| 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. |
| 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 |
| 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. |
| 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 |
| 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. |
| 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. |
| Configuration | L164-L221 | Configuring, monitoring, and evaluating Foundry classic agents, models, tools, and infrastructure, including BYO resources, RAG, safety, tracing, and Azure OpenAI monitoring. |
| 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. |
| 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. |