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.

Location, current course term

Contact us

Custom Customized Training (date, location, content, duration)

The course:

Hide detail
  • 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
Assumed knowledge:
Basic familiarity with Azure and APIs or development is recommended.
Schedule:
2 days (9:00 AM - 5:00 PM )
Language: