Expert knowledge for Azure AI Document Intelligence development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when using AnalyzeDocument v4.0, custom models, containers/Docker, SAS/managed identity auth, or SDK/REST workflows, and other Azure AI Document Intelligence related development tasks. Not for Azure AI Vision (use azure-ai-vision), Azure AI Custom Vision (use azure-custom-vision), Azure AI Search (use azure-cognitive-search), Azure AI Video Indexer (use azure-video-indexer).
global
Requires network access. Uses mcp_microsoftdocs:microsoft_docs_fetch or fetch_webpage to retrieve documentation.
generated_at:2026-06-21
generator:docs2skills/1.0.0
New
Saved Jun 26, 2026
Azure AI Document Intelligence Skill
This skill provides expert guidance for Azure AI Document Intelligence. Covers troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. It combines local quick-reference content with remote documentation fetching capabilities.
How to Use This Skill
IMPORTANT for Agent: Use the Category Index below to locate relevant sections. For categories with line ranges (e.g., L35-L120), use read_file with the specified lines. For categories with file links (e.g., [security.md](security.md)), use read_file on the linked reference file
IMPORTANT for Agent: If metadata.generated_at is more than 3 months old, suggest the user pull the latest version from the repository. If mcp_microsoftdocs tools are not available, suggest the user install it: Installation Guide
This skill requires network access to fetch documentation content:
Preferred: Use mcp_microsoftdocs:microsoft_docs_fetch with query string from=learn-agent-skill. Returns Markdown.
Fallback: Use fetch_webpage with query string from=learn-agent-skill&accept=text/markdown. Returns Markdown.
Category Index
Category
Lines
Description
Troubleshooting
L37-L43
Diagnosing and fixing Document Intelligence issues: latency/performance problems, service error codes and meanings, and known Foundry-specific bugs and workarounds.
Best Practices
L44-L54
Improving custom model accuracy and confidence, labeling and table-tagging best practices, training/classification workflows, and managing the full Document Intelligence model lifecycle
Decision Making
L55-L60
Guidance on choosing the right Document Intelligence model for your scenario and planning/migrating workloads to the v4.0 API and feature set.
Architecture & Design Patterns
L61-L65
Guidance on designing disaster recovery, redundancy, and failover strategies for Azure AI Document Intelligence models and deployments.
Limits & Quotas
L66-L75
Quotas, capacity add-ons, throttling behavior, batch scaling, and language/OCR support limits for Document Intelligence (service, custom, and prebuilt models).
Security
L76-L83
Securing Document Intelligence: creating SAS tokens, configuring data-at-rest encryption, and using managed identities and VNets to lock down access to resources.
Configuration
L84-L89
Configuring Document Intelligence containers and building, training, and composing custom models for tailored document processing workflows.
Integrations & Coding Patterns
L90-L99
Using SDKs/REST to call Document Intelligence, handle AnalyzeDocument/Markdown outputs, and integrate with apps, Azure Functions, and Logic Apps for end‑to‑end document workflows
Deployment
L100-L106
Deploying Document Intelligence via Docker/containers, including image tags, offline/disconnected setups, and installing/running the service and sample labeling tool.