From Cloud to Chip: Building Smarter AI at the Edge with Windows AI PCs
As AI engineers, we’ve spent years optimizing models for the cloud, scaling inference, wrangling latency, and chasing compute across clusters. But the frontier is shifting. With the rise of Windows AI PCs and powerful local accelerators, the edge is no longer a constraint it’s now a canvas. Whether you're deploying vision models to industrial cameras, optimizing speech interfaces for offline assistants, or building privacy-preserving apps for healthcare, Edge AI is where real-world intelligence meets real-time performance. Why Edge AI, Why Now? Edge AI isn’t just about running models locally, it’s about rethinking the entire lifecycle: - Latency: Decisions in milliseconds, not round-trips to the cloud. - Privacy: Sensitive data stays on-device, enabling HIPAA/GDPR compliance. - Resilience: Offline-first apps that don’t break when the network does. - Cost: Reduced cloud compute and bandwidth overhead. With Windows AI PCs powered by Intel and Qualcomm NPUs and tools like ONNX Runtime, DirectML, and Olive, developers can now optimize and deploy models with unprecedented efficiency. What You’ll Learn in Edge AI for Beginners The Edge AI for Beginners curriculum is a hands-on, open-source guide designed for engineers ready to move from theory to deployment. Multi-Language Support This content is available in over 48 languages, so you can read and study in your native language. What You'll Master This course takes you from fundamental concepts to production-ready implementations, covering: Small Language Models (SLMs) optimized for edge deployment Hardware-aware optimization across diverse platforms Real-time inference with privacy-preserving capabilities Production deployment strategies for enterprise applications Why EdgeAI Matters Edge AI represents a paradigm shift that addresses critical modern challenges: Privacy & Security: Process sensitive data locally without cloud exposure Real-time Performance: Eliminate network latency for time-critical applications Cost Efficiency: Reduce bandwidth and cloud computing expenses Resilient Operations: Maintain functionality during network outages Regulatory Compliance: Meet data sovereignty requirements Edge AI Edge AI refers to running AI algorithms and language models locally on hardware, close to where data is generated without relying on cloud resources for inference. It reduces latency, enhances privacy, and enables real-time decision-making. Core Principles: On-device inference: AI models run on edge devices (phones, routers, microcontrollers, industrial PCs) Offline capability: Functions without persistent internet connectivity Low latency: Immediate responses suited for real-time systems Data sovereignty: Keeps sensitive data local, improving security and compliance Small Language Models (SLMs) SLMs like Phi-4, Mistral-7B, Qwen and Gemma are optimized versions of larger LLMs, trained or distilled for: Reduced memory footprint: Efficient use of limited edge device memory Lower compute demand: Optimized for CPU and edge GPU performance Faster startup times: Quick initialization for responsive applications They unlock powerful NLP capabilities while meeting the constraints of: Embedded systems: IoT devices and industrial controllers Mobile devices: Smartphones and tablets with offline capabilities IoT Devices: Sensors and smart devices with limited resources Edge servers: Local processing units with limited GPU resources Personal Computers: Desktop and laptop deployment scenarios Course Modules & Navigation Course duration. 10 hours of content Module Topic Focus Area Key Content Level Duration 📖 00 Introduction to EdgeAI Foundation & Context EdgeAI Overview • Industry Applications • SLM Introduction • Learning Objectives Beginner 1-2 hrs 📚 01 EdgeAI Fundamentals Cloud vs Edge AI comparison EdgeAI Fundamentals • Real World Case Studies • Implementation Guide • Edge Deployment Beginner 3-4 hrs 🧠 02 SLM Model Foundations Model families & architecture Phi Family • Qwen Family • Gemma Family • BitNET • μModel • Phi-Silica Beginner 4-5 hrs 🚀 03 SLM Deployment Practice Local & cloud deployment Advanced Learning • Local Environment • Cloud Deployment Intermediate 4-5 hrs ⚙️ 04 Model Optimization Toolkit Cross-platform optimization Introduction • Llama.cpp • Microsoft Olive • OpenVINO • Apple MLX • Workflow Synthesis Intermediate 5-6 hrs 🔧 05 SLMOps Production Production operations SLMOps Introduction • Model Distillation • Fine-tuning • Production Deployment Advanced 5-6 hrs 🤖 06 AI Agents & Function Calling Agent frameworks & MCP Agent Introduction • Function Calling • Model Context Protocol Advanced 4-5 hrs 💻 07 Platform Implementation Cross-platform samples AI Toolkit • Foundry Local • Windows Development Advanced 3-4 hrs 🏭 08 Foundry Local Toolkit Production-ready samples Sample applications (see details below) Expert 8-10 hrs Each module includes Jupyter notebooks, code samples, and deployment walkthroughs, perfect for engineers who learn by doing. Developer Highlights - 🔧 Olive: Microsoft's optimization toolchain for quantization, pruning, and acceleration. - 🧩 ONNX Runtime: Cross-platform inference engine with support for CPU, GPU, and NPU. - 🎮 DirectML: GPU-accelerated ML API for Windows, ideal for gaming and real-time apps. - 🖥️ Windows AI PCs: Devices with built-in NPUs for low-power, high-performance inference. Local AI: Beyond the Edge Local AI isn’t just about inference, it’s about autonomy. Imagine agents that: - Learn from local context - Adapt to user behavior - Respect privacy by design With tools like Agent Framework, Azure AI Foundry and Windows Copilot Studio, and Foundry Local developers can orchestrate local agents that blend LLMs, sensors, and user preferences, all without cloud dependency. Try It Yourself Ready to get started? Clone the Edge AI for Beginners GitHub repo, run the notebooks, and deploy your first model to a Windows AI PC or IoT devices Whether you're building smart kiosks, offline assistants, or industrial monitors, this curriculum gives you the scaffolding to go from prototype to production.AI Toolkit Extension Pack for Visual Studio Code: Ignite 2025 Update
Unlock the Latest Agentic App Capabilities The Ignite 2025 update delivers a major leap forward for the AI Toolkit extension pack in VS Code, introducing a unified, end-to-end environment for building, visualizing, and deploying agentic applications to Microsoft Foundry, and the addition of Anthropic’s frontier Claude models in the Model Catalog! This release enables developers to build and debug locally in VS Code, then deploy to the cloud with a single click. Seamlessly switch between VS Code and the Foundry portal for visualization, orchestration, and evaluation, creating a smooth roundtrip workflow that accelerates innovation and delivers a truly unified AI development experience. Download the http://aka.ms/aitoolkit today and start building next-generation agentic apps in VS Code! What Can You Do with the AI Toolkit Extension Pack? Access Anthropic models in the Model Catalog Following the Microsoft, NVIDIA and Anthropic strategic partnerships announcement today, we are excited to share that Anthropic’s frontier Claude models including Claude Sonnet 4.5, Claude Opus 4.1, and Claude Haiku 4.5, are now integrated into the AI Toolkit, providing even more choices and flexibility when building intelligent applications and AI agents. Build AI Agents Using GitHub Copilot Scaffold agent applications using best-practice patterns, tool-calling examples, tracing hooks, and test scaffolds, all powered by Copilot and aligned with the Microsoft Agent Framework. Generate agent code in Python or .NET, giving you flexibility to target your preferred runtime. Build and Customize YAML Workflows Design YAML-based workflows in the Foundry portal, then continue editing and testing directly in VS Code. To customize your YAML-based workflows, instantly convert it to Agent Framework code using GitHub Copilot. Upgrade from declarative design to code-first customization without starting from scratch. Visualize Multi-Agent Workflows Envision your code-based agent workflows with an interactive graph visualizer that reveals each component and how they connect Watch in real-time how each node lights up as you run your agent. Use the visualizer to understand and debug complex agent graphs, making iteration fast and intuitive. Experiment, Debug, and Evaluate Locally Use the Hosted Agents Playground to quickly interact with your agents on your development machine. Leverage local tracing support to debug reasoning steps, tool calls, and latency hotspots—so you can quickly diagnose and fix issues. Define metrics, tasks, and datasets for agent evaluation, then implement metrics using the Foundry Evaluation SDK and orchestrate evaluations runs with the help of Copilot. Seamless Integration Across Environments Jump from Foundry Portal to VS Code Web for a development environment in your preferred code editor setting. Open YAML workflows, playgrounds, and agent templates directly in VS Code for editing and deployment. How to Get Started Install the AI Toolkit extension pack from the VS Code marketplace. Check out documentation. Get started with building workflows with Microsoft Foundry in VS Code 1. Work with Hosted (Pro-code) Agent workflows in VS Code 2. Work with Declarative (Low-code) Agent workflows in VS Code Feedback & Support Try out the extensions and let us know what you think! File issues or feedback on our GitHub repo for Foundry extension and AI Toolkit extension. Your input helps us make continuous improvements.Python + IA: Resumen y Recursos
Acabamos de concluir nuestra serie sobre Python + IA, un recorrido completo de nueve sesiones donde exploramos a fondo cómo usar modelos de inteligencia artificial generativa desde Python. Durante la serie presentamos varios tipos de modelos, incluyendo LLMs, modelos de embeddings y modelos de visión. Profundizamos en técnicas populares como RAG, tool calling y salidas estructuradas. Evaluamos la calidad y seguridad de la IA mediante evaluaciones automatizadas y red-teaming. Finalmente, desarrollamos agentes de IA con frameworks populares de Python y exploramos el nuevo Model Context Protocol (MCP). Para que puedas aplicar lo aprendido, todos nuestros ejemplos funcionan con GitHub Models, un servicio que ofrece modelos gratuitos a todos los usuarios de GitHub para experimentación y aprendizaje. Aunque no hayas asistido a las sesiones en vivo, ¡todavía puedes acceder a todos los materiales usando los enlaces de abajo! Si eres instructor, puedes usar las diapositivas y el código en tus propias clases. Python + IA: Modelos de Lenguaje Grandes (LLMs) 📺 Ver grabación En esta sesión exploramos los LLMs, los modelos que impulsan ChatGPT y GitHub Copilot. Usamos Python con paquetes como OpenAI SDK y LangChain, experimentamos con prompt engineering y ejemplos few-shot, y construimos una aplicación completa basada en LLMs. También explicamos la importancia de la concurrencia y el streaming en apps de IA. Diapositivas: aka.ms/pythonia/diapositivas/llms Código: python-openai-demos Guía de repositorio: video Python + IA: Embeddings Vectoriales 📺 Ver grabación En nuestra segunda sesión, aprendemos sobre los modelos de embeddings vectoriales, que convierten texto o imágenes en arreglos numéricos. Comparamos métricas de distancia, aplicamos cuantización y experimentamos con modelos multimodales. Diapositivas: aka.ms/pythonia/diapositivas/embeddings Código: vector-embedding-demos Guía de repositorio: video Python + IA: Retrieval Augmented Generation (RAG) 📺 Ver grabación Descubrimos cómo usar RAG para mejorar las respuestas de los LLMs añadiendo contexto relevante. Construimos flujos RAG en Python con distintas fuentes (CSVs, sitios web, documentos y bases de datos) y terminamos con una aplicación completa basada en Azure AI Search. Diapositivas: aka.ms/pythonia/diapositivas/rag Código: python-openai-demos Guía de repositorio: video Python + IA: Modelos de Visión 📺 Ver grabación Los modelos de visión aceptan texto e imágenes, como GPT-4o y GPT-4o mini. Creamos una app de chat con imágenes, realizamos extracción de datos y construimos un motor de búsqueda multimodal. Diapositivas: aka.ms/pythonia/diapositivas/vision Código: vector-embeddings Guía de repositorio: video Python + IA: Salidas Estructuradas 📺 Ver grabación Aprendemos a generar respuestas estructuradas con LLMs usando Pydantic BaseModel. Este enfoque permite validación automática de los resultados, útil para extracción de entidades, clasificación y flujos de agentes. Diapositivas: aka.ms/pythonia/diapositivas/salidas Código: python-openai-demos y entity-extraction-demos Guía de repositorio: video Python + IA: Calidad y Seguridad 📺 Ver grabación Analizamos cómo usar la IA de forma segura y cómo evaluar la calidad de las respuestas. Mostramos cómo configurar Azure AI Content Safety y usar el Azure AI Evaluation SDK para medir resultados de los modelos. Diapositivas: aka.ms/pythonia/diapositivas/calidad Código: ai-quality-safety-demos Guía de repositorio: video Python + IA: Tool Calling 📺 Ver grabación Exploramos el tool calling, base para crear agentes de IA. Definimos herramientas con esquemas JSON y funciones Python, manejamos llamadas paralelas y flujos iterativos. Diapositivas: aka.ms/pythonia/diapositivas/herramientas Código: python-openai-demos Guía de repositorio: video Python + IA: Agentes de IA 📺 Ver grabación Creamos agentes de IA con frameworks como el agent-framework de Microsoft y LangGraph, mostrando arquitecturas con múltiples herramientas, supervisores y flujos con intervención humana. Diapositivas: aka.ms/pythonia/diapositivas/agentes Código: python-ai-agents-demos Guía de repositorio: video Python + IA: Model Context Protocol (MCP) 📺 Ver grabación Cerramos la serie con MCP (Model Context Protocol), la tecnología más innovadora de 2025. Mostramos cómo usar el SDK de FastMCP en Python para crear un servidor MCP local, conectarlo a GitHub Copilot, construir un cliente MCP y conectar frameworks como LangGraph y agent-framework. También discutimos los riesgos de seguridad asociados. Diapositivas: aka.ms/pythonia/diapositivas/mcp Código: python-ai-mcp-demos Guía de repositorio: video Además Si tienen preguntas, por favor, en el canal #Espanol en nuestro Discord: https://aka.ms/pythonia/discord Todos los jueves tengo office hours: https://aka.ms/pythonia/horas Encuentra más tutoriales 100% en español sobre Python + AI en https://youtube.com/@lagpsIntroducing langchain-azure-storage: Azure Storage integrations for LangChain
We're excited to introduce langchain-azure-storage , the first official Azure Storage integration package built by Microsoft for LangChain 1.0. As part of its launch, we've built a new Azure Blob Storage document loader (currently in public preview) that improves upon prior LangChain community implementations. This new loader unifies both blob and container level access, simplifying loader integration. More importantly, it offers enhanced security through default OAuth 2.0 authentication, supports reliably loading millions to billions of documents through efficient memory utilization, and allows pluggable parsing, so you can leverage other document loaders to parse specific file formats. What are LangChain document loaders? A typical Retrieval‑Augmented Generation (RAG) pipeline follows these main steps: Collect source content (PDFs, DOCX, Markdown, CSVs) — often stored in Azure Blob Storage. Parse into text and associated metadata (i.e., represented as LangChain Document objects). Chunk + embed those documents and store in a vector store (e.g., Azure AI Search, Postgres pgvector, etc.). At query time, retrieve the most relevant chunks and feed them to an LLM as grounded context. LangChain document loaders make steps 1–2 turnkey and consistent so the rest of the stack (splitters, vector stores, retrievers) “just works”. See this LangChain RAG tutorial for a full example of these steps when building a RAG application in LangChain. How can the Azure Blob Storage document loader help? The langchain-azure-storage package offers the AzureBlobStorageLoader , a document loader that simplifies retrieving documents stored in Azure Blob Storage for use in a LangChain RAG application. Key benefits of the AzureBlobStorageLoader include: Flexible loading of Azure Storage blobs to LangChain Document objects. You can load blobs as documents from an entire container, a specific prefix within a container, or by blob names. Each document loaded corresponds 1:1 to a blob in the container. Lazy loading support for improved memory efficiency when dealing with large document sets. Documents can now be loaded one-at-a-time as you iterate over them instead of all at once. Automatically uses DefaultAzureCredential to enable seamless OAuth 2.0 authentication across various environments, from local development to Azure-hosted services. You can also explicitly pass your own credential (e.g., ManagedIdentityCredential , SAS token). Pluggable parsing. Easily customize how documents are parsed by providing your own LangChain document loader to parse downloaded blob content. Using the Azure Blob Storage document loader Installation To install the langchain-azure-storage package, run: pip install langchain-azure-storage Loading documents from a container To load all blobs from an Azure Blob Storage container as LangChain Document objects, instantiate the AzureBlobStorageLoader with the Azure Storage account URL and container name: from langchain_azure_storage.document_loaders import AzureBlobStorageLoader loader = AzureBlobStorageLoader( "https://<your-storage-account>.blob.core.windows.net/", "<your-container-name>" ) # lazy_load() yields one Document per blob for all blobs in the container for doc in loader.lazy_load(): print(doc.metadata["source"]) # The "source" metadata contains the full URL of the blob print(doc.page_content) # The page_content contains the blob's content decoded as UTF-8 text Loading documents by blob names To only load specific blobs as LangChain Document objects, you can additionally provide a list of blob names: from langchain_azure_storage.document_loaders import AzureBlobStorageLoader loader = AzureBlobStorageLoader( "https://<your-storage-account>.blob.core.windows.net/", "<your-container-name>", ["<blob-name-1>", "<blob-name-2>"] ) # lazy_load() yields one Document per blob for only the specified blobs for doc in loader.lazy_load(): print(doc.metadata["source"]) # The "source" metadata contains the full URL of the blob print(doc.page_content) # The page_content contains the blob's content decoded as UTF-8 text Pluggable parsing By default, loaded Document objects contain the blob's UTF-8 decoded content. To parse non-UTF-8 content (e.g., PDFs, DOCX, etc.) or chunk blob content into smaller documents, provide a LangChain document loader via the loader_factory parameter. When loader_factory is provided, the AzureBlobStorageLoader processes each blob with the following steps: Downloads the blob to a new temporary file Passes the temporary file path to the loader_factory callable to instantiate a document loader Uses that loader to parse the file and yield Document objects Cleans up the temporary file For example, below shows parsing PDF documents with the PyPDFLoader from the langchain-community package: from langchain_azure_storage.document_loaders import AzureBlobStorageLoader from langchain_community.document_loaders import PyPDFLoader # Requires langchain-community and pypdf packages loader = AzureBlobStorageLoader( "https://<your-storage-account>.blob.core.windows.net/", "<your-container-name>", prefix="pdfs/", # Only load blobs that start with "pdfs/" loader_factory=PyPDFLoader # PyPDFLoader will parse each blob as a PDF ) # Each blob is downloaded to a temporary file and parsed by PyPDFLoader instance for doc in loader.lazy_load(): print(doc.page_content) # Content parsed by PyPDFLoader (yields one Document per page in the PDF) This file path-based interface allows you to use any LangChain document loader that accepts a local file path as input, giving you access to a wide range of parsers for different file formats. Migrating from community document loaders to langchain-azure-storage If you're currently using AzureBlobStorageContainerLoader or AzureBlobStorageFileLoader from the langchain-community package, the new AzureBlobStorageLoader provides an improved alternative. This section provides step-by-step guidance for migrating to the new loader. Steps to migrate To migrate to the new Azure Storage document loader, make the following changes: Depend on the langchain-azure-storage package Update import statements from langchain_community.document_loaders to langchain_azure_storage.document_loaders . Change class names from AzureBlobStorageFileLoader and AzureBlobStorageContainerLoader to AzureBlobStorageLoader . Update document loader constructor calls to: Use an account URL instead of a connection string. Specify UnstructuredLoader as the loader_factory to continue to use Unstructured for parsing documents. Enable Microsoft Entra ID authentication in environment (e.g., run az login or configure managed identity) instead of using connection string authentication. Migration samples Below shows code snippets of what usage patterns look like before and after migrating from langchain-community to langchain-azure-storage : Before migration from langchain_community.document_loaders import AzureBlobStorageContainerLoader, AzureBlobStorageFileLoader container_loader = AzureBlobStorageContainerLoader( "DefaultEndpointsProtocol=https;AccountName=<account>;AccountKey=<account-key>;EndpointSuffix=core.windows.net", "<container>", ) file_loader = AzureBlobStorageFileLoader( "DefaultEndpointsProtocol=https;AccountName=<account>;AccountKey=<account-key>;EndpointSuffix=core.windows.net", "<container>", "<blob>" ) After migration from langchain_azure_storage.document_loaders import AzureBlobStorageLoader from langchain_unstructured import UnstructuredLoader # Requires langchain-unstructured and unstructured packages container_loader = AzureBlobStorageLoader( "https://<account>.blob.core.windows.net", "<container>", loader_factory=UnstructuredLoader # Only needed if continuing to use Unstructured for parsing ) file_loader = AzureBlobStorageLoader( "https://<account>.blob.core.windows.net", "<container>", "<blob>", loader_factory=UnstructuredLoader # Only needed if continuing to use Unstructured for parsing ) What's next? We're excited for you to try the new Azure Blob Storage document loader and would love to hear your feedback! Here are some ways you can help shape the future of langchain-azure-storage : Show support for interface stabilization - The document loader is currently in public preview and the interface may change in future versions based on feedback. If you'd like to see the current interface marked as stable, upvote the proposal PR to show your support. Report issues or suggest improvements - Found a bug or have an idea to make the document loaders better? File an issue on our GitHub repository. Propose new LangChain integrations - Interested in other ways to use Azure Storage with LangChain (e.g., checkpointing for agents, persistent memory stores, retriever implementations)? Create a feature request or write to us to let us know. Your input is invaluable in making langchain-azure-storage better for the entire community! Resources langchain-azure GitHub repository langchain-azure-storage PyPI package AzureBlobStorageLoader usage guide AzureBlobStorageLoader documentation referenceAnnouncing Public Preview: AI Toolkit for GitHub Copilot Prompt-First Agent Development
This week at GitHub Universe, we’re announcing the Public Preview of the GitHub Copilot prompt-first agent development in the AI Toolkit for Visual Studio Code. With this release, building powerful AI agents is now simpler and faster - no need to wrestle with complex frameworks or orchestrators. Just start with natural language prompts and let GitHub Copilot guide you from concept to working agent code. Accelerate Agent Development in VS Code The AI Toolkit embeds agent development workflows directly into Visual Studio Code and GitHub Copilot, enabling you to transform ideas into production-ready agents within minutes. This unified experience empowers developers and product teams to: Select the best model for your agent scenario Build and orchestrate agents using Microsoft Agent Framework Trace agent behaviors Evaluate agent response quality Select the best model for your scenario Models are the foundation for building powerful agents. Using the AI Toolkit, you can already explore and experiment with a wide range of local and remote models. Copilot now recommends models tailored to your agent’s needs, helping you make informed choices quickly. Build and orchestrate agents Whether you’re creating a single agent or designing a multi-agent workflow, Copilot leverages the latest Microsoft Agent Framework to generate robust agent code. You can initiate agent creation with simple prompts and visualize workflows for greater clarity and control. Create a single agent using Copilot Create a multi-agent workflow using Copilot and visualize workflow execution Trace agent behaviors As agents become more sophisticated, understanding their actions is crucial. The AI Toolkit enables tracing via Copilot, collecting local traces and displaying detailed agent calls, all within VS Code. Evaluate agent response quality Copilot guides you through structured evaluation, recommending metrics and generating test datasets. Integrate evaluations into your CI/CD pipeline for continuous quality assurance and confident deployments. Get started and share feedback This release marks a significant step toward making AI agent development easier and more accessible in Visual Studio Code. Try out the AI Toolkit for Visual Studio Code, share your thoughts, and file issues and suggest features on our GitHub repo. Thank you for being a part of this journey with us!Serverless MCP Agent with LangChain.js v1 — Burgers, Tools, and Traces 🍔
AI agents that can actually do stuff (not just chat) are the fun part nowadays, but wiring them cleanly into real APIs, keeping things observable, and shipping them to the cloud can get... messy. So we built a fresh end‑to‑end sample to show how to do it right with the brand new LangChain.js v1 and Model Context Protocol (MCP). In case you missed it, MCP is a recent open standard that makes it easy for LLM agents to consume tools and APIs, and LangChain.js, a great framework for building GenAI apps and agents, has first-class support for it. You can quickly get up speed with the MCP for Beginners course and AI Agents for Beginners course. This new sample gives you: A LangChain.js v1 agent that streams its result, along reasoning + tool steps An MCP server exposing real tools (burger menu + ordering) from a business API A web interface with authentication, sessions history, and a debug panel (for developers) A production-ready multi-service architecture Serverless deployment on Azure in one command ( azd up ) Yes, it’s a burger ordering system. Who doesn't like burgers? Grab your favorite beverage ☕, and let’s dive in for a quick tour! TL;DR key takeaways New sample: full-stack Node.js AI agent using LangChain.js v1 + MCP tools Architecture: web app → agent API → MCP server → burger API Runs locally with a single npm start , deploys with azd up Uses streaming (NDJSON) with intermediate tool + LLM steps surfaced to the UI Ready to fork, extend, and plug into your own domain / tools What will you learn here? What this sample is about and its high-level architecture What LangChain.js v1 brings to the table for agents How to deploy and run the sample How MCP tools can expose real-world APIs Reference links for everything we use GitHub repo LangChain.js docs Model Context Protocol Azure Developer CLI MCP Inspector Use case You want an AI assistant that can take a natural language request like “Order two spicy burgers and show me my pending orders” and: Understand intent (query menu, then place order) Call the right MCP tools in sequence, calling in turn the necessary APIs Stream progress (LLM tokens + tool steps) Return a clean final answer Swap “burgers” for “inventory”, “bookings”, “support tickets”, or “IoT devices” and you’ve got a reusable pattern! Sample overview Before we play a bit with the sample, let's have a look at the main services implemented here: Service Role Tech Agent Web App ( agent-webapp ) Chat UI + streaming + session history Azure Static Web Apps, Lit web components Agent API ( agent-api ) LangChain.js v1 agent orchestration + auth + history Azure Functions, Node.js Burger MCP Server ( burger-mcp ) Exposes burger API as tools over MCP (Streamable HTTP + SSE) Azure Functions, Express, MCP SDK Burger API ( burger-api ) Business logic: burgers, toppings, orders lifecycle Azure Functions, Cosmos DB Here's a simplified view of how they interact: There are also other supporting components like databases and storage not shown here for clarity. For this quickstart we'll only interact with the Agent Web App and the Burger MCP Server, as they are the main stars of the show here. LangChain.js v1 agent features The recent release of LangChain.js v1 is a huge milestone for the JavaScript AI community! It marks a significant shift from experimental tools to a production-ready framework. The new version doubles down on what’s needed to build robust AI applications, with a strong focus on agents. This includes first-class support for streaming not just the final output, but also intermediate steps like tool calls and agent reasoning. This makes building transparent and interactive agent experiences (like the one in this sample) much more straightforward. Quickstart Requirements GitHub account Azure account (free signup, or if you're a student, get free credits here) Azure Developer CLI Deploy and run the sample We'll use GitHub Codespaces for a quick zero-install setup here, but if you prefer to run it locally, check the README. Click on the following link or open it in a new tab to launch a Codespace: Create Codespace This will open a VS Code environment in your browser with the repo already cloned and all the tools installed and ready to go. Provision and deploy to Azure Open a terminal and run these commands: # Install dependencies npm install # Login to Azure azd auth login # Provision and deploy all resources azd up Follow the prompts to select your Azure subscription and region. If you're unsure of which one to pick, choose East US 2 . The deployment will take about 15 minutes the first time, to create all the necessary resources (Functions, Static Web Apps, Cosmos DB, AI Models). If you're curious about what happens under the hood, you can take a look at the main.bicep file in the infra folder, which defines the infrastructure as code for this sample. Test the MCP server While the deployment is running, you can run the MCP server and API locally (even in Codespaces) to see how it works. Open another terminal and run: npm start This will start all services locally, including the Burger API and the MCP server, which will be available at http://localhost:3000/mcp . This may take a few seconds, wait until you see this message in the terminal: 🚀 All services ready 🚀 When these services are running without Azure resources provisioned, they will use in-memory data instead of Cosmos DB so you can experiment freely with the API and MCP server, though the agent won't be functional as it requires a LLM resource. MCP tools The MCP server exposes the following tools, which the agent can use to interact with the burger ordering system: Tool Name Description get_burgers Get a list of all burgers in the menu get_burger_by_id Get a specific burger by its ID get_toppings Get a list of all toppings in the menu get_topping_by_id Get a specific topping by its ID get_topping_categories Get a list of all topping categories get_orders Get a list of all orders in the system get_order_by_id Get a specific order by its ID place_order Place a new order with burgers (requires userId , optional nickname ) delete_order_by_id Cancel an order if it has not yet been started (status must be pending , requires userId ) You can test these tools using the MCP Inspector. Open another terminal and run: npx -y @modelcontextprotocol/inspector Then open the URL printed in the terminal in your browser and connect using these settings: Transport: Streamable HTTP URL: http://localhost:3000/mcp Connection Type: Via Proxy (should be default) Click on Connect, then try listing the tools first, and run get_burgers tool to get the menu info. Test the Agent Web App After the deployment is completed, you can run the command npm run env to print the URLs of the deployed services. Open the Agent Web App URL in your browser (it should look like https://<your-web-app>.azurestaticapps.net ). You'll first be greeted by an authentication page, you can sign in either with your GitHub or Microsoft account and then you should be able to access the chat interface. From there, you can start asking any question or use one of the suggested prompts, for example try asking: Recommend me an extra spicy burger . As the agent processes your request, you'll see the response streaming in real-time, along with the intermediate steps and tool calls. Once the response is complete, you can also unfold the debug panel to see the full reasoning chain and the tools that were invoked: Tip: Our agent service also sends detailed tracing data using OpenTelemetry. You can explore these either in Azure Monitor for the deployed service, or locally using an OpenTelemetry collector. We'll cover this in more detail in a future post. Wrap it up Congratulations, you just finished spinning up a full-stack serverless AI agent using LangChain.js v1, MCP tools, and Azure’s serverless platform. Now it's your turn to dive in the code and extend it for your use cases! 😎 And don't forget to azd down once you're done to avoid any unwanted costs. Going further This was just a quick introduction to this sample, and you can expect more in-depth posts and tutorials soon. Since we're in the era of AI agents, we've also made sure that this sample can be explored and extended easily with code agents like GitHub Copilot. We even built a custom chat mode to help you discover and understand the codebase faster! Check out the Copilot setup guide in the repo to get started. You can quickly get up speed with the MCP for Beginners course and AI Agents for Beginners course. If you like this sample, don't forget to star the repo ⭐️! You can also join us in the Azure AI community Discord to chat and ask any questions. Happy coding and burger ordering! 🍔
Orchestrating Multi-Agent Intelligence: MCP-Driven Patterns in Agent Framework
Building reliable AI systems requires modular, stateful coordination and deterministic workflows that enable agents to collaborate seamlessly. The Microsoft Agent Framework provides these foundations, with memory, tracing, and orchestration built in. This implementation demonstrates four multi-agentic patterns — Single Agent, Handoff, Reflection, and Magentic Orchestration — showcasing different interaction models and collaboration strategies. From lightweight domain routing to collaborative planning and self-reflection, these patterns highlight the framework’s flexibility. At the core is Model Context Protocol (MCP), connecting agents, tools, and memory through a shared context interface. Persistent session state, conversation thread history, and checkpoint support are handled via Cosmos DB when configured, with an in-memory dictionary as a default fallback. This setup enables dynamic pattern swapping, performance comparison, and traceable multi-agent interactions — all within a unified, modular runtime. Business Scenario: Contoso Customer Support Chatbot Contoso’s chatbot handles multi-domain customer inquiries like billing anomalies, promotion eligibility, account locks, and data usage questions. These require combining structured data (billing, CRM, security logs, promotions) with unstructured policy documents processed via vector embeddings. Using MCP, the system orchestrates tool calls to fetch real-time structured data and relevant policy content, ensuring policy-aligned, auditable responses without exposing raw databases. This enables the assistant to explain anomalies, recommend actions, confirm eligibility, guide account recovery, and surface risk indicators—reducing handle time and improving first-contact resolution while supporting richer multi-agent reasoning. Architecture & Core Concepts The Contoso chatbot leverages the Microsoft Agent Framework to deliver a modular, stateful, and workflow-driven architecture. At its core, the system consists of: Base Agent: All agent patterns—single agent, reflection, handoff and magentic orchestration—inherit from a common base class, ensuring consistent interfaces for message handling, tool invocation, and state management. Backend: A FastAPI backend manages session routing, agent execution, and workflow orchestration. Frontend: A React-based UI (or Streamlit alternative) streams responses in real-time and visualizes agent reasoning and tool calls. Modular Runtime and Pattern Swapping One of the most powerful aspects of this implementation is its modular runtime design. Each agentic pattern—Single, Reflection, Handoff, and Magnetic—plugs into a shared execution pipeline defined by the base agent and MCP integration. By simply updating the .env configuration (e.g., agent_module=handoff), developers can swap in and out entire coordination strategies without touching the backend, frontend, or memory layers. This makes it easy to compare agent styles side by side, benchmark reasoning behaviors, and experiment with orchestration logic—all while maintaining a consistent, deterministic runtime. The same MCP connectors, FastAPI backend, and Cosmos/in-memory state management work seamlessly across every pattern, enabling rapid iteration and reliable evaluation. # Dynamic agent pattern loading agent_module_path = os.getenv("AGENT_MODULE") agent_module = __import__(agent_module_path, fromlist=["Agent"]) Agent = getattr(agent_module, "Agent") # Common MCP setup across all patterns async def _create_tools(self, headers: Dict[str, str]) -> List[MCPStreamableHTTPTool] | None: if not self.mcp_server_uri: return None return [MCPStreamableHTTPTool( name="mcp-streamable", url=self.mcp_server_uri, headers=headers, timeout=30, request_timeout=30, )] Memory & State Management State management is critical for multi-turn conversations and cross-agent workflows. The system supports two out-of-the-box options: Persistent Storage (Cosmos DB) Acts as the durable, enterprise-ready backend. Stores serialized conversation threads and workflow checkpoints keyed by tenant and session ID. Ensures data durability and auditability across restarts. In-Memory Session Store Default fallback when Cosmos DB credentials are not configured. Maintains ephemeral state per session for fast prototyping or lightweight use cases. All patterns leverage the same thread-based state abstraction, enabling: Session isolation: Each user session maintains its own state and history. Checkpointing: Multi-agent workflows can snapshot shared and executor-local state at any point, supporting pause/resume and fault recovery. Model Context Protocol (MCP): Acts as the connector between agents and tools, standardizing how data is fetched and results are returned to agents, whether querying structured databases or unstructured knowledge sources. Core Principles Across all patterns, the framework emphasizes: Modularity: Components are interchangeable—agents, tools, and state stores can be swapped without disrupting the system. Stateful Coordination: Multi-agent workflows coordinate through shared and local state, enabling complex reasoning without losing context. Deterministic Workflows: While agents operate autonomously, the workflow layer ensures predictable, auditable execution of multi-agent tasks. Unified Execution: From single-agent Q&A to complex Magentic orchestrations, every agent follows the same execution lifecycle and integrates seamlessly with MCP and the state store. Multi-Agent Patterns: Workflow and Coordination With the architecture and core concepts established, we can now explore the agentic patterns implemented in the Contoso chatbot. Each pattern builds on the base agent and MCP integration but differs in how agents orchestrate tasks and communicate with one another to handle multi-domain customer queries. In the sections that follow, we take a deeper dive into each pattern’s workflow and examine the under-the-hood communication flows between agents: Single Agent – A simple, single-domain agent handling straightforward queries. Reflection Agent – Allows agents to introspect and refine their outputs. Handoff Pattern – Routes conversations intelligently to specialized agents across domains. Magentic Orchestration – Coordinates multiple specialist agents for complex, parallel tasks. For each pattern, the focus will be on how agents communicate and coordinate, showing the practical orchestration mechanisms in action. Single Intelligent Agent The Single Agent Pattern represents the simplest orchestration style within the framework. Here, a single autonomous agent handles all reasoning, decision-making, and tool interactions directly — without delegation or multi-agent coordination. When a user submits a request, the single agent processes the query using all tools, memory, and data sources available through the Model Context Protocol (MCP). It performs retrieval, reasoning, and response composition in a single, cohesive loop. Communication Flow: User Input → Agent: The user submits a question or command. Agent → MCP Tools: The agent invokes one or more tools (e.g., vector retrieval, structured queries, or API calls) to gather relevant context and data. Agent → User: The agent synthesizes the tool outputs, applies reasoning, and generates the final response to the user. Session Memory: Throughout the exchange, the agent stores conversation history and extracted entities in the configured memory store (in-memory or Cosmos DB). Key Communication Principles: Single Responsibility: One agent performs both reasoning and action, ensuring fast response times and simpler state management. Direct Tool Invocation: The agent has direct access to all registered tools through MCP, enabling flexible retrieval and action chaining. Stateful Execution: The session memory preserves dialogue context, allowing the agent to maintain continuity across user turns. Deterministic Behavior: The workflow is fully predictable — input, reasoning, tool call, and output occur in a linear sequence. Reflection pattern The Reflection Pattern introduces a lightweight, two-agent communication loop designed to improve the quality and reliability of responses through structured self-review. In this setup, a Primary Agent first generates an initial response to the user’s query. This draft is then passed to a Reviewer Agent, whose role is to critique and refine the response—identifying gaps, inaccuracies, or missed context. Finally, the Primary Agent incorporates this feedback and produces a polished final answer for the user. This process introduces one round of reflection and improvement without adding excessive latency, balancing quality with responsiveness. Communication Flow: User Input → Primary Agent: The user submits a query. Primary Agent → Reviewer Agent: The primary generates an initial draft and passes it to the reviewer. Reviewer Agent → Primary Agent: The reviewer provides feedback or suggested improvements. Primary Agent → User: The primary revises its response and sends the refined version back to the user. Key Communication Principles: Two-Stage Dialogue: Structured interaction between Primary and Reviewer ensures each output undergoes quality assurance. Focused Review: The Reviewer doesn’t recreate answers—it critiques and enhances, reducing redundancy. Stateful Context: Both agents operate over the same shared memory, ensuring consistency between draft and revision. Deterministic Flow: A single reflection round guarantees predictable latency while still improving answer quality. Transparent Traceability: Each step—initial draft, feedback, and final output—is logged, allowing developers to audit reasoning or assess quality improvements over time. In practice, this pattern enables the system to reason about its own output before responding, yielding clearer, more accurate, and policy-aligned answers without requiring multiple independent retries. Handoff Pattern When a user request arrives, the system first routes it through an Intent Classifier (or triage agent) to determine which domain specialist should handle the conversation. Once identified, control is handed off directly to that Specialist Agent, which uses its own tools, domain knowledge, and state context to respond. This specialist continues to handle the user interaction as long as the conversation stays within its domain. If the user’s intent shifts — for example, moving from billing to security — the conversation is routed back to the Intent Classifier, which re-assigns it to the correct specialist agent. This pattern reduces latency and maintains continuity by minimizing unnecessary routing. Each handoff is tracked through the shared state store, ensuring seamless context carry-over and full traceability of decisions. Key Communication Principles: Dynamic Routing: The Intent Classifier routes user input to the right specialist domain. Domain Persistence: The specialist remains active while the user stays within its domain. Context Continuity: Conversation history and entities persist across agents through the shared state store. Traceable Handoffs: Every routing decision is logged for observability and auditability. Low Latency: Responses are faster since domain-appropriate agents handle queries directly. In practice, this means a user could begin a conversation about billing, continue seamlessly, and only be re-routed when switching topics — without losing any conversational context or history. Magentic Pattern The Magentic Pattern is designed for open-ended, multi-faceted tasks that require multiple agents to collaborate. It introduces a Manager (Planner) Agent, which interprets the user’s goal, breaks it into subtasks, and orchestrates multiple Specialist Agents to execute those subtasks. The Manager creates and maintains a Task Ledger, which tracks the status, dependencies, and results of each specialist’s work. As specialists perform their tool calls or reasoning, the Manager monitors their progress, gathers intermediate outputs, and can dynamically re-plan, dispatch additional tasks, or adjust the overall workflow. When all subtasks are complete, the Manager synthesizes the combined results into a coherent final response for the user. Key Communication Principles: Centralized Orchestration: The Manager coordinates all agent interactions and workflow logic. Parallel and Sequential Execution: Specialists can work simultaneously or in sequence based on task dependencies. Task Ledger: Acts as a transparent record of all task assignments, updates, and completions. Dynamic Re-planning: The Manager can modify or extend workflows in real time based on intermediate findings. Shared Memory: All agents access the same state store for consistent context and result sharing. Unified Output: The Manager consolidates results into one response, ensuring coherence across multi-agent reasoning. In practice, Magentic orchestration enables complex reasoning where the system might combine insights from multiple agents — e.g., billing, product, and security — and present a unified recommendation or resolution to the user. Choosing the Right Agent for Your Use Case Selecting the appropriate agent pattern hinges on the complexity of the task and the level of coordination required. As use cases evolve from straightforward queries to intricate, multi-step processes, the need for specialized orchestration increases. Below is a decision matrix to guide your choice: Feature / Requirement Single Agent Reflection Agent Handoff Pattern Magentic Orchestration Handles simple, domain-bound tasks ✔ ✔ ✖ ✖ Supports review / quality assurance ✖ ✔ ✖ ✔ Multi-domain routing ✖ ✖ ✔ ✔ Open-ended / complex workflows ✖ ✖ ✖ ✔ Parallel agent collaboration ✖ ✖ ✖ ✔ Direct tool access ✔ ✔ ✔ ✔ Low latency / fast response ✔ ✔ ✔ ✖ Easy to implement / low orchestration ✔ ✔ ✖ ✖ Dive Deeper: Explore, Build, and Innovate We've explored various agent patterns, from Single Agent to Magentic Orchestration, each tailored to different use cases and complexities. To see these patterns in action, we invite you to explore our Github repo. Clone the repo, experiment with the examples, and adapt them to your own scenarios. Additionally, beyond the patterns discussed here, the repository also features a Human-in-the-Loop (HITL) workflow designed for fraud detection. This workflow integrates human oversight into AI decision-making, ensuring higher accuracy and reliability. For an in-depth look at this approach, we recommend reading our detailed blog post: Building Human-in-the-loop AI Workflows with Microsoft Agent Framework | Microsoft Community Hub Engage with these resources, and start building intelligent, reliable, and scalable AI systems today! This repository and content is developed and maintained by James Nguyen, Nicole Serafino, Kranthi Kumar Manchikanti, Heena Ugale, and Tim Sullivan.Transform Your AI Applications with Local LLM Deployment
Introduction Are you tired of watching your AI application costs spiral out of control every time your user base grows? As AI Engineers and Developers, we've all felt the pain of cloud-dependent LLM deployments. Every API call adds up, latency becomes a bottleneck in real-time applications, and sensitive data must leave your infrastructure to get processed. Meanwhile, your users demand faster responses, better privacy, and more reliable service. What if there was a way to run powerful language models directly on your users' devices or your local infrastructure? Enter the world of Edge AI deployment with Microsoft's Foundry Local a game-changing approach that brings enterprise-grade LLM capabilities to local hardware while maintaining full OpenAI API compatibility. The Edge AI for Beginners https://aka.ms/edgeai-for-beginners curriculum provides AI Engineers and Developers with comprehensive, hands-on training to master local LLM deployment. This isn't just another theoretical course, it's a practical guide that will transform how you think about AI infrastructure, combining cutting-edge local deployment techniques with production-ready implementation patterns. In this post, we'll explore why Edge AI deployment represents the future of AI applications, dive deep into Foundry Local's capabilities across multiple frameworks, and show you exactly how to implement local LLM solutions that deliver both technical excellence and significant business value. Why Edge AI Deployment Changes Everything for Developers The shift from cloud-dependent to edge-deployed AI represents more than just a technical evolution, it's a fundamental reimagining of how we build intelligent applications. As AI Engineers, we're witnessing a transformation that addresses the most pressing challenges in modern AI deployment while opening up entirely new possibilities for innovation. Consider the current state of cloud-based LLM deployment. Every user interaction requires a round-trip to external servers, introducing latency that can kill user experience in real-time applications. Costs scale linearly (or worse) with usage, making successful applications expensive to operate. Sensitive data must traverse networks and live temporarily in external systems, creating compliance nightmares for enterprise applications. Edge AI deployment fundamentally changes this equation. By running models locally, we achieve several critical advantages: Data Sovereignty and Privacy Protection: Your sensitive data never leaves your infrastructure. For healthcare applications processing patient records, financial services handling transactions, or enterprise tools managing proprietary information, this represents a quantum leap in security posture. You maintain complete control over data flow, meeting even the strictest compliance requirements without architectural compromises. Real-Time Performance at Scale: Local inference eliminates network latency entirely. Instead of 200-500ms round-trips to cloud APIs, you get sub-10ms response times. This enables entirely new categories of applications—real-time code completion, interactive AI tutoring systems, voice assistants that respond instantly, and IoT devices that make intelligent decisions without connectivity. Predictable Cost Structure: Transform variable API costs into fixed infrastructure investments. Instead of paying per-token for potentially unlimited usage, you invest in local hardware that serves unlimited requests. This makes ROI calculations straightforward and removes the fear of viral success destroying your margins. Offline Capabilities and Resilience: Local deployment means your AI features work even when connectivity fails. Mobile applications can provide intelligent features in areas with poor network coverage. Critical systems maintain AI capabilities during network outages. Edge devices in remote locations operate autonomously. The technical implications extend beyond these obvious benefits. Local deployment enables new architectural patterns: AI-powered applications that work entirely client-side, edge computing nodes that make intelligent routing decisions, and distributed systems where intelligence lives close to data sources. Foundry Local: Multi-Framework Edge AI Deployment Made Simple Microsoft's Foundry Local https://www.foundrylocal.ai represents a breakthrough in local AI deployment, designed specifically for developers who need production-ready edge AI solutions. Unlike single-framework tools, Foundry Local provides a unified platform that works seamlessly across multiple programming languages and deployment scenarios while maintaining full compatibility with existing OpenAI-based workflows. The platform's approach to multi-framework support means you're not locked into a single technology stack. Whether you're building TypeScript applications, Python ML pipelines, Rust systems programming projects, or .NET enterprise applications, Foundry Local provides native SDKs and consistent APIs that integrate naturally with your existing codebase. Enterprise-Grade Model Catalog: Foundry Local comes with a curated selection of production-ready models optimized for edge deployment. The `phi-3.5-mini` model delivers impressive performance in a compact footprint, perfect for resource-constrained environments. For applications requiring more sophisticated reasoning, `qwen2.5-0.5b` provides enhanced capabilities while maintaining efficiency. When you need maximum capability and have sufficient hardware resources, `gpt-oss-20b` offers state-of-the-art performance with full local control. Intelligent Hardware Optimization: One of Foundry Local's most powerful features is its automatic hardware detection and optimization. The platform automatically identifies your available compute resources, NVIDIA CUDA GPUs, AMD GPUs, Intel NPUs, Qualcomm Snapdragon NPUs, or CPU-only environments and downloads the most appropriate model variant. This means the same application code delivers optimal performance across diverse hardware configurations without manual intervention. ONNX Runtime Acceleration: Under the hood, Foundry Local leverages Microsoft's ONNX Runtime for maximum performance. This provides significant advantages over generic inference engines, delivering optimized execution paths for different hardware architectures while maintaining model accuracy and compatibility. OpenAI SDK Compatibility: Perhaps most importantly for developers, Foundry Local maintains complete API compatibility with the OpenAI SDK. This means existing applications can migrate to local inference by changing only the endpoint configuration—no rewriting of application logic, no learning new APIs, no disruption to existing workflows. The platform handles the complex aspects of local AI deployment automatically: model downloading, hardware-specific optimization, memory management, and inference scheduling. This allows developers to focus on building intelligent applications rather than managing AI infrastructure. Framework-Agnostic Benefits: Foundry Local's multi-framework approach delivers consistent benefits regardless of your technology choices. Whether you're working in a Node.js microservices architecture, a Python data science environment, a Rust embedded system, or a C# enterprise application, you get the same advantages: reduced latency, eliminated API costs, enhanced privacy, and offline capabilities. This universal compatibility means teams can adopt edge AI deployment incrementally, starting with pilot projects in their preferred language and expanding across their technology stack as they see results. The learning curve is minimal because the API patterns remain familiar while the underlying infrastructure transforms to local deployment. Implementing Edge AI: From Code to Production Moving from cloud APIs to local AI deployment requires understanding the implementation patterns that make edge AI both powerful and practical. Let's explore how Foundry Local's SDKs enable seamless integration across different development environments, with real-world code examples that you can adapt for your production systems. Python Implementation for Data Science and ML Pipelines Python developers will find Foundry Local's integration particularly natural, especially in data science and machine learning contexts where local processing is often preferred for security and performance reasons. import openai from foundry_local import FoundryLocalManager # Initialize with automatic hardware optimization alias = "phi-3.5-mini" manager = FoundryLocalManager(alias) This simple initialization handles a remarkable amount of complexity automatically. The `FoundryLocalManager` detects your hardware configuration, downloads the most appropriate model variant for your system, and starts the local inference service. Behind the scenes, it's making intelligent decisions about memory allocation, selecting optimal execution providers, and preparing the model for efficient inference. # Configure OpenAI client for local deployment client = openai.OpenAI( base_url=manager.endpoint, api_key=manager.api_key # Not required for local, but maintains API compatibility ) # Production-ready inference with streaming def analyze_document(content: str): stream = client.chat.completions.create( model=manager.get_model_info(alias).id, messages=[{ "role": "system", "content": "You are an expert document analyzer. Provide structured analysis." }, { "role": "user", "content": f"Analyze this document: {content}" }], stream=True, temperature=0.7 ) result = "" for chunk in stream: if chunk.choices[0].delta.content: content_piece = chunk.choices[0].delta.content result += content_piece yield content_piece # Enable real-time UI updates return result Key implementation benefits here: • Automatic model management: The `FoundryLocalManager` handles model lifecycle, memory optimization, and hardware-specific acceleration without manual configuration. • Streaming interface compatibility: Maintains the familiar OpenAI streaming API while processing locally, enabling real-time user interfaces with zero latency overhead. • Production error handling: The manager includes built-in retry logic, graceful degradation, and resource management for reliable production deployment. JavaScript/TypeScript Implementation for Web Applications JavaScript and TypeScript developers can integrate local AI capabilities directly into web applications, enabling entirely new categories of client-side intelligent features. import { OpenAI } from "openai"; import { FoundryLocalManager } from "foundry-local-sdk"; class LocalAIService { constructor() { this.foundryManager = null; this.openaiClient = null; this.isInitialized = false; } async initialize(modelAlias = "phi-3.5-mini") { this.foundryManager = new FoundryLocalManager(); const modelInfo = await this.foundryManager.init(modelAlias); this.openaiClient = new OpenAI({ baseURL: this.foundryManager.endpoint, apiKey: this.foundryManager.apiKey, }); this.isInitialized = true; return modelInfo; } The initialization pattern establishes local AI capabilities with full error handling and resource management. This enables web applications to provide AI features without external API dependencies. async generateCodeCompletion(codeContext, userPrompt) { if (!this.isInitialized) { throw new Error("LocalAI service not initialized"); } try { const completion = await this.openaiClient.chat.completions.create({ model: this.foundryManager.getModelInfo().id, messages: [ { role: "system", content: "You are a code completion assistant. Provide accurate, efficient code suggestions." }, { role: "user", content: `Context: ${codeContext}\n\nComplete: ${userPrompt}` } ], max_tokens: 150, temperature: 0.2 }); return completion.choices[0].message.content; } catch (error) { console.error("Local AI completion failed:", error); throw new Error("Code completion unavailable"); } } } Implementation advantages for web applications • Zero-dependency AI features: Applications work entirely offline once models are downloaded, enabling AI capabilities in disconnected environments. • Instant response times: Eliminate network latency for real-time features like code completion, content generation, or intelligent search. • Client-side privacy: Sensitive code or content never leaves the user's device, meeting strict security requirements for enterprise development tools. Cross-Platform Production Deployment Patterns Both Python and JavaScript implementations share common production deployment patterns that make Foundry Local particularly suitable for enterprise applications: Automatic Hardware Optimization: The platform automatically detects and utilizes available acceleration hardware. On systems with NVIDIA GPUs, it leverages CUDA acceleration. On newer Intel systems, it uses NPU acceleration. On ARM-based systems like Apple Silicon or Qualcomm Snapdragon, it optimizes for those architectures. This means the same application code delivers optimal performance across diverse deployment environments. Graceful Resource Management: Foundry Local includes sophisticated memory management and resource allocation. Models are loaded efficiently, memory is recycled properly, and concurrent requests are handled intelligently to maintain system stability under load. Production Monitoring Integration: The platform provides comprehensive metrics and logging that integrate naturally with existing monitoring systems, enabling production observability for AI workloads running at the edge. These implementation patterns demonstrate how Foundry Local transforms edge AI from an experimental concept into a practical, production-ready deployment strategy that works consistently across different technology stacks and hardware environments. Measuring Success: Technical Performance and Business Impact The transition to edge AI deployment delivers measurable improvements across both technical and business metrics. Understanding these impacts helps justify the architectural shift and demonstrates the concrete value of local LLM deployment in production environments. Technical Performance Gains Latency Elimination: The most immediately visible benefit is the dramatic reduction in response times. Cloud API calls typically require 200-800ms round-trips, depending on geographic location and network conditions. Local inference with Foundry Local reduces this to sub-10ms response times—a 95-99% improvement that fundamentally changes user experience possibilities. Consider a code completion feature: cloud-based completion feels sluggish and interrupts developer flow, while local completion provides instant suggestions that enhance productivity. The same applies to real-time chat applications, interactive AI tutoring systems, and any application where response latency directly impacts usability. Automatic Hardware Utilization: Foundry Local's intelligent hardware detection and optimization delivers significant performance improvements without manual configuration. On systems with NVIDIA RTX 4000 series GPUs, inference speeds can be 10-50x faster than CPU-only processing. On newer Intel systems with NPUs, the platform automatically leverages neural processing units for efficient AI workloads. Apple Silicon systems benefit from Metal Performance Shaders optimization, delivering excellent performance per watt. ONNX Runtime Optimization: Microsoft's ONNX Runtime provides substantial performance advantages over generic inference engines. In benchmark testing, ONNX Runtime consistently delivers 2-5x performance improvements compared to standard PyTorch or TensorFlow inference, while maintaining full model accuracy and compatibility. Scalability Characteristics: Local deployment transforms scaling economics entirely. Instead of linear cost scaling with usage, you get horizontal scaling through hardware deployment. A single modern GPU can handle hundreds of concurrent inference requests, making per-request costs approach zero for high-volume applications. Business Impact Analysis Cost Structure Transformation: The financial implications of local deployment are profound. Consider an application processing 1 million tokens daily through OpenAI's API—this represents $20-60 in daily costs depending on the model. Over a year, this becomes $7,300-21,900 in recurring expenses. A comparable local deployment might require a $2,000-5,000 hardware investment with no ongoing API costs. For high-volume applications, the savings become dramatic. Applications processing 100 million tokens monthly face $60,000-180,000 annual API costs. Local deployment with appropriate hardware infrastructure could reduce this to electricity and maintenance costs—typically under $10,000 annually for equivalent processing capacity. Enhanced Privacy and Compliance: Local deployment eliminates data sovereignty concerns entirely. Healthcare applications processing patient records, financial services handling transaction data, and enterprise tools managing proprietary information can deploy AI capabilities without data leaving their infrastructure. This simplifies compliance with GDPR, HIPAA, SOX, and other regulatory frameworks while reducing legal and security risks. Operational Resilience: Local deployment provides significant business continuity advantages. Applications continue functioning during network outages, API service disruptions, or third-party provider issues. For mission-critical systems, this resilience can prevent costly downtime and maintain user productivity during external service failures. Development Velocity: Local deployment accelerates development cycles by eliminating API rate limits, usage quotas, and external dependencies during development and testing. Developers can iterate freely, run comprehensive test suites, and experiment with AI features without cost concerns or rate limiting delays. Enterprise Adoption Metrics Real-world enterprise deployments demonstrate measurable business value: Local Usage: Foundry Local for internal AI-powered tools, reporting 60-80% reduction in AI-related operational costs while improving developer productivity through instant AI responses in development environments. Manufacturing Applications: Industrial IoT deployments using edge AI for predictive maintenance show 40-60% reduction in unplanned downtime while eliminating cloud connectivity requirements in remote facilities. Financial Services: Trading firms deploying local LLMs for market analysis report sub-millisecond decision latencies while maintaining complete data isolation for competitive advantage and regulatory compliance. ROI Calculation Framework For AI Engineers evaluating edge deployment, consider these quantifiable factors: Direct Cost Savings: Compare monthly API costs against hardware amortization over 24-36 months. Most applications with >$1,000 monthly API costs achieve positive ROI within 12-18 months. Performance Value: Quantify the business impact of reduced latency. For customer-facing applications, each 100ms of latency reduction typically correlates with 1-3% conversion improvement. Risk Mitigation: Calculate the cost of downtime or compliance violations prevented by local deployment. For many enterprise applications, avoiding a single significant outage justifies the infrastructure investment. Development Efficiency: Measure developer productivity improvements from unlimited local AI access during development. Teams report 20-40% faster iteration cycles when AI features can be tested without external dependencies. These metrics demonstrate that edge AI deployment with Foundry Local delivers both immediate technical improvements and substantial long-term business value, making it a strategic investment in AI infrastructure that pays dividends across multiple dimensions. Your Edge AI Journey Starts Here The shift to edge AI represents more than just a technical evolution, it's an opportunity to fundamentally improve your applications while building valuable expertise in an emerging field. Whether you're looking to reduce costs, improve performance, or enhance privacy, the path forward involves both learning new concepts and connecting with a community of practitioners solving similar challenges. Master Edge AI with Comprehensive Training The Edge AI for Beginners https://aka.ms/edgeai-for-beginners curriculum provides the complete foundation you need to become proficient in local AI deployment. This isn't a superficial overview, it's a comprehensive, hands-on program designed specifically for developers who want to build production-ready edge AI applications. The curriculum takes you through hours of structured learning, progressing from fundamental concepts to advanced deployment scenarios. You'll start by understanding the principles of edge AI and local inference, then dive deep into practical implementation with Foundry Local across multiple programming languages. The program includes working examples and comprehensive sample applications that demonstrate real-world use cases. What sets this curriculum apart is its practical focus. Instead of theoretical discussions, you'll build actual applications: document analysis systems that work offline, real-time code completion tools, intelligent chatbots that protect user privacy, and IoT applications that make decisions locally. Each project teaches both the technical implementation and the architectural thinking needed for successful edge AI deployment. The curriculum covers multi-framework deployment patterns extensively, ensuring you can apply edge AI principles regardless of your preferred development stack. Whether you're working in Python data science environments, JavaScript web applications, C# enterprise systems, or Rust embedded projects, you'll learn the patterns and practices that make edge AI successful. Join a Community of AI Engineers Learning edge AI doesn't happen in isolation, it requires connection with other developers who are solving similar challenges and discovering new possibilities. The Foundry Local Discord community https://aka.ms/foundry-local-discord provides exactly this environment, connecting AI Engineers and Developers from around the world who are implementing local AI solutions. This community serves multiple crucial functions for your development as an edge AI practitioner. You'll find experienced developers sharing implementation patterns they've discovered, debugging complex deployment issues collaboratively, and discussing the architectural decisions that make edge AI successful in production environments. The Discord community includes dedicated channels for different programming languages, specific deployment scenarios, and technical discussions about optimization and performance. Whether you're implementing your first local AI feature or optimizing a complex multi-model deployment, you'll find peers and experts ready to help problem-solve and share insights. Beyond technical support, the community provides valuable career and business insights. Members share their experiences with edge AI adoption in different industries, discuss the business cases that have proven most successful, and collaborate on open-source projects that advance the entire ecosystem. Share Your Experience and Build Expertise One of the most effective ways to solidify your edge AI expertise is by sharing your implementation experiences with the community. As you build applications with Foundry Local and deploy edge AI solutions, documenting your process and sharing your learnings provides value both to others and to your own professional development. Consider sharing your deployment stories, whether they're successes or challenges you've overcome. The community benefits from real-world case studies that show how edge AI performs in different environments and use cases. Your experience implementing local AI in a healthcare application, financial services system, or manufacturing environment provides valuable insights that others can build upon. Technical contributions are equally valuable, whether it's sharing configuration patterns you've discovered, performance optimizations you've implemented, or integration approaches you've developed for specific frameworks or libraries. The edge AI field is evolving rapidly, and practical contributions from working developers drive much of the innovation. Sharing your work also builds your professional reputation as an edge AI expert. As organizations increasingly adopt local AI deployment strategies, developers with proven experience in this area become valuable resources for their teams and the broader industry. The combination of structured learning through the Edge AI curriculum, active participation in the community, and sharing your practical experiences creates a comprehensive path to edge AI expertise that serves both your immediate project needs and your long-term career development as AI deployment patterns continue evolving. Key Takeaways Local LLM deployment transforms application economics: Replace variable API costs with fixed infrastructure investments that scale to unlimited usage, typically achieving ROI within 12-18 months for applications with significant AI workloads. Foundry Local enables multi-framework edge AI: Consistent deployment patterns across Python, JavaScript, C#, and Rust environments with automatic hardware optimization and OpenAI API compatibility. Performance improvements are dramatic and measurable: Sub-10ms response times replace 200-800ms cloud API latency, while automatic hardware acceleration delivers 2-50x performance improvements depending on available compute resources. Privacy and compliance become architectural advantages: Local deployment eliminates data sovereignty concerns, simplifies regulatory compliance, and provides complete control over sensitive information processing. Edge AI expertise is a strategic career investment: As organizations increasingly adopt local AI deployment, developers with hands-on edge AI experience become valuable technical resources with unique skills in an emerging field. Conclusion Edge AI deployment represents the next evolution in intelligent application development, transforming both the technical possibilities and economic models of AI-powered systems. With Foundry Local and the comprehensive Edge AI for Beginners curriculum, you have access to production-ready tools and expert guidance to make this transition successfully. The path forward is clear: start with the Edge AI for Beginners curriculum to build solid foundations, connect with the Foundry Local Discord community to learn from practicing developers, and begin implementing local AI solutions in your projects. Each step builds valuable expertise while delivering immediate improvements to your applications. As cloud costs continue rising and privacy requirements become more stringent, organizations will increasingly rely on developers who can implement local AI solutions effectively. Your early adoption of edge AI deployment patterns positions you at the forefront of this technological shift, with skills that will become increasingly valuable as the industry evolves. The future of AI deployment is local, private, and performance-optimized. Start building that future today. Resources Edge AI for Beginners Curriculum: Comprehensive training with 36-45 hours of hands-on content examples, and production-ready deployment patterns https://aka.ms/edgeai-for-beginners Foundry Local GitHub Repository: Official documentation, samples, and community contributions for local AI deployment https://github.com/microsoft/foundry_local Foundry Local Discord Community: Connect with AI Engineers and Developers implementing edge AI solutions worldwide https://aka.ms/foundry/discord Foundry Local Documentation: Complete technical documentation and API references Foundry Local documentation | Microsoft Learn Foundry Local Model Catalog: Browse available models and deployment options for different hardware configurations Foundry Local Models - Browse AI Models
