microsoft/frontier-ai-starter-kit-rvas

excalidraw-diagram

Create Excalidraw diagram JSON files that make visual arguments. Use when the user wants to visualize workflows, architectures, or concepts.

Langue du texte source : anglais

content-accuracy-audit

Audit session content (activity guides, scenario lessons, READMEs, validate.py, solution.md, the rendered _site/, docs/, skills, infra, scripts) for correctness, currency, hallucinations, broken cross-references, and pacing. Cross-checks every Azure /…

Langue du texte source : anglais

customer-activity-forge

Research a customer and industry from public sources, then generate ranked AI-application ideas mapped to the three customer-delivery scenario playbooks.

Langue du texte source : anglais

microsoft-foundry

Deploy, evaluate, fine-tune, and manage Foundry agents end-to-end: Docker build, ACR push, hosted/prompt agent create, container start, batch eval, continuous eval, prompt optimizer, Agent Optimizer scaffold, agent.yaml, dataset curation from traces, model…

Langue du texte source : anglais

foundry-hosted-agents

Build, deploy, and manage Microsoft Foundry hosted (containerized) agents — Responses + Invocations protocols, agent.yaml, azd ai agent, per-agent Entra identity, dedicated endpoints, ACR. Use for Advanced Deploy as a Hosted Agent.

Langue du texte source : anglais

foundry-iq-knowledge-bases

Build Microsoft Foundry IQ knowledge bases (preview) — multi-source, permission-aware grounding with agentic retrieval (query decomposition + parallel search + reranking); expose to agents via MCP. Use for Foundations Step 4 (Knowledge Base — Index + Foundry…

Langue du texte source : anglais

foundry-models

Discover, deploy, and manage Microsoft Foundry models; preset vs customized deployments; capacity discovery across regions; quota; PTU vs PAYG; RAI policy. Use for Foundations Step 2 (Model Selection & the Playground).

Langue du texte source : anglais

foundry-observability

Trace, monitor, and evaluate Microsoft Foundry agents — OpenTelemetry GenAI traces in Application Insights (KQL), eval↔trace correlation, azd ai agent monitor, dataset curation from prod traces, built-in quality + safety/RAI evaluators, batch evals,…

Langue du texte source : anglais

foundry-projects-resources

Provision Microsoft Foundry resources and projects; wire connections (key / OAuth / managed identity / agent identity); standard vs private-network infra. Use for Foundations Step 1 (Setup & Provisioning).

Langue du texte source : anglais

foundry-toolboxes

Curate intent-based Microsoft Foundry Toolboxes (preview) — one MCP-compatible endpoint bundling MCP, Web Search, Azure AI Search, Code Interpreter, File Search, OpenAPI, A2A, Browser Automation, and Computer Use tools. Build once, consume everywhere. Use for…

Langue du texte source : anglais

foundry-workflows

Multi-agent orchestration in Microsoft Foundry — declarative workflow vs A2A tool call vs Connected Agents pattern; Microsoft Agent Framework (MAF) patterns including Magentic manager/planner. Use for the Magentic Workflows and MAF Extras.

Langue du texte source : anglais