1---2name: microsoft-foundry-classic3description: Expert knowledge for Microsoft Foundry Classic (aka Azure AI Foundry classic) development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when building Foundry agents, prompt flows, RAG/search, Azure OpenAI deployments, or multi-agent architectures, and other Microsoft Foundry Classic related development tasks. Not for Microsoft Foundry (use microsoft-foundry), Microsoft Foundry Local (use microsoft-foundry-local), Microsoft Foundry Tools (use microsoft-foundry-tools).4---5# Microsoft Foundry Classic Skill67This skill provides expert guidance for Microsoft Foundry Classic. 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.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 | L37-L47 | Diagnosing and fixing Foundry issues: compute/usage in prompt flow, deployments/monitoring, private endpoints, Azure OpenAI fine-tuning, risks & safety alerts, and known bugs/workarounds. |24| Best Practices | L48-L61 | Best practices for prompts, safety, fine-tuning (incl. vision), latency/cost optimization, DeepSeek-R1 use, On Your Data, and evaluating/improving Foundry/Azure OpenAI chat apps |25| Decision Making | L62-L88 | Guides for choosing models, regions, deployments, costs, PTU, streaming, SDKs, and upgrade/migration paths to design, scale, and optimize Foundry and Azure OpenAI solutions. |26| Architecture & Design Patterns | L89-L98 | Architectural guidance for Foundry: multi-agent design, service/resource topology, high availability, and full BCDR (backup, recovery, DR, and resiliency) for Agent Service and Azure OpenAI workloads |27| Limits & Quotas | L99-L115 | Quotas, rate limits, and capacity for Foundry Agents/Models and Azure OpenAI (deployments, regions, VNets, batch, dynamic quota), plus model availability/retirement and how to request increases. |28| Security | L116-L163 | Security, privacy, and compliance for Foundry and Azure OpenAI: auth/RBAC, networking (VNet/Private Link), keys and Key Vault, guardrails/content filters, Azure Policy, and data handling. |29| Configuration | L164-L221 | Configuring, monitoring, and evaluating Foundry classic agents, models, tools, and infrastructure, including BYO resources, RAG, safety, tracing, and Azure OpenAI monitoring. |30| Integrations & Coding Patterns | L222-L342 | Patterns and code to integrate Foundry and Azure OpenAI with tools, data, and frameworks: search/RAG, files, SharePoint, Bing, MCP/OpenAPI, Functions/Logic Apps, SDKs, fine-tuning, and realtime audio. |31| Deployment | L343-L360 | Deploying Foundry hubs, projects, and models (managed/serverless), setting up agents and prompt flows, and automating deployments/evaluations via CLI, Bicep, Terraform, VS Code, and CI/CD. |3233### Troubleshooting34| Topic | URL |35|-------|-----|36| Resolve common issues in Microsoft Foundry (classic) | https://learn.microsoft.com/en-us/azure/foundry-classic/faq |37| Troubleshoot compute and usage issues in prompt flow | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/prompt-flow-troubleshoot |38| Troubleshoot Foundry deployments and monitoring issues | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/troubleshoot-deploy-and-monitor |39| Troubleshoot Foundry private endpoint connection errors | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/troubleshoot-secure-connection-project |40| Troubleshoot Azure OpenAI fine-tuning issues in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/fine-tuning-troubleshoot |41| Monitor and troubleshoot Risks & Safety in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/risks-safety-monitor |42| Resolve known issues and workarounds in Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/reference/foundry-known-issues |4344### Best Practices45| Topic | URL |46|-------|-----|47| Deploy and use DeepSeek-R1 reasoning model in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/tutorials/get-started-deepseek-r1 |48| Design effective system messages for Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/advanced-prompt-engineering |49| Apply safety system message templates in Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/safety-system-message-templates |50| Author safety-focused system messages in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/system-message |51| Apply safety evaluation when fine-tuning Foundry models | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/fine-tuning-safety-evaluation |52| Fine-tune GPT-4 vision models with image data | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/fine-tuning-vision |53| Optimize Azure OpenAI performance and latency | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/latency |54| Apply best practices for Azure OpenAI On Your Data | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/on-your-data-best-practices |55| Optimize Azure OpenAI predicted outputs for latency | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/predicted-outputs |56| Evaluate and improve Foundry-based chat apps with SDK | https://learn.microsoft.com/en-us/azure/foundry-classic/tutorials/copilot-sdk-evaluate |5758### Decision Making59| Topic | URL |60|-------|-----|61| Select Azure OpenAI models and regions for Foundry Agents | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/concepts/model-region-support |62| Decide when and how to fine-tune models in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/fine-tuning-overview |63| Use Foundry model benchmarks and leaderboards | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/model-benchmarks |64| Plan for Foundry model deprecation and retirement | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/model-lifecycle-retirement |65| Plan Microsoft Foundry classic rollout at scale | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/planning |66| Choose the right Azure resource type for Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/resource-types |67| Choose Microsoft Foundry deployment types and residency | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/concepts/deployment-types |68| Plan and manage model versioning in Foundry Models | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/concepts/model-versions |69| Plan and manage model versioning in Foundry Models | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/concepts/model-versions |70| Decide between GPT-5 and GPT-4.1 in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/model-choice-guide |71| Compare models with Foundry leaderboards | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/benchmark-model-in-catalog |72| Plan and manage costs for Microsoft Foundry hubs | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/costs-plan-manage |73| Choose Microsoft Foundry SDKs and endpoints | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/sdk-overview |74| Migrate from hub-based to new Foundry projects | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/migrate-project |75| Decide when and how to upgrade Azure OpenAI to Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/upgrade-azure-openai |76| Choose content streaming and filtering modes in Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/content-streaming |77| Enable and evaluate Foundry priority processing tiers | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/priority-processing |78| Evaluate 2024 Azure OpenAI provisioned throughput updates | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/provisioned-migration |79| Understand provisioned throughput for Foundry models | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/provisioned-throughput |80| Plan using your data with Azure OpenAI deployments | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/use-your-data |81| Plan PTU costs and capacity for Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/provisioned-throughput-onboarding |82| Migrate from preview to GA Realtime API protocol | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/realtime-audio-preview-api-migration-guide |83| Use Azure OpenAI reasoning models effectively | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/reasoning |8485### Architecture & Design Patterns86| Topic | URL |87|-------|-----|88| Design multi-agent systems with Foundry connected agents | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/connected-agents |89| Plan disaster recovery for Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/agent-service-disaster-recovery |90| Recover Foundry Agent Service from resource and data loss | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/agent-service-operator-disaster-recovery |91| Recover Foundry Agent Service from platform outages | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/agent-service-platform-disaster-recovery |92| Design high availability and resiliency for Foundry projects | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/high-availability-resiliency |93| Design BCDR architecture for Azure OpenAI workloads | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/business-continuity-disaster-recovery |9495### Limits & Quotas96| Topic | URL |97|-------|-----|98| Review quotas and limits for Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/quotas-limits |99| Evaluate Foundry classic with regional limits and VNet | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/evaluation-regions-limits-virtual-network |100| Reference quotas and limits for Foundry Models | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/quotas-limits |101| Manage and request quotas for Microsoft Foundry hub resources | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/hub-quota |102| Manage and increase model deployment quotas in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/quota |103| Review retired Azure OpenAI model availability | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/legacy-models |104| Azure OpenAI model availability and retirement schedule | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/model-retirements |105| Azure OpenAI FAQ with usage limits and policies | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/faq |106| Use Azure OpenAI global batch processing | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/batch |107| Use dynamic quota for Azure OpenAI deployments | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/dynamic-quota |108| Manage Azure OpenAI quota in Foundry classic | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/quota |109| Use reinforcement fine-tuning for reasoning models | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/reinforcement-fine-tuning |110| Azure OpenAI quotas and limits in Foundry Models | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/quotas-limits |111112### Security113| Topic | URL |114|-------|-----|115| Configure Browser Automation tool securely for Foundry agents | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/browser-automation |116| Securely use Foundry Computer Use tool with agents | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/computer-use |117| Set up private networking and VNet integration for Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/virtual-networks |118| Configure authentication and authorization in Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/authentication-authorization-foundry |119| Configure customer-managed keys for Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/encryption-keys-portal |120| Configure customer-managed keys for Foundry hub projects | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/hub-encryption-keys-portal |121| Configure RBAC for Microsoft Foundry hubs and projects | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/hub-rbac-foundry |122| Configure guardrails for Azure-sold Foundry models | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/model-catalog-content-safety |123| Assign and manage RBAC roles in Microsoft Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/rbac-foundry |124| Understand vulnerability management for Microsoft Foundry images | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/vulnerability-management |125| Use default safety policies for Foundry Models | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/concepts/default-safety-policies |126| Create custom Azure Policies to restrict Foundry model deployments | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/configure-deployment-policies |127| Configure keyless Entra ID authentication for Foundry models | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/configure-entra-id |128| Allow Foundry managed networks to access on-premises resources | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/access-on-premises-resources |129| Add Microsoft Foundry resources to a network security perimeter | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/add-foundry-to-network-security-perimeter |130| Apply Azure Policy to govern Foundry hubs and projects | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/azure-policy |131| Control Foundry model deployments with Azure Policy | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/built-in-policy-model-deployment |132| Understand data handling and privacy in Foundry models | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/concept-data-privacy |133| Configure managed network isolation for Foundry hubs | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/configure-managed-network |134| Configure Private Link for Microsoft Foundry projects | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/configure-private-link |135| Create and manage a Microsoft Foundry hub securely | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/create-azure-ai-resource |136| Create a secure Microsoft Foundry hub with managed VNet | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/create-secure-ai-hub |137| Create custom Azure Policy definitions for Foundry resources | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/custom-policy-definition |138| Disable shared key access to Foundry hub storage | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/disable-local-auth |139| Configure storage accounts and access for Foundry evaluations | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/evaluations-storage-account |140| Configure Private Link for Microsoft Foundry hubs | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/hub-configure-private-link |141| Set up managed virtual network for Foundry projects | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/managed-virtual-network |142| Use built-in Azure Policy to govern Foundry model deployments | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/model-deployment-policy |143| Configure the Content Safety tool in prompt flows | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/prompt-flow-tools/content-safety-tool |144| Secure configuration for Foundry playground chat on your data | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/secure-data-playground |145| Set up Azure Key Vault connection for Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/set-up-key-vault-connection |146| Use Content Credentials for Azure OpenAI images | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/content-credentials |147| Configure and use PII filtering in Foundry OpenAI | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/content-filter-personal-information |148| Understand default Guardrail safety policies in Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/default-safety-policies |149| Understand Azure OpenAI prompt transformation for image safety | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/prompt-transformation |150| Configure Azure OpenAI content filters and gating | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/content-filters |151| Configure Microsoft Entra ID auth for Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/managed-identity |152| Secure Azure OpenAI with virtual networks and private endpoints | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/network |153| Add Azure OpenAI to a network security perimeter | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/network-security-perimeter |154| Apply Azure RBAC roles to Azure OpenAI resources | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/role-based-access-control |155| Configure custom block lists for Azure OpenAI content filtering | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/use-blocklists |156| Apply copyright commitment mitigations for Azure OpenAI in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/responsible-ai/openai/customer-copyright-commitment |157| Understand data handling and privacy for Azure Direct Models | https://learn.microsoft.com/en-us/azure/foundry-classic/responsible-ai/openai/data-privacy |158| Understand limited access policy for Azure OpenAI in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/responsible-ai/openai/limited-access |159160### Configuration161| Topic | URL |162|-------|-----|163| Configure and troubleshoot capability hosts in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/concepts/capability-hosts |164| Configure standard agent setup with customer-managed resources | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/concepts/standard-agent-setup |165| Configure environment and infrastructure for Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/environment-setup |166| Monitor Foundry Agent Service with Azure Monitor and KQL | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/metrics |167| Configure Foundry Agent Service to use your own Azure resources | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/use-your-own-resources |168| Use Azure Monitor metrics and logs for Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/reference/monitor-service |169| Configure and use built-in Foundry evaluators | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/built-in-evaluators |170| Configure agent evaluators for Azure AI agents | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/evaluation-evaluators/agent-evaluators |171| Use Azure OpenAI graders for model evaluation | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/evaluation-evaluators/azure-openai-graders |172| Create and configure custom evaluators in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/evaluation-evaluators/custom-evaluators |173| Configure general-purpose evaluators for generative AI | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/evaluation-evaluators/general-purpose-evaluators |174| Configure RAG evaluators for relevance and groundedness | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/evaluation-evaluators/rag-evaluators |175| Configure risk and safety evaluators in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/evaluation-evaluators/risk-safety-evaluators |176| Use textual similarity evaluators in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/evaluation-evaluators/textual-similarity-evaluators |177| Configure and use endpoints for Foundry Models | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/concepts/endpoints |178| Configure Foundry model content filters and gated changes | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/configure-content-filters |179| Configure Foundry Models project connection settings | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/configure-project-connection |180| Configure Azure Monitor for Foundry model deployments | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/monitor-models |181| Upgrade AI project to use Foundry model deployments | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/quickstart-ai-project |182| Select SDKs and languages for Foundry Models | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/supported-languages |183| Configure bring-your-own Azure Storage for Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/bring-your-own-azure-storage-foundry |184| Configure BYOS for Speech and Language in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/bring-your-own-azure-storage-speech-language-services |185| Set up continuous evaluation for AI agents in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/continuous-evaluation-agents |186| Configure and manage Foundry compute instances | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/create-manage-compute |187| Configure and manage prompt flow compute sessions | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/create-manage-compute-session |188| Provision Microsoft Foundry (classic) with Terraform | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/create-resource-terraform |189| Add and manage data in Foundry hub-based projects | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/data-add |190| Configure cross-project access to serverless model APIs | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/deploy-models-serverless-connect |191| Create a Foundry hub via Azure ML SDK and CLI | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/create-hub-project-sdk |192| Generate synthetic and simulated data for Foundry evaluation | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/simulator-interaction-data |193| Trace and observe Foundry agents with OpenTelemetry | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/trace-agents-sdk |194| Enable tracing and feedback for prompt flow deployments | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/trace-production-sdk |195| Hide Foundry preview features using Azure tags | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/disable-preview-features |196| Create and use vector indexes for RAG in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/index-add |197| Configure continuous monitoring for Foundry AI applications | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/monitor-applications |198| Monitor quality and token usage for prompt flow apps | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/monitor-quality-safety |199| Use GPT-4 Turbo with Vision tool in prompt flows | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/prompt-flow-tools/azure-open-ai-gpt-4v-tool |200| Configure the Embedding tool in Foundry prompt flows | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/prompt-flow-tools/embedding-tool |201| Configure the Index Lookup tool for RAG flows | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/prompt-flow-tools/index-lookup-tool |202| Configure the LLM tool in Foundry prompt flows | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/prompt-flow-tools/llm-tool |203| Configure the Prompt tool in Foundry prompt flows | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/prompt-flow-tools/prompt-tool |204| Configure the Python tool in Foundry prompt flows | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/prompt-flow-tools/python-tool |205| Configure the Rerank tool to improve search results | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/prompt-flow-tools/rerank-tool |206| Enable and interpret Prompt Shields in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/content-filter-prompt-shields |207| Configure Azure Blob Storage for OpenAI Batch I/O | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/batch-blob-storage |208| Configure and run Azure OpenAI model evaluations | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/evaluations |209| Apply direct preference optimization to Azure OpenAI models | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/fine-tuning-direct-preference-optimization |210| Configure monitoring and logging for Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/monitor-openai |211| Configure network and access for On Your Data | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/on-your-data-configuration |212| Configure and use prompt caching in Azure OpenAI Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/prompt-caching |213| Create and tune provisioned deployments in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/provisioned-get-started |214| Configure reproducible output for Azure OpenAI chats | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/reproducible-output |215| Configure spillover traffic management for provisioned deployments | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/spillover-traffic-management |216| Configure Azure OpenAI monitoring data and metrics | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/monitor-openai-reference |217218### Integrations & Coding Patterns219| Topic | URL |220|-------|-----|221| Connect Foundry agents to existing Azure AI Search indexes | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/azure-ai-search |222| Ground Foundry agents with Azure AI Search content | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/azure-ai-search-samples |223| Integrate Azure Functions as tools with Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/azure-functions |224| Use Azure Functions and Storage Queues with Foundry agents | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/azure-functions-samples |225| Use Bing Search grounding tool with code samples | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/bing-code-samples |226| Configure Custom Bing Search grounding for agents | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/bing-custom-search |227| Call Custom Bing Search grounding tool from code | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/bing-custom-search-samples |228| Ground Foundry agents with Bing Search results | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/bing-grounding |229| Automate website tasks with Foundry Browser Automation tool | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/browser-automation-samples |230| Run Python code with Foundry Code Interpreter tool | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/code-interpreter |231| Use Computer Use tool with Azure AI Projects SDK | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/computer-use-samples |232| Configure deprecated Deep Research tool for agents | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/deep-research |233| Integrate Deep Research tool with Azure AI Projects SDK | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/deep-research-samples |234| Connect Foundry agents to Microsoft Fabric data agent | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/fabric |235| Configure and use Foundry file search tool | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/file-search |236| Upload files to Foundry file search from code | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/file-search-upload-files |237| Implement function calling with Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/function-calling |238| Connect Foundry agents to external MCP servers | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/model-context-protocol |239| MCP server integration code samples for Foundry agents | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/model-context-protocol-samples |240| Configure OpenAPI tools and auth for Foundry agents | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/openapi-spec |241| Use OpenAPI-based tools with Foundry agents in code | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/openapi-spec-samples |242| Ground Foundry agents with SharePoint content | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/sharepoint |243| Use SharePoint grounding tool with Foundry agents | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/sharepoint-samples |244| Trigger Foundry agents from Logic Apps events | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/triggers |245| Serverless API inference examples for Foundry Models | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/models-inference-examples |246| Call Foundry Models Responses API for text generation | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/generate-responses |247| Process images and audio in Foundry chat completions | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/use-chat-multi-modal |248| Use reasoning models with Foundry Models service | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/use-chat-reasoning |249| Generate text embeddings with Foundry Models | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/use-embeddings |250| Deploy and use FLUX image models in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/use-foundry-models-flux |251| Generate image embeddings with Foundry Models | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/use-image-embeddings |252| Use structured outputs with Foundry chat models | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/use-structured-outputs |253| Configure project connections in Foundry classic | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/connections-add |254| Evaluate AI agents using the Foundry SDK | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/agent-evaluate-sdk |255| Run scalable cloud evaluations with Foundry SDK | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/cloud-evaluation |256| Run local evaluations with Azure AI Evaluation SDK | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/evaluate-sdk |257| Build LangChain apps with Microsoft Foundry models | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/langchain |258| Connect LangGraph and LangChain apps to Foundry agents | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/langchain-agents |259| Integrate LlamaIndex with Microsoft Foundry models | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/llama-index |260| Run AI Red Teaming Agent in the cloud with Foundry SDK | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/run-ai-red-teaming-cloud |261| Run AI Red Teaming Agent locally with Azure AI SDK | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/run-scans-ai-red-teaming-agent |262| Use Semantic Kernel with Foundry model catalog | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/semantic-kernel |263| View OpenAI SDK traces with OpenTelemetry in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/trace-application |264| Configure MCP server tools for Foundry agents in VS Code | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/vs-code-agents-mcp |265| Deploy and use CXRReportGen healthcare AI model | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/healthcare-ai/deploy-cxrreportgen |266| Deploy and invoke MedImageInsight embeddings model | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/healthcare-ai/deploy-medimageinsight |267| Use MedImageParse medical image segmentation models | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/healthcare-ai/deploy-medimageparse |268| Create and manage hub-scoped connections in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/hub-connections-add |269| Migrate Azure AI Inference SDK apps to OpenAI SDK | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/model-inference-to-openai-migration |270| Use the Serp API tool within Foundry prompt flows | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/prompt-flow-tools/serp-api-tool |271| Use image-to-text models from Foundry catalog | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/use-image-models |272| Use Azure OpenAI v1 API in Foundry Models | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/api-version-lifecycle |273| Get started with Azure OpenAI audio generation | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/audio-completions-quickstart |274| Use Azure OpenAI authoring preview REST API in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/authoring-reference-preview |275| Interpret Guardrail annotations for Azure OpenAI in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/content-filter-annotations |276| Format prompts with document embeddings for Guardrails in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/content-filter-document-embedding |277| Use groundedness detection for RAG in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/content-filter-groundedness |278| Apply protected material detection to LLM outputs in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/content-filter-protected-material |279| Create Azure OpenAI Assistants with tools in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/assistant |280| Implement Assistants function calling in Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/assistant-functions |281| Trigger Azure Logic Apps from Foundry Assistants | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/assistants-logic-apps |282| Work with Azure OpenAI chat completion models | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/chatgpt |283| Run code with Azure OpenAI Assistants Code Interpreter | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/code-interpreter |284| Use Codex CLI and VS Code with Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/codex |285| Implement Computer Use agents in Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/computer-use |286| Use Azure OpenAI image generation and editing APIs | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/dall-e |287| Run deep research using Azure OpenAI Responses API | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/deep-research |288| Migrate from Azure.AI.OpenAI .NET 1.x beta to 2.x | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/dotnet-migration |289| Use Assistants file search with external knowledge | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/file-search |290| Test fine-tuned models using Chat Completions and Evaluations | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/fine-tune-test |291| Fine-tune Foundry models via Python, REST, or portal | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/fine-tuning |292| Fine-tune Azure OpenAI function calling in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/fine-tuning-functions |293| Use function calling with Azure OpenAI models | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/function-calling |294| Use Azure OpenAI vision-enabled chat models via API | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/gpt-with-vision |295| Configure Azure OpenAI JSON mode responses | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/json-mode |296| Migrate Azure OpenAI apps to OpenAI Python v1.x | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/migration |297| Migrate Azure OpenAI apps to OpenAI JavaScript v4 | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/migration-javascript |298| Use GPT Realtime API for low-latency audio | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/realtime-audio |299| Connect to GPT Realtime API via SIP | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/realtime-audio-sip |300| Integrate GPT Realtime audio via WebRTC in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/realtime-audio-webrtc |301| Connect to GPT Realtime API via WebSockets | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/realtime-audio-websockets |302| Call Azure OpenAI Responses API with tools and streaming | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/responses |303| Use stored completions and distillation in Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/stored-completions |304| Define and305306…(truncated)
luokai0