The AI-200: Develop AI Cloud Solutions on Azure course replaces the AZ-204 course, which will be retired in May 2026.
AI-200 Course: Develop AI Solutions on Microsoft Azure
The AI-200: Develop AI Cloud Solutions on Azure course is an official Microsoft training program designed for professionals who want to design, develop, and deploy artificial intelligence solutions using Azure services. This training provides the necessary knowledge to build intelligent applications based on generative AI models, agents, Azure AI Services, and advanced data processing services.
Microsoft Azure is Microsoft's cloud platform that enables the development of scalable and secure enterprise solutions. Within the Azure ecosystem, artificial intelligence capabilities facilitate the creation of intelligent assistants, process automation, content analysis, natural language processing, and AI-driven applications for various business sectors.
The AI-200 course is aimed at developers, software engineers, cloud architects, and technical professionals involved in artificial intelligence projects. Its practical approach allows for implementing real solutions using Azure AI, integrating cognitive services, working with advanced AI models, and developing applications prepared for modern enterprise environments.
Additionally, this course is official from Microsoft and eligible for funding through FUNDAE for companies, facilitating training in one of the fastest-growing and most in-demand technological areas.
Course Overview
The AI-200: Develop AI Cloud Solutions on Azure course provides the knowledge and skills necessary to design, develop, and deploy artificial intelligence solutions in the cloud using Microsoft Azure services. This official training allows for acquiring a practical understanding of how to build intelligent applications leveraging the advanced AI capabilities of the Microsoft ecosystem.
Throughout the course, students will learn to work with technologies such as Azure AI Services, Azure OpenAI Service, language models, natural language processing, computer vision, and intelligent agents. Development patterns, service integration, and best practices for creating scalable, secure solutions ready for enterprise environments will also be addressed.
The training focuses on developing applications capable of automating processes, analyzing information, generating intelligent content, and improving decision-making through artificial intelligence. All of this with a practical approach that allows applying the acquired knowledge in real digital transformation projects based on Azure AI.
Virtual course with certification exam included as a gift. Don't miss this opportunity! The exam is valued at €126 + VAT and is included at no additional cost.
Promotion valid until December 31, 2026. One-attempt exam available only in Virtual - Teleformation mode. Not applicable to Self-Learning mode.
What is the Microsoft AI-200 certification for in a professional environment?
The Microsoft AI-200 certification validates the necessary competencies to design, develop, and deploy artificial intelligence solutions using Microsoft Azure services. It is aimed at technical professionals involved in generative AI projects, intelligent automation, virtual assistants, content analysis, and the development of AI-driven applications.
In the job market, this certification is especially relevant for profiles such as AI Developer, cloud developer, software engineer, solutions architect, or specialized artificial intelligence consultant. Companies are increasingly demanding professionals capable of integrating AI models, intelligent agents, and cognitive services within secure and scalable enterprise applications.
Obtaining AI-200 certification improves employability, strengthens technical specialization, and allows participation in digital transformation projects where artificial intelligence becomes a strategic component for optimizing processes, automating tasks, and generating value from data.
Professional Applications of Microsoft Azure AI
Microsoft Azure AI is Microsoft's suite of artificial intelligence services designed to develop advanced enterprise solutions in the cloud. The platform enables the incorporation of generative AI capabilities, natural language processing, computer vision, document analysis, and the creation of intelligent agents within corporate applications.
In organizations, Azure AI is used to automate processes, improve customer service, analyze unstructured information, generate intelligent content, and develop applications capable of interacting with users through natural language. These capabilities accelerate operational processes, improve productivity, and facilitate data-driven decision-making.
The AI-200 course allows applying these technologies in real scenarios by developing intelligent solutions on Azure, facilitating the creation of modern, scalable enterprise applications prepared to leverage the potential of artificial intelligence in different sectors of activity.
What the official Microsoft course at Nanfor includes
The training includes Microsoft Learn material, expert tutor presentations, authorized labs, specialized tutoring, and certification preparation.
Nanfor combines official Microsoft content with expert guidance, enabling training focused on practical application in real business environments.
Learn about all components
Advantages of the AI-200 training
Official Microsoft training in artificial intelligence: Updated content based on the most advanced Azure AI services.
Specialization in developing AI solutions in the cloud: You will learn to design scalable intelligent applications on Azure.
Mastery of key technologies such as Azure OpenAI and Azure AI Services: Work with language models, vision, text analysis, and automation.
Practical approach oriented towards real projects: Development of solutions applicable in enterprise environments.
High professional demand in AI and Cloud: Training aligned with one of the fastest-growing areas of the IT market.
Prerequisites
To get the most out of this course, it is recommended:
- Basic programming knowledge
- Familiarity with Azure concepts and cloud services
- General notions of artificial intelligence or data analysis (recommended, not mandatory)
Preparation for the Microsoft Azure AI Cloud Developer Associate certification
This AI‑200 course prepares you for the official Microsoft certification in developing artificial intelligence solutions on Azure (Microsoft Certified: Azure AI Cloud Developer Associate), providing the necessary knowledge to design, build, and optimize AI-based applications in the cloud.
⏱️
Course Duration:
100 hours
🔑
Classroom Access:
3 months
General course information
Who is this course for?
This course is aimed at:
- Developers who want to specialize in artificial intelligence on Azure
- Software engineers working with cloud solutions
- IT professionals interested in incorporating AI into their applications
- Technical profiles wishing to evolve into AI Developer roles
Training Objectives: What will you learn?
Upon completion of the AI‑200 course, participants will be able to:
- Develop artificial intelligence solutions in Microsoft Azure
- Utilize Azure AI Services and Azure OpenAI in real projects
- Implement natural language processing (NLP) solutions
- Create computer vision applications and image analysis
- Design scalable AI architectures in the cloud
- Integrate artificial intelligence into enterprise applications
Elements of the AI-200 Microsoft Learn collection
- Introduction to Azure AI and cognitive services
- Developing solutions with Azure OpenAI Service
- Implementing natural language processing (NLP)
- Text analysis and language understanding
- Developing computer vision solutions
- Using AI services to automate processes
- Integrating AI into cloud applications
Course Content: Developing Artificial Intelligence Cloud Solutions on Azure - Program
Unit 1: Implement containerized application hosting in Azure
Module 1: Store and manage containers in Azure Container Registry
Learning Objectives:
- Explain how Azure Container Registry organizes images
- Create and manage container images with ACR Tasks
- Implement tagging and versioning strategies
- Use Azure CLI to manage images and tasks
- Understand production considerations in container environments
Lab / Practice:
- Building and running a container image with ACR Tasks
Module 2: Deploy containers to Azure App Service
Learning Objectives:
- Deploy custom containers to Azure App Service
- Configure container runtime environment (ports, startup, storage)
- Configure application variables and connection strings
- Monitor and troubleshoot containerized applications
Lab / Practice:
- Deploying a container to Azure App Service
Unit 2: Deploy and manage applications in Azure Container Apps
Module 1: Deploy containers to Azure Container Apps
Learning Objectives:
- Understand Azure Container Apps environments
- Deploy using CLI and YAML files
- Configure environment variables and secrets
- Configure authentication with the container registry
- Verify deployments using logs and revisions
Lab / Practice:
- Deploying a containerized backend API
Module 2: Manage containers in Azure Container Apps
Learning Objectives:
- Manage revisions and update images
- Diagnose revision errors
- Monitor logs and resolve incidents
- Configure health probes
- Optimize resources and scaling
Lab / Practice:
- Diagnosing and resolving a failed deployment
Module 3: Scale containers in Azure Container Apps
Learning Objectives:
- Configure scaling rules (HTTP, CPU, memory)
- Implement event-driven scaling with KEDA
- Select appropriate computing resources
- Apply revision modes to control scaling and traffic
Lab / Practice:
- Configuring autoscaling with KEDA
Unit 3: Deploy and monitor applications in Azure Kubernetes Service
Module 1: Deploy applications to Azure Kubernetes Service
Learning Objectives:
- Understand Deployments, Services, and Pods
- Create Kubernetes manifests
- Deploy and verify applications with kubectl
- Troubleshoot deployment errors
Lab / Practice:
- Deploying an inference API to AKS
Module 2: Configure applications in Azure Kubernetes Service
Learning Objectives:
- Use ConfigMaps for configuration
- Use Secrets for sensitive data
- Configure persistent storage (PVC)
- Apply configuration patterns in AKS
Lab / Practice:
- Configuring applications in AKS
Module 3: Monitor and troubleshoot in AKS
Learning Objectives:
- Monitor logs and metrics
- Diagnose problems in pods and services
- Verify connectivity and endpoints
- Apply structured troubleshooting methodologies
Lab / Practice:
- Diagnosing applications in AKS
Unit 4: Develop AI solutions with Azure Cosmos DB for NoSQL
Module 1: Create queries in Azure Cosmos DB for NoSQL
Learning Objectives:
- Understand the Cosmos DB data model
- Perform CRUD operations with the SDK
- Choose between direct reads and queries
- Build SQL queries for NoSQL
Lab / Practice:
- Building a document store for RAG
Module 2: Implement vector search in Azure Cosmos DB
Learning Objectives:
- Store and retrieve embeddings
- Configure vector policies
- Execute similarity queries
- Implement hybrid search
- Use change feed to keep embeddings updated
Lab / Practice:
- Developing a semantic search application
Module 3: Optimize query performance
Learning Objectives:
- Analyze RU query and consumption patterns
- Configure indexes (range, composite, vector)
- Optimize indexing policies
- Select appropriate consistency levels
Unit 5: Develop AI solutions with Azure Database for PostgreSQL
Module 1: Build and query with PostgreSQL
Learning objectives:
- Understand service architecture and features
- Configure secure connections with Entra ID and TLS
- Design database schemas
- Write efficient SQL queries
- Integrate PostgreSQL with Python applications
Lab / Practice:
- Develop a backend for AI assistants
Module 2: Implement vector search in PostgreSQL
Learning objectives:
- Store embeddings with pgvector
- Execute similarity searches
- Create vector indexes (IVFFlat, HNSW)
- Design retrieval patterns for RAG
Lab / Practice:
- Vector search implementation
Module 3: Optimize vector search
Learning objectives:
- Tune pgvector performance
- Optimize indexing strategies
- Scale PostgreSQL for AI workloads
Unit 6: Enhance AI solutions with Azure Managed Redis
Module 1: Implement data operations in Redis
Learning objectives:
- Understand caching strategies
- Select appropriate client libraries
- Implement storage and retrieval operations
- Manage data expiration and invalidation
Lab / Practice:
- Implement data operations in Redis
Module 2: Implement messaging with Redis
Learning objectives:
- Use pub/sub for real-time messaging
- Implement Streams as task queues
- Choose the appropriate messaging pattern
- Design processing pipelines for AI
Lab / Practice:
- Publishing and subscribing to events
Module 3: Implement vector storage in Redis
Learning objectives:
- Create vector indexes with RediSearch
- Store and query embeddings
- Develop semantic search applications
Unit 7: Integrate backend services for AI solutions
Module 1: Process AI operations with Azure Service Bus
Learning objectives:
- Understand messaging patterns
- Choose between queues and topics
- Design messages for AI
- Process messages reliably with DLQ
Lab / Practice:
- Message processing with Service Bus
Module 2: Develop workflows with Event Grid
Learning objectives:
- Design event-driven architectures
- Use the CloudEvents schema
- Configure event filtering and routing
- Manage retries and delivery
Lab / Practice:
- Publishing and receiving events
Module 3: Build serverless backends with Azure Functions
Learning objectives:
- Evaluate hosting options
- Create triggers and bindings
- Integrate Key Vault and App Configuration
- Apply security with managed identity
Unit 8: Manage secrets and configuration in AI solutions
Module 1: Manage secrets with Azure Key Vault
Learning objectives:
- Store secrets, keys, and certificates
- Retrieve secrets using SDK
- Implement secure rotation
- Apply caching strategies
Lab / Practice:
- Secret management with Azure Key Vault
Module 2: Manage configuration with Azure App Configuration
Learning objectives:
- Connect applications to App Configuration
- Manage configuration using labels
- Implement feature flags
- Integrate with Azure Key Vault
Lab / Practice:
- Retrieve configuration and secrets
Unit 9: Monitor and troubleshoot Azure applications
Module 1: Instrument applications with OpenTelemetry
Learning objectives:
- Understand observability concepts
- Instrument applications with OpenTelemetry
- Create custom traces and spans
- Export telemetry to Application Insights
Lab / Practice:
- Application instrumentation
Module 2: Analyze telemetry with logs and metrics
Learning objectives:
- Write KQL queries
- Analyze logs and metrics
- Create dashboards and workbooks
- Configure alerts
Lab / Practice:
Our differentiating factor: Practical labs
| Nanfor Lab |
Developed Technical Skills |
Practical Learning Outcome |
| Configuring the Azure environment for AI |
Creating resources in Azure, managing subscriptions and AI services |
The student deploys a complete environment for developing AI solutions in the cloud |
| Developing applications with Azure OpenAI |
Integrating GPT models, embeddings, and response generation |
The student creates generative AI applications ready for real use |
| Implementing RAG (Retrieval-Augmented Generation) solutions |
Indexing, embeddings, vector search, and data grounding |
The student builds systems that combine AI with corporate data |
| Creating serverless APIs with Azure Functions |
API design, triggers, bindings, and serverless logic |
The student exposes AI functionalities through scalable web services |
| Developing event-driven architecture |
Using Event Grid, Service Bus, and messaging |
The student implements decoupled and scalable AI workflows |
| Deploying applications with containers |
Using Azure Container Apps and Azure Kubernetes Service (AKS) |
The student deploys AI solutions in modern cloud environments |
| Managing container images |
Using Azure Container Registry (ACR) |
The student manages versions and deployments of AI applications |
| Developing solutions with Cosmos DB (NoSQL) |
Database design, querying, and optimization |
The student manages data storage for AI applications |
| Using PostgreSQL with pgvector |
Implementing vector databases |
The student builds advanced semantic search engines |
| Implementing caching with Azure Redis |
Performance optimization and latency reduction |
The student improves the performance of AI applications in production |
| Integrating Azure AI services |
Using language, vision, speech, and content APIs |
The student integrates multiple AI capabilities into one solution |
| Security and secret management |
Using Azure Key Vault, identities, and access |
The student protects sensitive applications and data in AI environments |
| Observability and monitoring |
Using logs, metrics, OpenTelemetry, and KQL |
The student monitors performance and detects errors in AI solutions |
| Automating deployments |
Configuring basic DevOps pipelines |
The student automates the delivery of AI solutions |
| Designing scalable AI architectures |
Service selection, cloud-native design |
The student designs robust, production-oriented solutions |
| Developing an end-to-end AI solution |
Integration of all previous components |
The student builds a complete application ready for an enterprise environment |
Language
- Course: English / Spanish
- Labs: English / Spanish
Do you want to take this course? Request information now
If you wish to take this training virtually, you can purchase it at the top of the product page. For any questions, please contact us.
If you wish to take it in in-person or telepresence modality, please contact us:
Nanfor, Microsoft's official ICT training center
Nanfor is a customized ICT training center, specialized in technological training for professionals and companies, and is officially approved by Microsoft as:
- Microsoft Solutions Partner – Training Services
- Microsoft Cloud Partner
These approvals certify that Nanfor complies with Microsoft's standards for delivering technical courses, using Microsoft content and Microsoft Certified Trainers (MCTs), ensuring quality, continuous updates, and alignment with certifications.
Frequently Asked Questions
What is the AI-200 course?
It is an official Microsoft training that teaches how to develop artificial intelligence solutions in the cloud with Azure, using services such as Azure AI and Azure OpenAI.
What will I learn in this course?
You will learn to create intelligent applications using Azure AI services, including natural language processing, computer vision, and generative AI models.
Does the course include the certification exam?
Yes. This course includes the official Microsoft certification exam (according to the terms of the current promotion).
Is it included in Nanfor's LaaS?
Yes. The AI-200 course is part of LaaS Cert, which allows access to this training along with other official certifications.
How is the course delivered?
It is delivered online, with access to content, labs, and expert support, allowing for flexible progress.
Can it be subsidized by FUNDAE?
Yes. This course may be eligible for FUNDAE subsidy, subject to the company's conditions.
How long is access to the course?
The course includes 3 months of access, with the possibility of extension (except for subsidized training).
