agentic-ai-immersion

Unified Azure OpenAI model deployment skill with intelligent intent-based routing. Handles quick preset deployments, fully customized deployments (version/SKU/capacity/RAI policy), and capacity discovery across regions and projects. USE FOR: deploy model, deploy gpt, create deployment, model deployment, deploy openai model, set up model, provision model, find capacity, check model availability, where can I deploy, best region for model, capacity analysis. DO NOT USE FOR: listing existing deployments (use foundry_models_deployments_list MCP tool), deleting deployments, agent creation (use agent/create), project creation (use project/create).

Deploy, evaluate, and manage Foundry agents end-to-end: Docker build, ACR push, hosted/prompt agent create, container start, batch eval, continuous eval, prompt optimizer workflows, agent.yaml, dataset curation from traces. USE FOR: deploy agent to Foundry, hosted agent, create agent, invoke agent, evaluate agent, run batch eval, continuous eval, continuous monitoring, continuous eval status, optimize prompt, improve prompt, prompt optimizer, optimize agent instructions, improve agent instructions, optimize system prompt, deploy model, Foundry project, RBAC, role assignment, permissions, quota, capacity, region, troubleshoot agent, deployment failure, create dataset from traces, dataset versioning, eval trending, create AI Services, Cognitive Services, create Foundry resource, provision resource, knowledge index, agent monitoring, customize deployment, onboard, availability. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure-prepare).

Build AI applications using the Azure AI Projects Python SDK (azure-ai-projects). Use when working with Foundry project clients, creating versioned agents with PromptAgentDefinition, running evaluations, managing connections/deployments/datasets/indexes, or using OpenAI-compatible clients. This is the high-level Foundry SDK - for low-level agent operations, use azure-ai-agents-python skill.

Guide for creating effective skills for AI coding agents working with Azure SDKs and Microsoft Foundry services. Use when creating new skills or updating existing skills.

Build Azure AI Foundry agents using the Microsoft Agent Framework Python SDK (agent-framework-azure-ai). Use when creating persistent agents with AzureAIAgentsProvider, using hosted tools (code interpreter, file search, web search), integrating MCP servers, managing conversation threads, or implementing streaming responses. Covers function tools, structured outputs, and multi-tool agents.

Azure AI Search SDK for Python. Use for vector search, hybrid search, semantic ranking, indexing, and skillsets. Triggers: "azure-search-documents", "SearchClient", "SearchIndexClient", "vector search", "hybrid search", "semantic search".

Discovers available Azure OpenAI model capacity across regions and projects. Analyzes quota limits, compares availability, and recommends optimal deployment locations based on capacity requirements. USE FOR: find capacity, check quota, where can I deploy, capacity discovery, best region for capacity, multi-project capacity search, quota analysis, model availability, region comparison, check TPM availability. DO NOT USE FOR: actual deployment (hand off to preset or customize after discovery), quota increase requests (direct user to Azure Portal), listing existing deployments.

Structured methodology for analyzing employee benefits costs, benchmarking against market data, and identifying optimization opportunities.

Region-neutral, illustrative statutory considerations affecting employee benefits — mandatory retirement contributions, statutory leave, and mandatory insurance.

Check financial transactions and operations against regulatory compliance rules. Use when asked about AML screening, KYC verification, transaction monitoring, or regulatory compliance.

Calculate credit risk scores for loan applications using financial metrics. Use when asked about credit risk assessment, loan scoring, debt-to-income analysis, or creditworthiness evaluation.

Azure Identity SDK for Python authentication with Microsoft Entra ID. Use for DefaultAzureCredential, managed identity, service principals, and token caching. Triggers: "azure-identity", "DefaultAzureCredential", "authentication", "managed identity", "service principal", "credential".

Govern Foundry agent fleets at scale — tool catalog visibility, AI Gateway MCP routing/policy, RBAC, agent identity, RAI policies on model deployments. USE FOR: governance, RBAC, RAI policy, tool catalog, AI Gateway.

Build, deploy, and manage Foundry hosted agents — containerized agents exposing Responses or Invocations protocols, with per-agent Entra identity and dedicated endpoints. USE FOR: hosted agent, create hosted agent, deploy hosted agent, agent.yaml, azd ai agent, ResponsesAgentServerHost, InvocationAgentServerHost. Routes to: microsoft-foundry/foundry-agent/create/create.md and microsoft-foundry/foundry-agent/deploy/deploy.md

Build Foundry IQ knowledge bases (preview) — multi-source, permission-aware grounding for agents using the agentic retrieval pipeline. USE FOR: knowledge base, IQ, agentic retrieval, grounding, Blob, SharePoint, OneLake.

Manage SKILL.md files as a Foundry-side resource (preview) — author behavioral guidelines once, store via the Skills REST API, load into hosted agent containers. USE FOR: managed skills, Skills REST API, agent instructions.

Build personalized Foundry agents with managed long-term memory (preview) — extract, consolidate, and retrieve user-specific context across sessions. USE FOR: memory store, long-term memory, user profile memory, chat summary memory, memory search tool, personalize agent.

Discover, deploy, and manage models on Foundry — preset/customized deployments, capacity discovery, quota management, PTU vs pay-as-you-go. USE FOR: deploy model, model catalog, capacity, quota, PTU.

Trace, monitor, and evaluate Foundry hosted agents end-to-end — OpenTelemetry GenAI traces in App Insights, eval-trace correlation, batch evals, regression detection. USE FOR: trace agent, evaluate agent, batch eval, App Insights, KQL, regression detection, continuous eval.

Provision Foundry resources/projects, configure project connections (key, OAuth, managed identity, agent identity), and set up standard or private-network agent infrastructure. USE FOR: create project, provision resource, connections, private network, standard agent setup.

Curate intent-based Foundry Toolboxes (preview) — a single MCP-compatible endpoint bundling tools (MCP, Web Search, AI Search, Code Interpreter, File Search, OpenAPI, A2A) for any agent to consume. USE FOR: toolbox, create toolbox, tool catalog, MCP endpoint, bundle tools.

Build multi-agent workflows — declarative orchestration for handing off control between specialist agents, plus the Connected Agents pattern. USE FOR: multi-agent, workflow, connected agents, orchestration, handoff.