Azure AI Document Intelligence (AIAZURE)

Microsoft, Azure

This course focuses on practical use of Azure AI Document Intelligence to extract structured data from unstructured documents such as invoices, forms, contracts, receipts and business cards. Participants learn solution architecture, integration and data protection.

The training covers using prebuilt and custom models, hands-on steps for building, labeling and testing models, deployment patterns and integration with Power Automate, Logic Apps and Power BI. It also addresses security and cost optimization for production.

THIS TRAINING COURSE WILL HELP YOU:

  • Understand Azure AI services for document processing
  • Use prebuilt models (invoices, IDs, receipts, business cards)
  • Train and test custom models for specific document types
  • Deploy solutions with Power Automate, Logic Apps or Power BI
  • Implement security: RBAC, encryption, private endpoints, GDPR

WHO SHOULD ATTEND?

  • IT specialists and developers working with documents and AI
  • Architects and consultants implementing cloud solutions
  • Data analysts and BI specialists

COURSE LOCATION AND AVAILABLE DATES



Public courses are usually delivered in Czech, but this course is also available in English. We can arrange private training for your team online, at your premises or in our classrooms, and tailor the content to your needs.

For groups of around 4 or more participants, private training can already be comparable in price to booking individual places on a public course. Send us your requirements and we’ll recommend the best format and provide an exact quote.

Request training in English

Course content:

Hide details
  • Introduction to Azure AI Document Intelligence
    1. Overview of Microsoft Azure AI services for document processing
    2. Difference between Document Intelligence (Form Recognizer) and other AI services
    3. Typical scenarios: invoices, forms, contracts, IDs, business cards, custom documents
    4. Basic service architecture, SLA and regional availability
  • Azure AI and cloud fundamentals
    1. IaaS vs. PaaS vs. SaaS in the Document Intelligence context
    2. Azure hierarchy: Tenant, Subscription, Resource Group, Resource
    3. Access control: Microsoft Entra ID and RBAC roles for AI services
    4. Overview of APIs, SDKs and Azure AI Studio
  • Hands-on demo: first AI model without code
    1. Create an Azure AI Document Intelligence resource in the portal
    2. Use the prebuilt Read model to extract text from PDFs and images
    3. Export results to JSON and inspect data structure
  • Prebuilt Document Intelligence models
    1. Read, Layout and General Document models (when to use each)
    2. Specialized prebuilt models: invoices, receipts, identity, business cards
    3. Limits and accuracy (how to interpret confidence scores)
    4. Pricing and API call costs
  • Practical demo: processing invoices
    1. Upload a set of invoices (PDF/JPG)
    2. Use the prebuilt invoice model
    3. Extract fields (vendor, customer, amount, due date)
    4. Export data to Excel/CSV and to Azure SQL
  • Custom models for specific documents
    1. When prebuilt models are insufficient
    2. Structured vs. unstructured documents
    3. Preparing a training dataset (minimum samples, scan quality)
    4. Labeling documents in Azure AI Document Intelligence Studio
  • Hands-on demo: create and train a custom model
    1. Import a custom document set
    2. Manually tag fields and zones in AI Studio
    3. Run training
    4. Test the model and compare with prebuilt models
  • Integration into applications and workflows
    1. Access via REST API and SDKs (C#, Python, JavaScript)
    2. Connect to Power Automate / Logic Apps for automation
    3. Direct integration with SharePoint, Dynamics 365 and ERP systems
    4. Export results to BI tools (Power BI)
  • Security, operations and cost management
    1. RBAC for Document Intelligence
    2. Data protection: encryption, private endpoints, GDPR considerations
    3. Monitoring usage (Azure Monitor, Log Analytics)
    4. Cost optimization: batch processing and result caching
  • Final workshop
    1. Automated processing of incoming PDF invoices from Azure Storage
    2. Trigger AI extraction using a Logic App
    3. Store results in SQL database and send notification emails
    4. Short participant presentations of their solutions
Prerequisites:
Basic familiarity with Azure and APIs or development is recommended.
Schedule:
2 days (9:00-17:00)

Training and learning environment