on App Service, Functions and Container Apps and see where each one fits on scaling, cost and cold starts.

  • Secure by default

    Managed identities, Key Vault and Entra ID app registrations are used from the first lab, so no secrets end up in your code.

  • Ready for the AZ-204 successor

    If you were preparing for AZ-204, this course maps your existing skills onto the newer AI-200 outline and fills the gaps.

Course overview

Application developers on Azure are now expected to do more than deploy a web app and connect it to a database. Teams want features that summarise documents, answer questions over company data or classify incoming requests, and they want those features built with the same discipline as the rest of the application: secure secrets, sensible scaling and proper monitoring. This five-day course trains you to do exactly that.

The course follows a single project. On day one you host an API on App Service, Azure Functions and Azure Container Apps and compare how each scales. Day two adds data with Blob Storage and Azure Cosmos DB through the SDKs. Day three secures the application with Microsoft Entra ID app registrations, managed identities, Key Vault and App Configuration.

Day four is about AI: calling hosted models from your code, writing effective system prompts, generating embeddings and building retrieval-augmented generation with Azure AI Search. You also add content filtering and simple evaluation so responses can be trusted. Day five connects services with API Management, Event Grid and Service Bus, instruments everything with Application Insights and closes with exam preparation.

Labs are written in C# with Python alternatives where practical, and each one builds on the previous so you finish with a working, deployable solution in your own repository.

This course is aligned to the AI-200 exam, reported as the developer path following the retirement of AZ-204 on 31 July 2026. Because the exam is new, confirm the current skills outline on Microsoft Learn before booking; we update the course as details are published.

Key features

  • Single end-to-end project built across five days
  • Code-along labs in C# with Python alternatives
  • Retrieval-augmented generation with Azure AI Search
  • Passwordless design with managed identities from the start
  • API Management, Event Grid and Service Bus integration
  • Application Insights tracing and troubleshooting
  • Exam strategy session and practice questions
  • 30 days of post-training doubt support

Who should attend

  • Software developers building applications on Azure
  • Developers who were preparing for the retired AZ-204 exam
  • Back-end and API engineers adding AI features to products
  • Solution engineers who prototype on Azure for clients
  • DevOps engineers who need stronger development depth

Prerequisites

  • At least one year of programming experience in C#, Python or a similar language
  • Comfort with REST APIs, JSON and Git
  • Basic familiarity with the Azure portal (AZ-900 level)
  • A laptop with VS Code or Visual Studio installed

Curriculum

5 Days · 40 Hours · 16 Modules · 14 Labs

  1. App Service

    • App Service plans and scaling rules
    • Configuration and application settings
    • Deployment slots and swaps
    • Diagnostics and log streaming
    • Lab: Deploy an API to App Service with a staging slot · 50 min

    Azure Functions

    • Triggers, bindings and hosting plans
    • Durable Functions patterns
    • Local development and debugging
    • Cold starts and concurrency
    • Lab: Build an HTTP and queue-triggered Function · 50 min

    Containers

    • Building images and pushing to Azure Container Registry
    • Azure Container Apps revisions and scaling
    • Dapr and service-to-service calls overview
    • Choosing between Functions, App Service and Container Apps
    • Lab: Containerise the API and deploy to Container Apps · 55 min

  2. Blob Storage from code

    • Storage SDK clients and authentication
    • Uploads, metadata and properties
    • Lifecycle policies and access tiers
    • Change feed and event-driven processing
    • Lab: Upload, tag and list documents with the Blob SDK · 45 min

    Azure Cosmos DB

    • Data modelling and partition keys
    • Consistency levels
    • SDK operations and request units
    • Change feed processors
    • Vector search in Cosmos DB overview
    • Lab: Model and query application data in Cosmos DB · 60 min

    Caching and relational data

    • Azure Cache for Redis patterns
    • Connecting to Azure SQL Database securely
    • Choosing a data store for each workload
    • Lab: Add a Redis cache in front of a slow query · 35 min

  3. Microsoft Entra ID for developers

    • App registrations and service principals
    • OAuth 2.0 and OpenID Connect flows
    • Microsoft Authentication Library (MSAL)
    • Calling Microsoft Graph
    • Lab: Protect the API with Entra ID and call it from a client · 55 min

    Secrets and configuration

    • Managed identities: system- and user-assigned
    • Azure Key Vault secrets, keys and certificates
    • Azure App Configuration and feature flags
    • Shared access signatures and when to avoid them
    • Lab: Remove all secrets from code with managed identity and Key Vault · 50 min

    Securing AI endpoints

    • Keyless access to model endpoints
    • Network isolation options
    • Quotas, rate limits and cost controls

  4. Calling models from code

    • Model deployments and endpoints
    • Chat completions and system prompts
    • Structured outputs and function calling
    • Streaming responses
    • Token usage and cost
    • Lab: Add a summarisation feature to the application · 50 min

    Retrieval-augmented generation

    • Embeddings and chunking strategies
    • Azure AI Search indexes and vector search
    • Hybrid search and semantic ranking
    • Grounding answers with citations
    • Lab: Build a RAG endpoint over your own documents · 75 min

    Responsible and reliable AI

    • Content filtering and safety settings
    • Evaluating response quality
    • Handling failures, retries and fallbacks
    • Lab: Add content filtering and a simple evaluation run · 30 min

  5. API Management

    • Products, subscriptions and policies
    • Rate limiting and caching policies
    • Fronting AI endpoints through a gateway
    • Lab: Publish the API through API Management with a rate-limit policy · 45 min

    Event- and message-based solutions

    • Event Grid topics and subscriptions
    • Service Bus queues and topics
    • Event Hubs at a glance
    • Choosing the right messaging service
    • Lab: Process uploads asynchronously with Event Grid and Service Bus · 50 min

    Monitoring and troubleshooting

    • Application Insights instrumentation
    • Distributed tracing and dependency maps
    • Availability tests and alerts
    • Investigating failures with KQL
    • Lab: Trace a failing request end to end · 35 min

    Exam readiness

    • Exam format and question styles
    • Reading code-based questions
    • Practice questions with review
Download full syllabus (PDF)

Skills you will gain

  • Azure App Service
  • Azure Functions
  • Azure Container Apps
  • Azure Cosmos DB
  • Blob Storage SDK
  • Managed identities
  • Azure Key Vault
  • MSAL
  • Embeddings
  • RAG
  • Azure AI Search
  • API Management
  • Event Grid
  • Service Bus
  • Application Insights

Tools & technologies

  • Visual Studio Code
  • Visual Studio
  • .NET SDK
  • Python
  • Azure CLI
  • Azure Functions Core Tools
  • Docker
  • Git
  • Azure portal
  • Azure AI Foundry

Certification exam

Exam details
Exam nameAzure AI Cloud Developer (AI-200)
Exam codeAI-200
Voucher includedNo — book directly with the vendor
DeliveryOnline proctored or Test centre
Validity & renewal1 year (free online renewal assessment)

Skill areas measured

  1. Develop Azure compute solutions
  2. Develop for Azure storage and data
  3. Implement security for Azure solutions
  4. Integrate AI models and services into applications
  5. Connect to and consume Azure services
  6. Monitor and troubleshoot solutions

Exam details are pending verification. Vendors change exams; confirm on the official vendor page before booking. Official exam page (opens in a new tab)

Schedule & Pricing

Live Online

Individual

Price on request

  • 40 hours of live, trainer-led sessions
  • 14 hands-on labs
  • Ace Skills course completion certificate

Onsite

At your office or our centre

Pricing depends on location, group size and dates.

  • Delivered at your premises or an Ace centre
  • Same curriculum and labs as live online
  • Dates planned around your team

Corporate / Team

Private batch for your organisation

A private batch with content adapted to your environment and goals.

  • Customised curriculum
  • Private batch, online or onsite
  • Progress and assessment reports
  • GST invoice and PO-based billing

No public batches scheduled — Talk to an Advisor for a private batch.

Projects & labs you will build

  • Day 2 · 60 min

    Model and query application data in Cosmos DB

  • Day 4 · 75 min

    Build a RAG endpoint over your own documents

Your certificate

Certificate of Completion — Ace Skills Consulting

Awarded on completing the course. It records the course title and training hours, and you can share it on your LinkedIn profile.

The Microsoft certification itself is awarded by Microsoft when you pass exam AI-200.

Frequently asked questions

I was preparing for AZ-204. Is this the right course?

Yes. AZ-204 retired on 31 July 2026 and AI-200 is the reported successor; this course keeps the core Azure development skills and adds the AI integration the newer exam expects.

Which programming language do the labs use?

Labs are written in C# with Python alternatives for most exercises. You can complete the course in either language.

Do I need prior AI or machine learning experience?

No. You will call hosted models through SDKs and APIs; no model training or data science background is required.

What happens if Microsoft updates the AI-200 exam?

We map the curriculum to the current published skills outline and revise it when Microsoft changes the exam. Always check the latest outline on Microsoft Learn before booking.

Do you run weekend batches?

Yes. Weekend batches cover the same 40 hours across consecutive Saturdays and Sundays, with timings in IST that also suit learners in the Gulf.

Can you run a private batch for our team?

Yes. We run private online or onsite batches for corporate teams, and we can weight the labs towards your own application stack. Request a corporate quote with your team size and preferred dates.

Related courses

Explore more

All Microsoft Azure courses Microsoft certifications

Microsoft, Azure, Microsoft 365, Power BI and Microsoft Entra are trademarks of the Microsoft group of companies.

Train your team on AI-200

Private batches online or at your office in India and the GCC, with a curriculum adapted to your environment.