| Troubleshooting | L37-L46 | Diagnosing and fixing hosted agent, evaluation/observability, webhook, and service issues, including health checks, recovery from data loss, and known bugs/workarounds. |
| Best Practices | L47-L61 | Best practices for configuring and tuning Foundry agents: tools, routing, system messages, safety, evaluation, latency/throughput, and operating provisioned deployments. |
| Decision Making | L62-L105 | Guides for choosing models, deployments, hosting, networking, billing modes, and upgrade/migration paths (Assistants→Foundry, preview→GA, Azure OpenAI→Foundry), plus cost/perf optimization and DR. |
| Architecture & Design Patterns | L106-L113 | Design patterns for secure, scalable Foundry agents: VNet networking, private retrieval with Foundry IQ, shared session pooling, and high availability architectures. |
| Limits & Quotas | L114-L133 | Quotas, rate limits, regions, and throughput settings for agents, models (Claude, Azure OpenAI, partner), vector stores, sessions, AI Gateway, and evaluation, including gov/enterprise options. |
| Security | L134-L181 | Identity, RBAC, networking, guardrails, data privacy, compliance, and policy controls for securing Foundry agents, models, tools, traces, and infrastructure. |
| Configuration | L182-L250 | Configuring and operating Foundry agents and models: YAML schemas, runtime contracts, networking, storage, observability, evaluations, OpenTelemetry, Azure OpenAI, and private/managed connectivity. |
| Integrations & Coding Patterns | L251-L341 | Patterns and code to integrate Foundry agents and models with tools, data, MCP, Azure/OpenAI APIs, tracing, memory, voice, search, and external services for end-to-end agent solutions. |
| Deployment | L342-L367 | Deploying and managing Foundry hosted agents and models: infrastructure setup, CI/CD, private registries, publishing to Copilot/Teams, evaluations, red teaming, and healthcare/model-specific deployments. |