1---2name: azure-ai-services3description: Azure AI services Skill4---5# Azure AI services Skill67This skill provides expert guidance for Azure AI services. Covers troubleshooting, best practices, decision making, limits & quotas, security, configuration, integrations & coding patterns, and deployment. It combines local quick-reference content with remote documentation fetching capabilities.89## How to Use This Skill1011> **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 file1213> **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](https://github.com/MicrosoftDocs/mcp/blob/main/README.md)1415This skill requires **network access** to fetch documentation content:16- **Preferred**: Use `mcp_microsoftdocs:microsoft_docs_fetch` with query string `from=learn-agent-skill`. Returns Markdown.17- **Fallback**: Use `fetch_webpage` with query string `from=learn-agent-skill&accept=text/markdown`. Returns Markdown.1819## Category Index2021| Category | Lines | Description |22|----------|-------|-------------|23| Troubleshooting | L36-L40 | Diagnosing and fixing common Content Understanding issues, including model errors, data ingestion problems, configuration mistakes, and troubleshooting steps for failed analyses. |24| Best Practices | L41-L46 | Best practices for Azure AI Content Understanding: designing extraction workflows, tuning models, improving document parsing accuracy, and handling complex or low‑quality documents. |25| Decision Making | L47-L56 | Guidance on choosing pricing tiers and tools (Foundry vs Content Understanding vs Document Intelligence/LLMs), standard vs pro modes, migration steps, and estimating Content Understanding costs. |26| Limits & Quotas | L57-L64 | Rate limits, quotas, and scaling for Foundry and Content Moderator/Understanding: autoscale strategies, image/term list limits, and how to stay within service quotas. |27| Security | L65-L80 | Securing Azure AI/Foundry: auth (Entra, keys, Key Vault), encryption (CMK, data-at-rest), DLP for outbound calls, VNet rules, policy-based governance, and secure analyzer access. |28| Configuration | L81-L99 | Configuring Foundry endpoints, credentials, containers, logging, and Content Understanding analyzers (classification, layout, audiovisual), routing, outputs, and resource recovery/purge. |29| Integrations & Coding Patterns | L100-L109 | Using Azure Content Moderator and Content Understanding via REST/.NET: text/image/video moderation, custom term lists, and building custom multimodal analyzers and workflows. |30| Deployment | L110-L117 | How to package and run Foundry tools/containers on Azure (ACI, Docker Compose, disconnected), and deploy Foundry resources using Azure AI containers and ARM templates |3132### Troubleshooting33| Topic | URL |34|-------|-----|35| Resolve common issues with Content Understanding | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/faq |3637### Best Practices38| Topic | URL |39|-------|-----|40| Apply best practices for Content Understanding workloads | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/best-practices |41| Improve Content Understanding document extraction quality | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/document/analyzer-improvement |4243### Decision Making44| Topic | URL |45|-------|-----|46| Choose and use Foundry commitment tier pricing | https://learn.microsoft.com/en-us/azure/ai-services/commitment-tier |47| Choose between Content Understanding, Document Intelligence, and LLMs | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/choosing-right-ai-tool |48| Choose between standard and pro modes in Content Understanding | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/standard-pro-modes |49| Choose between Foundry and Content Understanding Studio | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/foundry-vs-content-understanding-studio |50| Migrate Content Understanding analyzers from preview to GA | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/how-to/migration-preview-to-ga |51| Estimate and plan costs for Content Understanding | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/pricing-explainer |5253### Limits & Quotas54| Topic | URL |55|-------|-----|56| Use autoscale to increase Foundry rate limits | https://learn.microsoft.com/en-us/azure/ai-services/autoscale |57| Use Content Moderator image lists within quota limits | https://learn.microsoft.com/en-us/azure/ai-services/content-moderator/image-lists-quickstart-dotnet |58| Understand Content Moderator image and term list limits | https://learn.microsoft.com/en-us/azure/ai-services/content-moderator/samples-dotnet |59| Review Content Understanding service quotas and limits | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/service-limits |6061### Security62| Topic | URL |63|-------|-----|64| Configure authentication for Foundry Tools requests | https://learn.microsoft.com/en-us/azure/ai-services/authentication |65| Configure data loss prevention for Foundry outbound calls | https://learn.microsoft.com/en-us/azure/ai-services/cognitive-services-data-loss-prevention |66| Secure Foundry resources with virtual network rules | https://learn.microsoft.com/en-us/azure/ai-services/cognitive-services-virtual-networks |67| Understand Content Moderator data-at-rest encryption behavior | https://learn.microsoft.com/en-us/azure/ai-services/content-moderator/encrypt-data-at-rest |68| Configure secure access for Content Understanding analyzers | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/secure-communications |69| Enforce Entra-only auth by disabling local keys | https://learn.microsoft.com/en-us/azure/ai-services/disable-local-auth |70| Configure customer-managed encryption keys for Foundry | https://learn.microsoft.com/en-us/azure/ai-services/encryption/cognitive-services-encryption-keys-portal |71| Use built-in Azure Policies for Foundry governance | https://learn.microsoft.com/en-us/azure/ai-services/policy-reference |72| Rotate Foundry API keys without downtime | https://learn.microsoft.com/en-us/azure/ai-services/rotate-keys |73| Apply Azure Policy compliance controls to Foundry | https://learn.microsoft.com/en-us/azure/ai-services/security-controls-policy |74| Apply security features for Foundry Tools resources | https://learn.microsoft.com/en-us/azure/ai-services/security-features |75| Secure Foundry applications using Azure Key Vault | https://learn.microsoft.com/en-us/azure/ai-services/use-key-vault |7677### Configuration78| Topic | URL |79|-------|-----|80| Configure custom subdomains for Foundry endpoints | https://learn.microsoft.com/en-us/azure/ai-services/cognitive-services-custom-subdomains |81| Use environment variables for Foundry credentials | https://learn.microsoft.com/en-us/azure/ai-services/cognitive-services-environment-variables |82| Create reusable Azure AI container images with presets | https://learn.microsoft.com/en-us/azure/ai-services/containers/container-reuse-recipe |83| Configure Content Understanding analyzers and parameters | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/analyzer-reference |84| Configure classification and splitting in Content Understanding | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/classifier |85| Connect Content Understanding analyzers to Foundry model deployments | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/models-deployments |86| Use and customize Content Understanding prebuilt analyzers | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/concepts/prebuilt-analyzers |87| Configure document layout and data extraction with Content Understanding | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/document/elements |88| Interpret Content Understanding document Markdown output | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/document/markdown |89| Configure classification and routing in Content Understanding Studio | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/how-to/classification-content-understanding-studio |90| Copy Content Understanding custom analyzers across resources | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/how-to/copy-analyzers |91| Configure audiovisual analysis for audio and video inputs | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/video/elements |92| Interpret audiovisual Markdown output from Content Understanding | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/video/markdown |93| Configure diagnostic logging for Foundry resources | https://learn.microsoft.com/en-us/azure/ai-services/diagnostic-logging |94| Recover or purge deleted Foundry resources | https://learn.microsoft.com/en-us/azure/ai-services/recover-purge-resources |9596### Integrations & Coding Patterns97| Topic | URL |98|-------|-----|99| Reference for Azure Content Moderator REST APIs | https://learn.microsoft.com/en-us/azure/ai-services/content-moderator/api-reference |100| Call Content Moderator image moderation APIs | https://learn.microsoft.com/en-us/azure/ai-services/content-moderator/image-moderation-api |101| Use custom term lists with Content Moderator .NET SDK | https://learn.microsoft.com/en-us/azure/ai-services/content-moderator/term-lists-quickstart-dotnet |102| Use Content Moderator text moderation APIs | https://learn.microsoft.com/en-us/azure/ai-services/content-moderator/text-moderation-api |103| Integrate Content Moderator video scanning in .NET | https://learn.microsoft.com/en-us/azure/ai-services/content-moderator/video-moderation-api |104| Create custom Content Understanding analyzers via REST | https://learn.microsoft.com/en-us/azure/ai-services/content-understanding/tutorial/create-custom-analyzer |105106### Deployment107| Topic | URL |108|-------|-----|109| Run Foundry Tools using Azure AI containers | https://learn.microsoft.com/en-us/azure/ai-services/cognitive-services-container-support |110| Deploy Foundry containers to Azure Container Instances | https://learn.microsoft.com/en-us/azure/ai-services/containers/azure-container-instance-recipe |111| Run Foundry containers in disconnected environments | https://learn.microsoft.com/en-us/azure/ai-services/containers/disconnected-containers |112| Deploy multiple Azure AI containers with Docker Compose | https://learn.microsoft.com/en-us/azure/ai-services/containers/docker-compose-recipe |113| Deploy Foundry resources using ARM templates | https://learn.microsoft.com/en-us/azure/ai-services/create-account-resource-manager-template |
ComeOnOliver