Choose a Quest
Each Quest teaches a practical AI development pattern with JavaScript or TypeScript. Follow them in order for a complete path, or choose the outcome that matches what you want to learn next.
Quest 1: Local AI Development with Foundry Local
Run AI models on-device for privacy, low latency, and offline access.
You will explore: model management with the Foundry Local CLI, LangChain.js integration, structured extraction from unstructured text, and private coding assistance with local models.
Environment: Local
Quest 2: End-to-End Model Development on Microsoft Foundry
Work through the lifecycle of a cloud AI solution, from choosing a model to evaluating and protecting an agent.
You will explore: the model catalog and playgrounds, customization, evaluation, tracing, safety, and cloud-scale development patterns.
Environment: Cloud
Quest 3: Run a Serverless RAG Support System
Build a retrieval-augmented generation pipeline with LangChain.js and local models.
You will explore: document ingestion, vector storage, semantic retrieval, grounded responses with citations, streaming, and chat history.
Environment: Local & Cloud
Quest 4: Build Agents with AI Toolkit
Create and evaluate an agent with the AI Toolkit for Visual Studio Code.
You will explore: model comparison, Agent Builder, dynamic variables, MCP server integration, response evaluation, and code export.
Environment: Local & Cloud
Quest 5: Run an End-to-End Burger Ordering Agent System
Explore a complete agentic system with LangChain.js and MCP integrations.
You will explore: agent architecture, multi-service workflows, MCP tools, agent APIs, backend services, and an Azure scaling path.
Environment: Local & Cloud
Not sure where to begin? Read the start guide.