microsoft-foundry-classic

# Microsoft Foundry Classic Skill This 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. ## 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](https://github.com/MicrosoftDocs/mcp/blob/main/README.md) 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-L46 | Diagnosing and fixing Foundry classic issues: prompt flow compute, deployments/monitoring, private endpoints, Azure OpenAI (incl. fine-tuning), risks & safety alerts, and known portal bugs. | | Best Practices | L47-L61 | Guidance on designing system/safety messages, managing tokens, latency, throughput, fine-tuning (incl. vision), On Your Data, and evaluating/operating Foundry chat apps. | | Decision Making | L62-L89 | Model and platform decision guides: choosing Foundry/Azure OpenAI models, regions, deployments, billing and PTU sizing, migrations, lifecycle/retirement, DR, and SDK/endpoint options. | | Architecture & Design Patterns | L90-L96 | Designing multi-agent architectures, configuring Foundry Agent Service for resilience, and understanding model router behavior, failover, and disaster recovery strategies. | | Limits & Quotas | L97-L113 | Quotas, rate limits, and regional availability for Foundry Agents, Models, Claude, and Azure OpenAI, plus how to manage, increase, and use dynamic/provisioned throughput and batch limits | | Security | L114-L158 | Security, privacy, and compliance for Foundry: RBAC/Entra auth, managed networks/Private Link, CMK and storage, Azure Policy guardrails, content filters/PII, and Azure OpenAI/Claude protections | | Configuration | L159-L209 | Configuring, monitoring, and evaluating Foundry classic agents/models, including networking, storage, compute, Azure OpenAI, RAG, safety, tracing, and continuous quality/usage monitoring. | | Integrations & Coding Patterns | L210-L307 | Patterns and code for integrating Foundry/Agents with Azure AI Search, Bing, SharePoint, MCP/OpenAPI tools, Azure OpenAI (chat, audio, vision, fine-tuning), and external data/SDKs like LangChain, SK, and RAG. | | Deployment | L308-L327 | Deploying Foundry hubs/models at scale: regions, deployment types, Bicep/Terraform/CLI, managed and serverless compute, HF models, fine-tunes, evaluations, and region feature support | ### Troubleshooting | Topic | URL | |-------|-----| | Troubleshoot Prompt Flow compute session issues in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/prompt-flow-troubleshoot | | Troubleshoot Foundry deployments and monitoring issues | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/troubleshoot-deploy-and-monitor | | Troubleshoot Foundry private endpoint connection errors | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/troubleshoot-secure-connection-project | | Troubleshoot Azure OpenAI fine-tuning in Foundry classic | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/fine-tuning-troubleshoot | | Monitor and troubleshoot Risks & Safety in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/risks-safety-monitor | | Resolve known issues in Microsoft Foundry classic portal | https://learn.microsoft.com/en-us/azure/foundry-classic/reference/foundry-known-issues | ### Best Practices | Topic | URL | |-------|-----| | Design effective system messages for Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/advanced-prompt-engineering | | Apply safety system message templates in Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/safety-system-message-templates | | Author safety system messages for Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/system-message | | Manage chat completions and token budgets in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/chatgpt | | Apply safety evaluation when fine-tuning Foundry models | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/fine-tuning-safety-evaluation | | Fine-tune GPT-4 vision models with image data | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/fine-tuning-vision | | Optimize Azure OpenAI latency and throughput in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/latency | | 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 | | Optimize Azure OpenAI predicted outputs for latency | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/predicted-outputs | | Operate Foundry provisioned throughput in production | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/provisioned-get-started | | Evaluate and improve Foundry-based chat apps with SDK | https://learn.microsoft.com/en-us/azure/foundry-classic/tutorials/copilot-sdk-evaluate | ### Decision Making | Topic | URL | |-------|-----| | Select Azure OpenAI models and regions for Foundry Agents | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/concepts/model-region-support | | Decide when and how to fine-tune models in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/fine-tuning-overview | | Compare Foundry models using benchmarks and leaderboards | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/model-benchmarks | | Manage lifecycle of managed compute Foundry models | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/model-retirement-managed-compute | | Choose the right Azure resource type for Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/resource-types | | Choose Microsoft Foundry model deployment types | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/concepts/deployment-types | | Select Azure-sold Foundry models by capability and region | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/concepts/models-sold-directly-by-azure | | Choose 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 | | Migrate applications from GitHub Models to Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/quickstart-github-models | | Plan disaster recovery for Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/agent-service-disaster-recovery | | Compare models with Foundry leaderboards | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/benchmark-model-in-catalog | | Plan and manage costs for Microsoft Foundry hubs | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/costs-plan-manage | | Choose and configure Microsoft Foundry SDK endpoints | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/sdk-overview | | Migrate hub-based projects to Foundry classic projects | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/migrate-project | | Decide and plan migration from Prompt Flow to Agent Framework | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/prompt-flow-migration-overview | | Select Foundry models for Azure Government deployments | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/azure-government | | Choose content streaming and filtering modes in Azure OpenAI | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/content-streaming | | Plan migrations using Foundry model retirement schedule | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/model-retirement-schedule | | Plan around Foundry model lifecycle and support | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/model-retirements | | Evaluate 2024 Azure OpenAI provisioned throughput updates | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/provisioned-migration | | Choose billing options for Foundry PTU deployments | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/provisioned-throughput-billing | | Size provisioned throughput units for Foundry workloads | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/provisioned-throughput-sizing | | 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 | | Decide migration path from stored completions to Responses API | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/stored-completions-retirement | ### Architecture & Design Patterns | Topic | URL | |-------|-----| | Design multi-agent systems with Foundry connected agents | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/connected-agents | | 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 | | Recover Foundry Agent Service from platform outages | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/agent-service-platform-disaster-recovery | ### Limits & Quotas | Topic | URL | |-------|-----| | Review quotas and limits for Foundry Agent Service | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/quotas-limits | | Evaluate Foundry classic rate limits and region support | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/evaluation-regions-limits-virtual-network | | Compare Claude model capabilities, quotas, and regions in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/concepts/claude-models | | Understand Claude model quotas and rate limits in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/concepts/claude-models-quotas-limits | | Reference quotas and limits for Foundry Models | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/quotas-limits | | Manage and request quotas for Microsoft Foundry hub resources | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/hub-quota | | Manage and increase model deployment quotas in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/quota | | Understand Foundry provisioned throughput limits and quotas | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/provisioned-throughput | | Use Azure OpenAI global batch processing quotas | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/batch | | Use dynamic quota for Azure OpenAI deployments | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/dynamic-quota | | Manage Azure OpenAI quota and rate limits in Foundry | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/quota | | Use reinforcement fine-tuning with Azure OpenAI reasoning models | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/reinforcement-fine-tuning | | Azure OpenAI quotas and limits in Foundry Models | https://learn.microsoft.com/en-us/azure/foundry-classic/openai/quotas-limits | ### Security | Topic | URL | |-------|-----| | Configure Browser Automation tool securely for Foundry agents | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/browser-automation | | Securely use Foundry Computer Use tool with agents | https://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/computer-use | | Secure access to Microsoft Foundry with Entra ID and RBAC | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/authentication-authorization-foundry | | Configure customer-managed keys for Microsoft Foundry (classic) | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/encryption-keys-portal | | Configure customer-managed keys for Foundry hub projects | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/hub-encryption-keys-portal | | Configure RBAC for Microsoft Foundry hubs and projects | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/hub-rbac-foundry | | Configure guardrails for Azure-sold Foundry models | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/model-catalog-content-safety | | Configure RBAC roles for Microsoft Foundry projects | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/rbac-foundry | | Understand vulnerability management for Microsoft Foundry images | https://learn.microsoft.com/en-us/azure/foundry-classic/concepts/vulnerability-management | | Use default safety policies for Foundry Models | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/concepts/default-safety-policies | | Configure and manage Foundry content filters securely | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/configure-content-filters | | 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 | | Configure Microsoft Entra ID keyless auth for Foundry Models | https://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/configure-entra-id | | Allow Foundry managed networks to access on-premises resources | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/access-on-premises-resources | | Apply Azure Policy to govern Foundry hubs and projects | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/azure-policy | | Control Foundry model deployments with Azure Policy | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/built-in-policy-model-deployment | | Understand data handling and privacy in Foundry models | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/concept-data-privacy | | Configure managed network isolation for Foundry hubs | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/configure-managed-network | | Configure private link for secure Foundry projects | https://learn.microsoft.com/en-us/azure/foundry-classic/how-to/configure-private-link |