- Document Intelligence is a powerful AI tool within Foundry Tools (formerly Azure AI Services) that enables organizations to automatically extract text, key-value pairs, tables, and document structure from files such as PDFs, images, and forms. It uses advanced AI and optical character recognition (OCR) to transform unstructured content into structured, actionable data. As part of Foundry Tools, Document Intelligence integrates seamlessly with other tools like Language, Vision, and Content Understanding—making it easier to build intelligent agents and applications that can read, analyze, and respond to real-world documents with precision and speed.
- Yes, Azure Document Intelligence—formerly part of Azure AI Services—is now rebranded as Document Intelligence in Foundry Tools. This change is part of a broader platform unification under Foundry, aligning these services with how developers build intelligent, agentic applications today.
Document Intelligence still offers the same powerful capabilities—like extracting text, tables, key-value pairs, and layout from documents, forms, and images using prebuilt and custom models. Document Intelligence is now a core tool within the Foundry ecosystem, designed to work seamlessly with other tools like Speech, Translator, and Content Understanding.
This rebrand helps clarify how Document Intelligence fits into the Foundry platform—making it easier to discover, orchestrate, and integrate into modern AI workflows for document automation, knowledge extraction, and agentic reasoning.
- See Azure Document Intelligence availability.
- It supports printed and handwritten forms, PDFs, and images.
- Document Intelligence supports multiple languages including English, French, German, Italian, Spanish, Portuguese, Dutch, Chinese, Japanese, and Korean. See the full list here.
- The custom option uses five samples to learn the structure of your documents and intelligently extract text and data tailored to them. The prebuilt option doesn't use samples—the model has already been trained and is ready to use off the shelf to extract key fields from specific document types.
- Layout extracts text using high-definition optical character recognition (OCR) tailored for documents. It also extracts the structures of tables (row and column numbers), selection marks and more.