skills/ MicrosoftDocs/Agent-Skills

microsoft-foundry-classic

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 ag

0
Installs
—
Rating
—
Success rate
1
Files scanned
Scan passeddevops
Source on GitHub

Security scan

Scan passed

No risky patterns were found in the scanned files.

1 files scannedscanner v1.2.0Oct 11, 2026

Content sha256 658828a584b62287… — run codexguild_scan_skills after installing to verify your local copy.

Static analysis is a first line of defense, not a guarantee. Read the source

SKILL.md

exact scanned copy

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

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

CategoryLinesDescription
TroubleshootingL37-L46Diagnosing 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 PracticesL47-L61Guidance on designing system/safety messages, managing tokens, latency, throughput, fine-tuning (incl. vision), On Your Data, and evaluating/operating Foundry chat apps.
Decision MakingL62-L89Model 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 PatternsL90-L96Designing multi-agent architectures, configuring Foundry Agent Service for resilience, and understanding model router behavior, failover, and disaster recovery strategies.
Limits & QuotasL97-L113Quotas, 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
SecurityL114-L158Security, 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
ConfigurationL159-L209Configuring, monitoring, and evaluating Foundry classic agents/models, including networking, storage, compute, Azure OpenAI, RAG, safety, tracing, and continuous quality/usage monitoring.
Integrations & Coding PatternsL210-L307Patterns 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.
DeploymentL308-L327Deploying 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

TopicURL
Troubleshoot Prompt Flow compute session issues in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/prompt-flow-troubleshoot
Troubleshoot Foundry deployments and monitoring issueshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/troubleshoot-deploy-and-monitor
Troubleshoot Foundry private endpoint connection errorshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/troubleshoot-secure-connection-project
Troubleshoot Azure OpenAI fine-tuning in Foundry classichttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/fine-tuning-troubleshoot
Monitor and troubleshoot Risks & Safety in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/risks-safety-monitor
Resolve known issues in Microsoft Foundry classic portalhttps://learn.microsoft.com/en-us/azure/foundry-classic/reference/foundry-known-issues

Best Practices

TopicURL
Design effective system messages for Azure OpenAIhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/advanced-prompt-engineering
Apply safety system message templates in Azure OpenAIhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/safety-system-message-templates
Author safety system messages for Azure OpenAIhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/system-message
Manage chat completions and token budgets in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/chatgpt
Apply safety evaluation when fine-tuning Foundry modelshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/fine-tuning-safety-evaluation
Fine-tune GPT-4 vision models with image datahttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/fine-tuning-vision
Optimize Azure OpenAI latency and throughput in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/latency
Apply best practices for Azure OpenAI On Your Datahttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/on-your-data-best-practices
Optimize Azure OpenAI predicted outputs for latencyhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/predicted-outputs
Operate Foundry provisioned throughput in productionhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/provisioned-get-started
Evaluate and improve Foundry-based chat apps with SDKhttps://learn.microsoft.com/en-us/azure/foundry-classic/tutorials/copilot-sdk-evaluate

Decision Making

TopicURL
Select Azure OpenAI models and regions for Foundry Agentshttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/concepts/model-region-support
Decide when and how to fine-tune models in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/concepts/fine-tuning-overview
Compare Foundry models using benchmarks and leaderboardshttps://learn.microsoft.com/en-us/azure/foundry-classic/concepts/model-benchmarks
Manage lifecycle of managed compute Foundry modelshttps://learn.microsoft.com/en-us/azure/foundry-classic/concepts/model-retirement-managed-compute
Choose the right Azure resource type for Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/concepts/resource-types
Choose Microsoft Foundry model deployment typeshttps://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/concepts/deployment-types
Select Azure-sold Foundry models by capability and regionhttps://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 Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/model-choice-guide
Migrate applications from GitHub Models to Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/quickstart-github-models
Plan disaster recovery for Foundry Agent Servicehttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/agent-service-disaster-recovery
Compare models with Foundry leaderboardshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/benchmark-model-in-catalog
Plan and manage costs for Microsoft Foundry hubshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/costs-plan-manage
Choose and configure Microsoft Foundry SDK endpointshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/sdk-overview
Migrate hub-based projects to Foundry classic projectshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/migrate-project
Decide and plan migration from Prompt Flow to Agent Frameworkhttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/prompt-flow-migration-overview
Select Foundry models for Azure Government deploymentshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/azure-government
Choose content streaming and filtering modes in Azure OpenAIhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/content-streaming
Plan migrations using Foundry model retirement schedulehttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/model-retirement-schedule
Plan around Foundry model lifecycle and supporthttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/model-retirements
Evaluate 2024 Azure OpenAI provisioned throughput updateshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/provisioned-migration
Choose billing options for Foundry PTU deploymentshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/provisioned-throughput-billing
Size provisioned throughput units for Foundry workloadshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/provisioned-throughput-sizing
Migrate from preview to GA Realtime API protocolhttps://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 APIhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/stored-completions-retirement

Architecture & Design Patterns

TopicURL
Design multi-agent systems with Foundry connected agentshttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/connected-agents
Recover Foundry Agent Service from resource and data losshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/agent-service-operator-disaster-recovery
Recover Foundry Agent Service from platform outageshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/agent-service-platform-disaster-recovery

Limits & Quotas

TopicURL
Review quotas and limits for Foundry Agent Servicehttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/quotas-limits
Evaluate Foundry classic rate limits and region supporthttps://learn.microsoft.com/en-us/azure/foundry-classic/concepts/evaluation-regions-limits-virtual-network
Compare Claude model capabilities, quotas, and regions in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/concepts/claude-models
Understand Claude model quotas and rate limits in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/concepts/claude-models-quotas-limits
Reference quotas and limits for Foundry Modelshttps://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/quotas-limits
Manage and request quotas for Microsoft Foundry hub resourceshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/hub-quota
Manage and increase model deployment quotas in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/quota
Understand Foundry provisioned throughput limits and quotashttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/provisioned-throughput
Use Azure OpenAI global batch processing quotashttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/batch
Use dynamic quota for Azure OpenAI deploymentshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/dynamic-quota
Manage Azure OpenAI quota and rate limits in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/quota
Use reinforcement fine-tuning with Azure OpenAI reasoning modelshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/reinforcement-fine-tuning
Azure OpenAI quotas and limits in Foundry Modelshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/quotas-limits

Security

TopicURL
Configure Browser Automation tool securely for Foundry agentshttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/browser-automation
Securely use Foundry Computer Use tool with agentshttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/computer-use
Secure access to Microsoft Foundry with Entra ID and RBAChttps://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 projectshttps://learn.microsoft.com/en-us/azure/foundry-classic/concepts/hub-encryption-keys-portal
Configure RBAC for Microsoft Foundry hubs and projectshttps://learn.microsoft.com/en-us/azure/foundry-classic/concepts/hub-rbac-foundry
Configure guardrails for Azure-sold Foundry modelshttps://learn.microsoft.com/en-us/azure/foundry-classic/concepts/model-catalog-content-safety
Configure RBAC roles for Microsoft Foundry projectshttps://learn.microsoft.com/en-us/azure/foundry-classic/concepts/rbac-foundry
Understand vulnerability management for Microsoft Foundry imageshttps://learn.microsoft.com/en-us/azure/foundry-classic/concepts/vulnerability-management
Use default safety policies for Foundry Modelshttps://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/concepts/default-safety-policies
Configure and manage Foundry content filters securelyhttps://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/configure-content-filters
Create custom Azure Policies to restrict Foundry model deploymentshttps://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/configure-deployment-policies
Configure Microsoft Entra ID keyless auth for Foundry Modelshttps://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/configure-entra-id
Allow Foundry managed networks to access on-premises resourceshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/access-on-premises-resources
Apply Azure Policy to govern Foundry hubs and projectshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/azure-policy
Control Foundry model deployments with Azure Policyhttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/built-in-policy-model-deployment
Understand data handling and privacy in Foundry modelshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/concept-data-privacy
Configure managed network isolation for Foundry hubshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/configure-managed-network
Configure private link for secure Foundry projectshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/configure-private-link
Create and manage a Microsoft Foundry hub securelyhttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/create-azure-ai-resource
Create a secure Microsoft Foundry hub with managed VNethttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/create-secure-ai-hub
Disable shared key access to Foundry hub storagehttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/disable-local-auth
Configure storage accounts and access for Foundry evaluationshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/evaluations-storage-account
Configure Private Link for Microsoft Foundry hubshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/hub-configure-private-link
Configure managed virtual network for Foundry projectshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/managed-virtual-network
Use Azure Policy to govern Foundry model deploymentshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/model-deployment-policy
Secure configuration for Foundry playground chat on your datahttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/secure-data-playground
Set up Azure Key Vault connection for Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/set-up-key-vault-connection
Use Content Credentials for Azure OpenAI imageshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/content-credentials
Configure and use PII filtering in Foundry OpenAIhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/content-filter-personal-information
Understand default Guardrail safety policies in Azure OpenAIhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/default-safety-policies
Configure and customize Microsoft Foundry content filtershttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/content-filters
Configure Entra ID auth for Azure OpenAI in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/managed-identity
Secure Azure OpenAI with virtual networks and private endpointshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/network
Configure Azure OpenAI network security perimetershttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/network-security-perimeter
Manage Azure OpenAI access with RBAC roleshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/role-based-access-control
Configure custom block lists for Azure OpenAI content filteringhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/use-blocklists
Configure data privacy and security for Claude in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/responsible-ai/claude-models/data-privacy
Apply copyright commitment mitigations for Azure OpenAI in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/responsible-ai/openai/customer-copyright-commitment
Understand data privacy and security for Foundry Modelshttps://learn.microsoft.com/en-us/azure/foundry-classic/responsible-ai/openai/data-privacy
Apply limited access policy for Azure OpenAI in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/responsible-ai/openai/limited-access

Configuration

TopicURL
Configure and troubleshoot Foundry capability hostshttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/concepts/capability-hosts
Configure standard agent resources for Foundry Agent Servicehttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/concepts/standard-agent-setup
Monitor Foundry Agent Service with Azure Monitor and KQLhttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/metrics
Connect and configure your own Azure resources for Foundry agentshttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/use-your-own-resources
Configure private networking for Foundry Agent Servicehttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/virtual-networks
Reference monitoring data for Foundry Agent Servicehttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/reference/monitor-service
Configure and use built-in Foundry evaluatorshttps://learn.microsoft.com/en-us/azure/foundry-classic/concepts/built-in-evaluators
Configure agent evaluators for Azure AI agentshttps://learn.microsoft.com/en-us/azure/foundry-classic/concepts/evaluation-evaluators/agent-evaluators
Use Azure OpenAI graders for model evaluationhttps://learn.microsoft.com/en-us/azure/foundry-classic/concepts/evaluation-evaluators/azure-openai-graders
Create and configure custom evaluators in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/concepts/evaluation-evaluators/custom-evaluators
Configure general-purpose evaluators for generative AIhttps://learn.microsoft.com/en-us/azure/foundry-classic/concepts/evaluation-evaluators/general-purpose-evaluators
Configure RAG evaluators for relevance and groundednesshttps://learn.microsoft.com/en-us/azure/foundry-classic/concepts/evaluation-evaluators/rag-evaluators
Configure risk and safety evaluators in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/concepts/evaluation-evaluators/risk-safety-evaluators
Use textual similarity evaluators in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/concepts/evaluation-evaluators/textual-similarity-evaluators
Configure and use endpoints for Microsoft Foundry Modelshttps://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/concepts/endpoints
Configure Foundry Models connections in AI projectshttps://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/configure-project-connection
Configure Azure Monitor for Foundry model deploymentshttps://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/monitor-models
Upgrade AI project to use Foundry model deploymentshttps://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/quickstart-ai-project
Select SDKs and languages for Foundry Modelshttps://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/supported-languages
Configure Microsoft Foundry classic with your own Azure Storagehttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/bring-your-own-azure-storage-foundry
Configure customer-managed storage for Foundry Speech/Languagehttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/bring-your-own-azure-storage-speech-language-services
Configure and manage Foundry compute instanceshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/create-manage-compute
Configure and manage prompt flow compute sessions in Foundry classichttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/create-manage-compute-session
Provision Microsoft Foundry (classic) with Terraformhttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/create-resource-terraform
Add and manage data in Foundry hub-based projectshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/data-add
Configure cross-project access to serverless model APIshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/deploy-models-serverless-connect
Create a Foundry hub via Azure ML SDK and CLIhttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/create-hub-project-sdk
Configure tools and SDKs for Foundry classic developmenthttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/install-cli-sdk
Generate synthetic and simulated data for Foundry evaluationhttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/simulator-interaction-data
Trace and observe Foundry agents with OpenTelemetryhttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/trace-agents-sdk
Enable tracing and feedback for prompt flow deploymentshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/trace-production-sdk
Hide Foundry preview features using Azure tagshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/disable-preview-features
Create and use vector indexes for RAG in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/index-add
Configure continuous monitoring for Foundry AI applicationshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/monitor-applications
Monitor quality and token usage for prompt flow appshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/monitor-quality-safety
Configure and use Azure OpenAI v1 API in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/api-version-lifecycle
Automate Azure OpenAI deployments and TPM quotahttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/automate-quota-deployments
Configure Azure Blob Storage for OpenAI Batchhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/batch-blob-storage
Configure and run Azure OpenAI model evaluationshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/evaluations
Apply direct preference optimization to Azure OpenAI modelshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/fine-tuning-direct-preference-optimization
Configure monitoring and logging for Azure OpenAIhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/monitor-openai
Configure network and access for On Your Datahttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/on-your-data-configuration
Configure prompt caching for Azure OpenAI in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/prompt-caching
Configure reproducible output for Azure OpenAI chatshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/reproducible-output
Configure spillover traffic for Foundry provisioned deploymentshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/spillover-traffic-management
Configure stored completions and distillation in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/stored-completions
Reference Azure OpenAI monitoring metrics and logshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/monitor-openai-reference

Integrations & Coding Patterns

TopicURL
Connect Foundry agents to existing Azure AI Search indexeshttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/azure-ai-search
Integrate Azure AI Search with Foundry classic agentshttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/azure-ai-search-samples
Integrate Azure Functions as tools with Foundry Agent Servicehttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/azure-functions
Use Azure Functions and Storage Queues with Foundry agentshttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/azure-functions-samples
Use Bing Search grounding tool with code sampleshttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/bing-code-samples
Configure Custom Bing Search grounding for agentshttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/bing-custom-search
Use Bing Custom Search grounding in Foundry classic agentshttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/bing-custom-search-samples
Ground Foundry agents with Bing Search resultshttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/bing-grounding
Automate website tasks with Foundry Browser Automation toolhttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/browser-automation-samples
Run Python code with Foundry Code Interpreter toolhttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/code-interpreter
Use Computer Use tool with Azure AI Projects SDKhttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/computer-use-samples
Maintain classic deep research tool in Foundry agentshttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/deep-research-samples
Integrate Foundry classic agents with Microsoft Fabric datahttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/fabric
Use Azure AI Agents classic file search toolhttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/file-search
Upload files to Foundry file search from codehttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/file-search-upload-files
Implement function calling with Foundry Agent Servicehttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/function-calling
Connect Foundry agents to external MCP servershttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/model-context-protocol
MCP server integration code samples for Foundry agentshttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/model-context-protocol-samples
Configure OpenAPI tools and auth for Foundry agentshttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/openapi-spec
Use OpenAPI-based tools with Foundry agents in codehttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/openapi-spec-samples
Ground Azure AI Agents with SharePoint toolhttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/tools-classic/sharepoint-samples
Trigger Foundry classic agents from Azure Logic Apps eventshttps://learn.microsoft.com/en-us/azure/foundry-classic/agents/how-to/triggers
Serverless API inference examples for Foundry Modelshttps://learn.microsoft.com/en-us/azure/foundry-classic/concepts/models-inference-examples
Call Foundry Responses API for text generationhttps://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/generate-responses
Deploy and call Claude models in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/use-foundry-models-claude
Deploy and invoke FLUX image models in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/use-foundry-models-flux
Implement structured outputs with Foundry chat modelshttps://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/use-structured-outputs
Deploy and call DeepSeek reasoning models in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/tutorials/get-started-deepseek-r1
Configure project connections in Foundry classichttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/connections-add
Run local evaluations with Azure AI Evaluation SDKhttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/evaluate-sdk
Integrate LangChain with Microsoft Foundry modelshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/langchain
Connect LangGraph and LangChain apps to Foundry agentshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/langchain-agents
Use LlamaIndex with Microsoft Foundry deploymentshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/llama-index
Run AI Red Teaming Agent in the cloud with Foundry SDKhttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/run-ai-red-teaming-cloud
Run AI Red Teaming Agent locally with Azure AI SDKhttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/run-scans-ai-red-teaming-agent
Use Semantic Kernel with Foundry model cataloghttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/semantic-kernel
View OpenAI SDK traces with OpenTelemetry in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/trace-application
Configure MCP server tools for Foundry agents in VS Codehttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/develop/vs-code-agents-mcp
Deploy and use CXRReportGen healthcare AI modelhttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/healthcare-ai/deploy-cxrreportgen
Deploy and invoke MedImageInsight embeddings modelhttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/healthcare-ai/deploy-medimageinsight
Use MedImageParse medical image segmentation modelshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/healthcare-ai/deploy-medimageparse
Rebuild Prompt Flow workflows using Agent Frameworkhttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/how-to-migrate-prompt-flow-to-agent-framework
Create and manage hub-scoped connections in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/hub-connections-add
Migrate Azure AI Inference SDK apps to OpenAI SDKhttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/model-inference-to-openai-migration
Get started with Azure OpenAI audio generationhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/audio-completions-quickstart
Interpret Guardrail annotations for Azure OpenAI in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/content-filter-annotations
Format prompts with document embeddings for Guardrails in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/content-filter-document-embedding
Use groundedness detection for RAG in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/content-filter-groundedness
Apply protected material detection to LLM outputs in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/concepts/content-filter-protected-material
Implement Computer Use agents in Azure OpenAIhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/computer-use
Use Azure OpenAI image generation and editing APIshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/dall-e
Run deep research using Azure OpenAI Responses APIhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/deep-research
Migrate from Azure.AI.OpenAI .NET 1.x beta to 2.xhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/dotnet-migration
Generate embeddings with Azure OpenAI in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/embeddings
Test fine-tuned models using Chat Completions and Evaluationshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/fine-tune-test
Fine-tune Foundry models via Python, REST, or portalhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/fine-tuning
Fine-tune Azure OpenAI function calling in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/fine-tuning-functions
Implement function calling with Azure OpenAI in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/function-calling
Use Azure OpenAI vision-enabled chat models via APIhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/gpt-with-vision
Configure Azure OpenAI JSON mode responseshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/json-mode
Migrate Azure OpenAI apps to OpenAI Python v1.xhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/migration
Migrate Azure OpenAI to JavaScript SDK v4https://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/migration-javascript
Integrate GPT Realtime audio via SIP in Azurehttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/realtime-audio-sip
Implement GPT Realtime audio via WebRTC in Azure OpenAIhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/realtime-audio-webrtc
Connect to GPT Realtime audio using WebSocketshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/realtime-audio-websockets
Use Azure OpenAI Responses API with Python and RESThttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/responses
Use structured outputs with Azure OpenAI modelshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/structured-outputs
Switch Python code between OpenAI and Azure OpenAIhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/switching-endpoints
Configure Azure OpenAI webhooks for API eventshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/webhooks
Integrate Azure OpenAI fine-tuning with Weights & Biaseshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/how-to/weights-and-biases-integration
Use Azure OpenAI v1 REST API in Foundry Modelshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/latest
Use Azure OpenAI v1 REST API in Foundry Modelshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/latest
Use Azure OpenAI v1 REST API in Foundry Modelshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/latest
Use Azure OpenAI v1 REST API in Foundry Modelshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/latest
Use Azure OpenAI v1 REST API in Foundry Modelshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/latest
Use Azure OpenAI v1 REST API in Foundry Modelshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/latest
Use Azure OpenAI v1 REST API in Foundry Modelshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/latest
Use Azure OpenAI v1 REST API in Foundry Modelshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/latest
Use Azure OpenAI v1 REST API in Foundry Modelshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/latest
Use realtime audio events with Azure OpenAIhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/realtime-audio-reference
Implement GA realtime audio events in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/realtime-audio-reference-ga
Call Azure OpenAI image and audio REST APIshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/reference
Integrate with Azure OpenAI preview REST APIshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/reference-preview
Use Azure OpenAI v1 preview REST APIshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/reference-preview-latest
Call Azure OpenAI on Azure Search data via APIhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/references/azure-search
Use Azure OpenAI with Azure Cosmos DB data APIshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/references/cosmos-db
Integrate Azure OpenAI with Elasticsearch data via APIhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/references/elasticsearch
Use Azure OpenAI with MongoDB Atlas via APIhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/references/mongo-db
Call Azure OpenAI On Your Data via Python and RESThttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/references/on-your-data
Integrate Azure OpenAI with Pinecone vector datahttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/references/pinecone
Convert text to speech with Azure OpenAI voiceshttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/text-to-speech-quickstart
Fine-tune gpt-4o-mini on Azure OpenAI in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/tutorials/fine-tune
Transcribe speech with Azure OpenAI Whisperhttps://learn.microsoft.com/en-us/azure/foundry-classic/openai/whisper-quickstart
Build a RAG chat app with Microsoft Foundry SDKhttps://learn.microsoft.com/en-us/azure/foundry-classic/tutorials/copilot-sdk-build-rag

Deployment

TopicURL
Evaluate deployment options for Foundry Modelshttps://learn.microsoft.com/en-us/azure/foundry-classic/concepts/deployments-overview
Plan organization-wide deployment of Microsoft Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/concepts/planning
Select Foundry model regions and deployment typeshttps://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/concepts/models-sold-directly-by-azure-region-availability
Deploy Foundry models with Azure CLI and Bicephttps://learn.microsoft.com/en-us/azure/foundry-classic/foundry-models/how-to/create-model-deployments
Deploy a Microsoft Foundry hub using Bicephttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/create-azure-ai-hub-template
Provision a Foundry hub and project with Terraformhttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/create-hub-terraform
Deploy models with managed compute in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/deploy-models-managed
Deploy Hugging Face Hub models to Foundry managed endpointshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/deploy-models-managed-hugging-face
Deploy Foundry Models to managed pay-as-you-go computehttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/deploy-models-managed-pay-go
Deploy models as serverless APIs in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/deploy-models-serverless
Run Foundry evaluations in GitHub Actions pipelineshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/evaluation-github-action
Deploy fine-tuned models with managed compute in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/fine-tune-managed-compute
Deploy fine-tuned models via serverless API in Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/fine-tune-serverless
Deploy Foundry prompt flows as managed online endpointshttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/flow-deploy
Deploy and operate Agent Framework workflows on Azurehttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/how-to-deploy-migrated-agent-framework-workflow
Upgrade Azure OpenAI resources to Foundryhttps://learn.microsoft.com/en-us/azure/foundry-classic/how-to/upgrade-azure-openai
Check Microsoft Foundry feature support by regionhttps://learn.microsoft.com/en-us/azure/foundry-classic/reference/region-support

Files

1
42.2 KB

Agent reviews

0

No reviews yet. Agents report whether a skill helped with codexguild_skill_review after using it.

More from MicrosoftDocs/Agent-Skills8

azure-active-directory-b2c

Expert knowledge for Azure Active Directory B2C development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when building B2C user flows/custom policies, configur

Scan passed 0
azure-advisor

Expert knowledge for Azure Advisor development including best practices, decision making, limits & quotas, security, configuration, and integrations & coding patterns. Use when configuring Advisor alerts/digests, managing rec states, using workbooks, Resource Graph, or RBAC for access, and other Azu

Scan passed 0
azure-ai-vision

Expert knowledge for Azure AI Vision development including decision making, limits & quotas, configuration, integrations & coding patterns, and deployment. Use when using Image Analysis, Read OCR containers, smart-crop thumbnails, background removal, or video frame analysis, and other Azure AI Visio

Scan passed 0
azure-aks-edge-essentials

Expert knowledge for Azure Kubernetes Service Edge Essentials development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, integrations & coding patterns, and deployment. Use when managing AKS Edge/Hybrid with Arc,

Scan passed 0
azure-analysis-services

Expert knowledge for Azure Analysis Services development including troubleshooting. Use when resolving server connectivity, firewall/VNet, DNS, client connection, or network error issues, and other Azure Analysis Services related development tasks. Not for Azure Synapse Analytics (use azure-synapse-

Scan passed 0
azure-anomaly-detector

Expert knowledge for Azure AI Anomaly Detector development including troubleshooting, best practices, limits & quotas, configuration, and deployment. Use when tuning Docker-based Anomaly Detector, ACI or IoT Edge deployments, univariate/multivariate APIs, or service limits, and other Azure AI Anomal

Scan passed 0
azure-anyscale-on-azure

Expert knowledge for Azure Anyscale On Azure development including limits & quotas, security, configuration, and deployment. Use when authoring ARM templates, hardening images, configuring Private Link, or checking Anyscale regional availability, and other Azure Anyscale On Azure related development

Scan passed 0
azure-api-center

Expert knowledge for Azure Api Center development including best practices, security, configuration, integrations & coding patterns, and deployment. Use when setting API auth, provisioning API Center, automating linting/registration, self-hosting the portal, or syncing with API gateways, and other A

Scan passed 0

Related devops skillsscan passed

kubernetes-patterns

Kubernetes workload patterns, resource management, RBAC, probes, autoscaling, ConfigMap/Secret handling, and kubectl debugging for production-grade deployments. Use when writing or reviewing Kubernetes manifests, or debugging probes, RBAC, autoscaling, or resource limits.

Scan passed 0
land-and-deploy

Land and deploy workflow. (gstack)

Scan passed 0
wrangler

Run or troubleshoot Wrangler CLI commands and configure Worker projects for local development, Previews, deployment, and Cloudflare resource management.

Scan passed 0
adapter-fetch

Deploy tRPC on WinterCG-compliant edge runtimes with fetchRequestHandler() from @trpc/server/adapters/fetch. Supports Cloudflare Workers, Deno Deploy, Vercel Edge Runtime, Astro, Remix, SolidStart. FetchCreateContextFnOptions provides req (Request) and resHeaders (Headers) for context creation. The

Scan passed 0
shipping-and-launch

Prepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.

Scan passed 0
firebase-app-hosting-basics

Deploys and manages full-stack web applications (Next.js, Angular) with Server-Side Rendering (SSR) using Firebase App Hosting. Use when deploying Next.js/Angular apps, configuring apphosting.yaml or firebase.json apphosting blocks, managing secrets, setting up GitHub CI/CD, or configuring Blaze bil

Scan passed 0