AZD for Beginners: A Practical Introduction to Azure Developer CLI
If you are learning how to get an application from your machine into Azure without stitching together every deployment step by hand, Azure Developer CLI, usually shortened to azd , is one of the most useful tools to understand early. It gives developers a workflow-focused command line for provisioning infrastructure, deploying application code, wiring environment settings, and working with templates that reflect real cloud architectures rather than toy examples. This matters because many beginners hit the same wall when they first approach Azure. They can build a web app locally, but once deployment enters the picture they have to think about resource groups, hosting plans, databases, secrets, monitoring, configuration, and repeatability all at once. azd reduces that operational overhead by giving you a consistent developer workflow. Instead of manually creating each resource and then trying to remember how everything fits together, you start with a template or an azd -compatible project and let the tool guide the path from local development to a running Azure environment. If you are new to the tool, the AZD for Beginners learning resources are a strong place to start. The repository is structured as a guided course rather than a loose collection of notes. It covers the foundations, AI-first deployment scenarios, configuration and authentication, infrastructure as code, troubleshooting, and production patterns. In other words, it does not just tell you which commands exist. It shows you how to think about shipping modern Azure applications with them. What Is Azure Developer CLI? The Azure Developer CLI documentation on Microsoft Learn, azd is an open-source tool designed to accelerate the path from a local development environment to Azure. That description is important because it explains what the tool is trying to optimise. azd is not mainly about managing one isolated Azure resource at a time. It is about helping developers work with complete applications. The simplest way to think about it is this. Azure CLI, az , is broad and resource-focused. It gives you precise control over Azure services. Azure Developer CLI, azd , is application-focused. It helps you take a solution made up of code, infrastructure definitions, and environment configuration and push that solution into Azure in a repeatable way. Those tools are not competitors. They solve different problems and often work well together. For a beginner, the value of azd comes from four practical benefits: It gives you a consistent workflow built around commands such as azd init , azd auth login , azd up , azd show , and azd down . It uses templates so you do not need to design every deployment structure from scratch on day one. It encourages infrastructure as code through files such as azure.yaml and the infra folder. It helps you move from a one-off deployment towards a repeatable development workflow that is easier to understand, change, and clean up. Why Should You Care About azd A lot of cloud frustration comes from context switching. You start by trying to deploy an app, but you quickly end up learning five or six Azure services, authentication flows, naming rules, environment variables, and deployment conventions all at once. That is not a good way to build confidence. azd helps by giving a workflow that feels closer to software delivery than raw infrastructure management. You still learn real Azure concepts, but you do so through an application lens. You initialise a project, authenticate, provision what is required, deploy the app, inspect the result, and tear it down when you are done. That sequence is easier to retain because it mirrors the way developers already think about shipping software. This is also why the AZD for Beginners resource is useful. It does not assume every reader is already comfortable with Azure. It starts with foundation topics and then expands into more advanced paths, including AI deployment scenarios that use the same core azd workflow. That progression makes it especially suitable for students, self-taught developers, workshop attendees, and engineers who know how to code but want a clearer path into Azure deployment. What You Learn from AZD for Beginners The AZD for Beginners course is structured as a learning journey rather than a single quickstart. That matters because azd is not just a command list. It is a deployment workflow with conventions, patterns, and trade-offs. The course helps readers build that mental model gradually. At a high level, the material covers: Foundational topics such as what azd is, how to install it, and how the basic deployment loop works. Template-based development, including how to start from an existing architecture rather than building everything yourself. Environment configuration and authentication practices, including the role of environment variables and secure access patterns. Infrastructure as code concepts using the standard azd project structure. Troubleshooting, validation, and pre-deployment thinking, which are often ignored in beginner content even though they matter in real projects. Modern AI and multi-service application scenarios, showing that azd is not limited to basic web applications. One of the strongest aspects of the course is that it does not stop at the first successful deployment. It also covers how to reason about configuration, resource planning, debugging, and production readiness. That gives learners a more realistic picture of what Azure development work actually looks like. The Core azd Workflow The official overview on Microsoft Learn and the get started guide both reinforce a simple but important idea: most beginners should first understand the standard workflow before worrying about advanced customisation. That workflow usually looks like this: Install azd . Authenticate with Azure. Initialise a project from a template or in an existing repository. Run azd up to provision and deploy. Inspect the deployed application. Remove the resources when finished. Here is a minimal example using an existing template: # Install azd on Windows winget install microsoft.azd # Check that the installation worked azd version # Sign in to your Azure account azd auth login # Start a project from a template azd init --template todo-nodejs-mongo # Provision Azure resources and deploy the app azd up # Show output values such as the deployed URL azd show # Clean up everything when you are done learning azd down --force --purge This sequence is important because it teaches beginners the full lifecycle, not only deployment. A lot of people remember azd up and forget the cleanup step. That leads to wasted resources and avoidable cost. The azd down --force --purge step is part of the discipline, not an optional extra. Installing azd and Verifying Your Setup The official install azd guide on Microsoft Learn provides platform-specific instructions. Because this repository targets developer learning, it is worth showing the common install paths clearly. # Windows winget install microsoft.azd # macOS brew tap azure/azd && brew install azd # Linux curl -fsSL https://aka.ms/install-azd.sh | bash After installation, verify the tool is available: azd version That sounds obvious, but it is worth doing immediately. Many beginner problems come from assuming the install completed correctly, only to discover a path issue or outdated version later. Verifying early saves time. The Microsoft Learn installation page also notes that azd installs supporting tools such as GitHub CLI and Bicep CLI within the tool's own scope. For a beginner, that is helpful because it removes some of the setup friction you might otherwise need to handle manually. What Happens When You Run azd up ? One of the most important questions is what azd up is actually doing. The short answer is that it combines provisioning and deployment into one workflow. The longer answer is where the learning value sits. When you run azd up , the tool looks at the project configuration, reads the infrastructure definition, determines which Azure resources need to exist, provisions them if necessary, and then deploys the application code to those resources. In many templates, it also works with environment settings and output values so that the project becomes reproducible rather than ad hoc. That matters because it teaches a more modern cloud habit. Instead of building infrastructure manually in the portal and then hoping you can remember how you did it, you define the deployment shape in source-controlled files. Even at beginner level, that is the right habit to learn. Understanding the Shape of an azd Project The Azure Developer CLI templates overview explains the standard project structure used by azd . If you understand this structure early, templates become much less mysterious. A typical azd project contains: azure.yaml to describe the project and map services to infrastructure targets. An infra folder containing Bicep or Terraform files for infrastructure as code. A src folder, or equivalent source folders, containing the application code that will be deployed. A local .azure folder to store environment-specific settings for the project. Here is a minimal example of what an azure.yaml file can look like in a simple app: name: beginner-web-app metadata: template: beginner-web-app services: web: project: ./src/web host: appservice This file is small, but it carries an important idea. azd needs a clear mapping between your application code and the Azure service that will host it. Once you see that, the tool becomes easier to reason about. You are not invoking magic. You are describing an application and its hosting model in a standard way. Start from a Template, Then Learn the Architecture Beginners often assume that using a template is somehow less serious than building something from scratch. In practice, it is usually the right place to begin. The official docs for templates and the Awesome AZD gallery both encourage developers to start from an existing architecture when it matches their goals. That is a sound learning strategy for two reasons. First, it lets you experience a working deployment quickly, which builds confidence. Second, it gives you a concrete project to inspect. You can look at azure.yaml , explore the infra folder, inspect the app source, and understand how the pieces connect. That teaches more than reading a command reference in isolation. The AZD for Beginners material also leans into this approach. It includes chapter guidance, templates, workshops, examples, and structured progression so that readers move from successful execution into understanding. That is much more useful than a single command demo. A practical beginner workflow looks like this: # Pick a known template azd init --template todo-nodejs-mongo # Review the files that were created or cloned # - azure.yaml # - infra/ # - src/ # Deploy it azd up # Open the deployed app details azd show Once that works, do not immediately jump to a different template. Spend time understanding what was deployed and why. Where AZD for Beginners Fits In The official docs are excellent for accurate command guidance and conceptual documentation. The AZD for Beginners repository adds something different: a curated learning path. It helps beginners answer questions such as these: Which chapter should I start with if I know Azure a little but not azd ? How do I move from a first deployment into understanding configuration and authentication? What changes when the application becomes an AI application rather than a simple web app? How do I troubleshoot failures instead of copying commands blindly? The repository also points learners towards workshops, examples, a command cheat sheet, FAQ material, and chapter-based exercises. That makes it particularly useful in teaching contexts. A lecturer or workshop facilitator can use it as a course backbone, while an individual learner can work through it as a self-study track. For developers interested in AI, the resource is especially timely because it shows how the same azd workflow can be used for AI-first solutions, including scenarios connected to Microsoft Foundry services and multi-agent architectures. The important beginner lesson is that the workflow stays recognisable even as the application becomes more advanced. Common Beginner Mistakes and How to Avoid Them A good introduction should not only explain the happy path. It should also point out the places where beginners usually get stuck. Skipping authentication checks. If azd auth login has not completed properly, later commands will fail in ways that are harder to interpret. Not verifying the installation. Run azd version immediately after install so you know the tool is available. Treating templates as black boxes. Always inspect azure.yaml and the infra folder so you understand what the project intends to provision. Forgetting cleanup. Learning environments cost money if you leave them running. Use azd down --force --purge when you are finished experimenting. Trying to customise too early. First get a known template working exactly as designed. Then change one thing at a time. If you do hit problems, the official troubleshooting documentation and the troubleshooting sections inside AZD for Beginners are the right next step. That is a much better habit than searching randomly for partial command snippets. How I Would Approach AZD as a New Learner If I were introducing azd to a student or a developer who is comfortable with code but new to Azure delivery, I would keep the learning path tight. Read the official What is Azure Developer CLI? overview so the purpose is clear. Install the tool using the Microsoft Learn install guide. Work through the opening sections of AZD for Beginners. Deploy one template with azd init and azd up . Inspect azure.yaml and the infrastructure files before making any changes. Run azd down --force --purge so the lifecycle becomes a habit. Only then move on to AI templates, configuration changes, or custom project conversion. That sequence keeps the cognitive load manageable. It gives you one successful deployment, one architecture to inspect, and one repeatable workflow to internalise before adding more complexity. Why azd Is Worth Learning Now azd matters because it reflects how modern Azure application delivery is actually done: repeatable infrastructure, source-controlled configuration, environment-aware workflows, and application-level thinking rather than isolated portal clicks. It is useful for straightforward web applications, but it becomes even more valuable as systems gain more services, more configuration, and more deployment complexity. That is also why the AZD for Beginners resource is worth recommending. It gives new learners a structured route into the tool instead of leaving them to piece together disconnected docs, samples, and videos on their own. Used alongside the official Microsoft Learn documentation, it gives you both accuracy and progression. Key Takeaways azd is an application-focused Azure deployment tool, not just another general-purpose CLI. The core beginner workflow is simple: install, authenticate, initialise, deploy, inspect, and clean up. Templates are not a shortcut to avoid learning. They are a practical way to learn architecture through working examples. AZD for Beginners is valuable because it turns the tool into a structured learning path. The official Microsoft Learn documentation for Azure Developer CLI should remain your grounding source for commands and platform guidance. Next Steps If you want to keep going, start with these resources: AZD for Beginners for the structured course, examples, and workshop materials. Azure Developer CLI documentation on Microsoft Learn for official command, workflow, and reference guidance. Install azd if you have not set up the tool yet. Deploy an azd template for the first full quickstart. Azure Developer CLI templates overview if you want to understand the project structure and template model. Awesome AZD if you want to browse starter architectures. If you are teaching others, this is also a good sequence for a workshop: start with the official overview, deploy one template, inspect the project structure, and then use AZD for Beginners as the path for deeper learning. That gives learners both an early win and a solid conceptual foundation.Agents League: Meet the Winners
Agents League brought together developers from around the world to build AI agents using Microsoft's developer tools. With 100+ submissions across three tracks, choosing winners was genuinely difficult. Today, we're proud to announce the category champions. 🎨 Creative Apps Winner: CodeSonify View project CodeSonify turns source code into music. As a genuinely thoughtful system, its functions become ascending melodies, loops create rhythmic patterns, conditionals trigger chord changes, and bugs produce dissonant sounds. It supports 7 programming languages and 5 musical styles, with each language mapped to its own key signature and code complexity directly driving the tempo. What makes CodeSonify stand out is the depth of execution. CodeSonify team delivered three integrated experiences: a web app with real-time visualization and one-click MIDI export, an MCP server exposing 5 tools inside GitHub Copilot in VS Code Agent Mode, and a diff sonification engine that lets you hear a code review. A clean refactor sounds harmonious. A messy one sounds chaotic. The team even built the MIDI generator from scratch in pure TypeScript with zero external dependencies. Built entirely with GitHub Copilot assistance, this is one of those projects that makes you think about code differently. 🧠 Reasoning Agents Winner: CertPrep Multi-Agent System View project CertPrep Multi-Agent System team built a production-grade 8-agent system for personalized Microsoft certification exam preparation, supporting 9 exam families including AI-102, AZ-204, AZ-305, and more. Each agent has a distinct responsibility: profiling the learner, generating a week-by-week study schedule, curating learning paths, tracking readiness, running mock assessments, and issuing a GO / CONDITIONAL GO / NOT YET booking recommendation. The engineering behind the scene here is impressive. A 3-tier LLM fallback chain ensures the system runs reliably even without Azure credentials, with the full pipeline completing in under 1 second in mock mode. A 17-rule guardrail pipeline validates every agent boundary. Study time allocation uses the Largest Remainder algorithm to guarantee no domain is silently zeroed out. 342 automated tests back it all up. This is what thoughtful multi-agent architecture looks like in practice. 💼 Enterprise Agents Winner: Whatever AI Assistant (WAIA) View project WAIA is a production-ready multi-agent system for Microsoft 365 Copilot Chat and Microsoft Teams. A workflow agent routes queries to specialized HR, IT, or Fallback agents, transparently to the user, handling both RAG-pattern Q&A and action automation — including IT ticket submission via a SharePoint list. Technically, it's a showcase of what serious enterprise agent development looks like: a custom MCP server secured with OAuth Identity Passthrough, streaming responses via the OpenAI Responses API, Adaptive Cards for human-in-the-loop approval flows, a debug mode accessible directly from Teams or Copilot, and full OpenTelemetry integration visible in the Foundry portal. Franck also shipped end-to-end automated Bicep deployment so the solution can land in any Azure environment. It's polished, thoroughly documented, and built to be replicated. Thank you To every developer who submitted and shipped projects during Agents League: thank you 💜 Your creativity and innovation brought Agents League to life! 👉 Browse all submissions on GitHubBuild a Fully Offline AI App with Foundry Local and CAG
A hands-on guide to building an on-device AI support agent using Context-Augmented Generation, JavaScript, and Foundry Local. You have probably heard the AI pitch: "just call our API." But what happens when your application needs to work without an internet connection? Perhaps your users are field engineers standing next to a pipeline in the middle of nowhere, or your organisation has strict data privacy requirements, or you simply want to build something that works without a cloud bill. This post walks you through how to build a fully offline, on-device AI application using Foundry Local and a pattern called Context-Augmented Generation (CAG). By the end, you will have a clear understanding of what CAG is, how it compares to RAG, and the practical steps to build your own solution. The finished application: a browser-based AI support agent that runs entirely on your machine. What Is Context-Augmented Generation? Context-Augmented Generation (CAG) is a pattern for making AI models useful with your own domain-specific content. Instead of hoping the model "knows" the answer from its training data, you pre-load your entire knowledge base into the model's context window at startup. Every query the model handles has access to all of your documents, all of the time. The flow is straightforward: Load your documents into memory when the application starts. Inject the most relevant documents into the prompt alongside the user's question. Generate a response grounded in your content. There is no retrieval pipeline, no vector database, and no embedding model. Your documents are read from disc, held in memory, and selected per query using simple keyword scoring. The model generates answers grounded in your content rather than relying on what it learnt during training. CAG vs RAG: Understanding the Trade-offs If you have explored AI application patterns before, you have likely encountered Retrieval-Augmented Generation (RAG). Both CAG and RAG solve the same core problem: grounding an AI model's answers in your own content. They take different approaches, and each has genuine strengths and limitations. CAG (Context-Augmented Generation) How it works: All documents are loaded at startup. The most relevant ones are selected per query using keyword scoring and injected into the prompt. Strengths: Drastically simpler architecture with no vector database, no embeddings, and no retrieval pipeline Works fully offline with no external services Minimal dependencies (just two npm packages in this sample) Near-instant document selection with no embedding latency Easy to set up, debug, and reason about Limitations: Constrained by the model's context window size Best suited to small, curated document sets (tens of documents, not thousands) Keyword scoring is less precise than semantic similarity for ambiguous queries Adding documents requires an application restart RAG (Retrieval-Augmented Generation) How it works: Documents are chunked, embedded into vectors, and stored in a database. At query time, the most semantically similar chunks are retrieved and injected into the prompt. Strengths: Scales to thousands or millions of documents Semantic search finds relevant content even when the user's wording differs from the source material Documents can be added or updated dynamically without restarting Fine-grained retrieval (chunk-level) can be more token-efficient for large collections Limitations: More complex architecture: requires an embedding model, a vector database, and a chunking strategy Retrieval quality depends heavily on chunking, embedding model choice, and tuning Additional latency from the embedding and search steps More dependencies and infrastructure to manage Want to compare these patterns hands-on? There is a RAG-based implementation of the same gas field scenario using vector search and embeddings. Clone both repositories, run them side by side, and see how the architectures differ in practice. When Should You Choose Which? Consideration Choose CAG Choose RAG Document count Tens of documents Hundreds or thousands Offline requirement Essential Optional (can run locally too) Setup complexity Minimal Moderate to high Document updates Infrequent (restart to reload) Frequent or dynamic Query precision Good for keyword-matchable content Better for semantically diverse queries Infrastructure None beyond the runtime Vector database, embedding model For the sample application in this post (20 gas engineering procedure documents on a local machine), CAG is the clear winner. If your use case grows to hundreds of documents or requires real-time ingestion, RAG becomes the better choice. Both patterns can run offline using Foundry Local. Foundry Local: Your On-Device AI Runtime Foundry Local is a lightweight runtime from Microsoft that downloads, manages, and serves language models entirely on your device. No cloud account, no API keys, no outbound network calls (after the initial model download). In this sample, your application is responsible for deciding which model to use, and it does that through the foundry-local-sdk . The app creates a FoundryLocalManager , asks the SDK for the local model catalogue, and then runs a small selection policy from src/modelSelector.js . That policy looks at the machine's available RAM, filters out models that are too large, ranks the remaining chat models by preference, and then returns the best fit for that device. Why does it work this way? Because shipping one fixed model would either exclude lower-spec machines or underuse more capable ones. A 14B model may be perfectly reasonable on a 32 GB workstation, but the same choice would be slow or unusable on an 8 GB laptop. By selecting at runtime, the same codebase can run across a wider range of developer machines without manual tuning. What makes it particularly useful for developers: No GPU required — runs on CPU or NPU, making it accessible on standard laptops and desktops Native SDK bindings — in-process inference via the foundry-local-sdk npm package, with no HTTP round-trips to a local server Automatic model management — downloads, caches, and loads models automatically Dynamic model selection — the SDK can evaluate your device's available RAM and pick the best model from the catalogue Real-time progress callbacks — ideal for building loading UIs that show download and initialisation progress The integration code is refreshingly minimal. Here is the core pattern: import { FoundryLocalManager } from "foundry-local-sdk"; // Create a manager and get the model catalogue const manager = FoundryLocalManager.create({ appName: "my-app" }); // Auto-select the best model for this device based on available RAM const models = await manager.catalog.getModels(); const model = selectBestModel(models); // Download if not cached, then load into memory if (!model.isCached) { await model.download((progress) => { console.log(`Download: ${progress.toFixed(0)}%`); }); } await model.load(); // Create a chat client for direct in-process inference const chatClient = model.createChatClient(); const response = await chatClient.completeChat([ { role: "system", content: "You are a helpful assistant." }, { role: "user", content: "How do I detect a gas leak?" } ]); That is it. No server configuration, no authentication tokens, no cloud provisioning. The model runs in the same process as your application. The download step matters for a simple reason: offline inference only works once the model files exist locally. The SDK checks whether the chosen model is already cached on the machine. If it is not, the application asks Foundry Local to download it once, store it locally, and then load it into memory. After that first run, the cached model can be reused, which is why subsequent launches are much faster and can operate without any network dependency. Put another way, there are two cooperating pieces here. Your application chooses which model is appropriate for the device and the scenario. Foundry Local and its SDK handle the mechanics of making that model available locally, caching it, loading it, and exposing a chat client for inference. That separation keeps the application logic clear whilst letting the runtime handle the heavy lifting. The Technology Stack The sample application is deliberately simple. No frameworks, no build steps, no Docker: Layer Technology Purpose AI Model Foundry Local + auto-selected model Runs locally via native SDK bindings; best model chosen for your device Back end Node.js + Express Lightweight HTTP server, everyone knows it Context Markdown files pre-loaded at startup No vector database, no embeddings, no retrieval step Front end Single HTML file with inline CSS No build step, mobile-responsive, field-ready The total dependency footprint is two npm packages: express and foundry-local-sdk . Architecture Overview The four-layer architecture, all running on a single machine. The system has four layers, all running in a single process on your device: Client layer: a single HTML file served by Express, with quick-action buttons and a responsive chat interface Server layer: Express.js starts immediately and serves the UI plus an SSE status endpoint; API routes handle chat (streaming and non-streaming), context listing, and health checks CAG engine: loads all domain documents at startup, selects the most relevant ones per query using keyword scoring, and injects them into the prompt AI layer: Foundry Local runs the auto-selected model on CPU/NPU via native SDK bindings (in-process inference, no HTTP round-trips) Building the Solution Step by Step Prerequisites You need two things installed on your machine: Node.js 20 or later: download from nodejs.org Foundry Local: Microsoft's on-device AI runtime: winget install Microsoft.FoundryLocal Foundry Local will automatically select and download the best model for your device the first time you run the application. You can override this by setting the FOUNDRY_MODEL environment variable to a specific model alias. Getting the Code Running # Clone the repository git clone https://github.com/leestott/local-cag.git cd local-cag # Install dependencies npm install # Start the server npm start Open http://127.0.0.1:3000 in your browser. You will see a loading overlay with a progress bar whilst the model downloads (first run only) and loads into memory. Once the model is ready, the overlay fades away and you can start chatting. Desktop view Mobile view How the CAG Pipeline Works Let us trace what happens when a user asks: "How do I detect a gas leak?" The query flow from browser to model and back. 1 Server starts and loads documents When you run npm start , the Express server starts on port 3000. All .md files in the docs/ folder are read, parsed (with optional YAML front-matter for title, category, and ID), and grouped by category. A document index is built listing all available topics. 2 Model is selected and loaded The model selector evaluates your system's available RAM and picks the best model from the Foundry Local catalogue. If the model is not already cached, it downloads it (with progress streamed to the browser via SSE). The model is then loaded into memory for in-process inference. 3 User sends a question The question arrives at the Express server. The chat engine selects the top 3 most relevant documents using keyword scoring. 4 Prompt is constructed The engine builds a messages array containing: the system prompt (with safety-first instructions), the document index (so the model knows all available topics), the 3 selected documents (approximately 6,000 characters), the conversation history, and the user's question. 5 Model generates a grounded response The prompt is sent to the locally loaded model via the Foundry Local SDK's native bindings. The response streams back token by token through Server-Sent Events to the browser. A response with safety warnings and step-by-step guidance The sources panel shows which documents were used Key Code Walkthrough Loading Documents (the Context Module) The context module reads all markdown files from the docs/ folder at startup. Each document can have optional YAML front-matter for metadata: // src/context.js export function loadDocuments() { const files = fs.readdirSync(config.docsDir) .filter(f => f.endsWith(".md")) .sort(); const docs = []; for (const file of files) { const raw = fs.readFileSync(path.join(config.docsDir, file), "utf-8"); const { meta, body } = parseFrontMatter(raw); docs.push({ id: meta.id || path.basename(file, ".md"), title: meta.title || file, category: meta.category || "General", content: body.trim(), }); } return docs; } There is no chunking, no vector computation, and no database. The documents are held in memory as plain text. Dynamic Model Selection Rather than hard-coding a model, the application evaluates your system at runtime: // src/modelSelector.js const totalRamMb = os.totalmem() / (1024 * 1024); const budgetMb = totalRamMb * 0.6; // Use up to 60% of system RAM // Filter to models that fit, rank by quality, boost cached models const candidates = allModels.filter(m => m.task === "chat-completion" && m.fileSizeMb <= budgetMb ); // Returns the best model: e.g. phi-4 on a 32 GB machine, // or phi-3.5-mini on a laptop with 8 GB RAM This means the same application runs on a powerful workstation (selecting a 14B parameter model) or a constrained laptop (selecting a 3.8B model), with no code changes required. This is worth calling out because it is one of the most practical parts of the sample. Developers do not have to decide up front which single model every user should run. The application makes that decision at startup based on the hardware budget you set, then asks Foundry Local to fetch the model if it is missing. The result is a smoother first-run experience and fewer support headaches when the same app is used on mixed hardware. The System Prompt For safety-critical domains, the system prompt is engineered to prioritise safety, prevent hallucination, and enforce structured responses: // src/prompts.js export const SYSTEM_PROMPT = `You are a local, offline support agent for gas field inspection and maintenance engineers. Behaviour Rules: - Always prioritise safety. If a procedure involves risk, explicitly call it out. - Do not hallucinate procedures, measurements, or tolerances. - If the answer is not in the provided context, say: "This information is not available in the local knowledge base." Response Format: - Summary (1-2 lines) - Safety Warnings (if applicable) - Step-by-step Guidance - Reference (document name + section)`; This pattern is transferable to any safety-critical domain: medical devices, electrical work, aviation maintenance, or chemical handling. Adapting This for Your Own Domain The sample project is designed to be forked and adapted. Here is how to make it yours in three steps: 1. Replace the documents Delete the gas engineering documents in docs/ and add your own markdown files. The context module handles any markdown content with optional YAML front-matter: --- title: Troubleshooting Widget Errors category: Support id: KB-001 --- # Troubleshooting Widget Errors ...your content here... 2. Edit the system prompt Open src/prompts.js and rewrite the system prompt for your domain. Keep the structure (summary, safety, steps, reference) and update the language to match your users' expectations. 3. Override the model (optional) By default the application auto-selects the best model. To force a specific model: # See available models foundry model list # Force a smaller, faster model FOUNDRY_MODEL=phi-3.5-mini npm start # Or a larger, higher-quality model FOUNDRY_MODEL=phi-4 npm start Smaller models give faster responses on constrained devices. Larger models give better quality. The auto-selector picks the largest model that fits within 60% of your system RAM. Building a Field-Ready UI The front end is a single HTML file with inline CSS. No React, no build tooling, no bundler. This keeps the project accessible to beginners and easy to deploy. Design decisions that matter for field use: Dark, high-contrast theme with 18px base font size for readability in bright sunlight Large touch targets (minimum 48px) for operation with gloves or PPE Quick-action buttons for common questions, so engineers do not need to type on a phone Responsive layout that works from 320px to 1920px+ screen widths Streaming responses via SSE, so the user sees tokens arriving in real time The mobile chat experience, optimised for field use. Visual Startup Progress with SSE A standout feature of this application is the loading experience. When the user opens the browser, they see a progress overlay showing exactly what the application is doing: Loading domain documents Initialising the Foundry Local SDK Selecting the best model for the device Downloading the model (with a percentage progress bar, first run only) Loading the model into memory This works because the Express server starts before the model finishes loading. The browser connects immediately and receives real-time status updates via Server-Sent Events. Chat endpoints return 503 whilst the model is loading, so the UI cannot send queries prematurely. // Server-side: broadcast status to all connected browsers function broadcastStatus(state) { initState = state; const payload = `data: ${JSON.stringify(state)}\n\n`; for (const client of statusClients) { client.write(payload); } } // During initialisation: broadcastStatus({ stage: "downloading", message: "Downloading phi-4...", progress: 42 }); This pattern is worth adopting in any application where model loading takes more than a few seconds. Users should never stare at a blank screen wondering whether something is broken. Testing The project includes unit tests using the built-in Node.js test runner, with no extra test framework needed: # Run all tests npm test Tests cover configuration, server endpoints, and document loading. Use them as a starting point when you adapt the project for your own domain. Ideas for Extending the Project Once you have the basics running, there are plenty of directions to explore: Conversation memory: persist chat history across sessions using local storage or a lightweight database Hybrid CAG + RAG: add a vector retrieval step for larger document collections that exceed the context window Multi-modal support: add image-based queries (photographing a fault code, for example) PWA packaging: make it installable as a standalone offline application on mobile devices Custom model fine-tuning: fine-tune a model on your domain data for even better answers Ready to Build Your Own? Clone the CAG sample, swap in your own documents, and have an offline AI agent running in minutes. Or compare it with the RAG approach to see which pattern suits your use case best. Get the CAG Sample Get the RAG Sample Summary Building a local AI application does not require a PhD in machine learning or a cloud budget. With Foundry Local, Node.js, and a set of domain documents, you can create a fully offline, mobile-responsive AI agent that answers questions grounded in your own content. The key takeaways: CAG is ideal for small, curated document sets where simplicity and offline capability matter most. No vector database, no embeddings, no retrieval pipeline. RAG scales further when you have hundreds or thousands of documents, or need semantic search for ambiguous queries. See the local-rag sample to compare. Foundry Local makes on-device AI accessible: native SDK bindings, in-process inference, automatic model selection, and no GPU required. The architecture is transferable. Replace the gas engineering documents with your own content, update the system prompt, and you have a domain-specific AI agent for any field. Start simple, iterate outwards. Begin with CAG and a handful of documents. If your needs outgrow the context window, graduate to RAG. Both patterns can run entirely offline. Clone the repository, swap in your own documents, and start building. The best way to learn is to get your hands on the code. This project is open source under the MIT licence. It is a scenario sample for learning and experimentation, not production medical or safety advice. local-cag on GitHub · local-rag on GitHub · Foundry LocalBuilding a Smart Building HVAC Digital Twin with AI Copilot Using Foundry Local
Introduction Building operations teams face a constant challenge: optimizing HVAC systems for energy efficiency while maintaining occupant comfort and air quality. Traditional building management systems display raw sensor data, temperatures, pressures, CO₂ levels—but translating this into actionable insights requires deep HVAC expertise. What if operators could simply ask "Why is the third floor so warm?" and get an intelligent answer grounded in real building state? This article demonstrates building a sample smart building digital twin with an AI-powered operations copilot, implemented using DigitalTwin, React, Three.js, and Microsoft Foundry Local. You'll learn how to architect physics-based simulators that model thermal dynamics, implement 3D visualizations of building systems, integrate natural language AI control, and design fault injection systems for testing and training. Whether you're building IoT platforms for commercial real estate, designing energy management systems, or implementing predictive maintenance for building automation, this sample provides proven patterns for intelligent facility operations. Why Digital Twins Matter for Building Operations Physical buildings generate enormous operational data but lack intelligent interpretation layers. A 50,000 square foot office building might have 500+ sensors streaming metrics every minute, zone temperatures, humidity levels, equipment runtimes, energy consumption. Traditional BMS (Building Management Systems) visualize this data as charts and gauges, but operators must manually correlate patterns, diagnose issues, and predict failures. Digital twins solve this through physics-based simulation coupled with AI interpretation. Instead of just displaying current temperature readings, a digital twin models thermal dynamics, heat transfer rates, HVAC response characteristics, occupancy impacts. When conditions deviate from expectations, the twin compares observed versus predicted states, identifying root causes. Layer AI on top, and operators get natural language explanations: "The conference room is 3 degrees too warm because the VAV damper is stuck at 40% open, reducing airflow by 60%." This application focuses on HVAC, the largest building energy consumer, typically 40-50% of total usage. Optimizing HVAC by just 10% through better controls can save thousands of dollars monthly while improving occupant satisfaction. The digital twin enables "what-if" scenarios before making changes: "What happens to energy consumption and comfort if we raise the cooling setpoint by 2 degrees during peak demand response events?" Architecture: Three-Tier Digital Twin System The application implements a clean three-tier architecture separating visualization, simulation, and state management: The frontend uses React with Three.js for 3D visualization. Users see an interactive 3D model of the three-floor building with color-coded zones indicating temperature and CO₂ levels. Click any equipment, AHUs, VAVs, chillers, to see detailed telemetry. The control panel enables adjusting setpoints, running simulation steps, and activating demand response scenarios. Real-time charts display KPIs: energy consumption, comfort compliance, air quality levels. The backend Node.js/Express server orchestrates simulation and state management. It maintains the digital twin state as JSON, the single source of truth for all equipment, zones, and telemetry. REST API endpoints handle control requests, simulation steps, and AI copilot queries. WebSocket connections push real-time updates to the frontend for live monitoring. The HVAC simulator implements physics-based models: 1R1C thermal models for zones, affinity laws for fan power, chiller COP calculations, CO₂ mass balance equations. Foundry Local provides AI copilot capabilities. The backend uses foundry-local-sdk to query locally running models. Natural language queries ("How's the lobby temperature?") get answered with building state context. The copilot can explain anomalies, suggest optimizations, and even execute commands when explicitly requested. Implementing Physics-Based HVAC Simulation Accurate simulation requires modeling actual HVAC physics. The simulator implements several established building energy models: // backend/src/simulator/thermal-model.js class ZoneThermalModel { // 1R1C (one resistance, one capacitance) thermal model static calculateTemperatureChange(zone, delta_t_seconds) { const C_thermal = zone.volume * 1.2 * 1000; // Heat capacity (J/K) const R_thermal = zone.r_value * zone.envelope_area; // Thermal resistance // Internal heat gains (occupancy, equipment, lighting) const Q_internal = zone.occupancy * 100 + // 100W per person zone.equipment_load + zone.lighting_load; // Cooling/heating from HVAC const airflow_kg_s = zone.vav.airflow_cfm * 0.0004719; // CFM to kg/s const c_p_air = 1006; // Specific heat of air (J/kg·K) const Q_hvac = airflow_kg_s * c_p_air * (zone.vav.supply_temp - zone.temperature); // Envelope losses const Q_envelope = (zone.outdoor_temp - zone.temperature) / R_thermal; // Net energy balance const Q_net = Q_internal + Q_hvac + Q_envelope; // Temperature change: Q = C * dT/dt const dT = (Q_net / C_thermal) * delta_t_seconds; return zone.temperature + dT; } } This model captures essential thermal dynamics while remaining computationally fast enough for real-time simulation. It accounts for internal heat generation from occupants and equipment, HVAC cooling/heating contributions, and heat loss through the building envelope. The CO₂ model uses mass balance equations: class AirQualityModel { static calculateCO2Change(zone, delta_t_seconds) { // CO₂ generation from occupants const G_co2 = zone.occupancy * 0.0052; // L/s per person at rest // Outdoor air ventilation rate const V_oa = zone.vav.outdoor_air_cfm * 0.000471947; // CFM to m³/s // CO₂ concentration difference (indoor - outdoor) const delta_CO2 = zone.co2_ppm - 400; // Outdoor ~400ppm // Mass balance: dC/dt = (G - V*ΔC) / Volume const dCO2_dt = (G_co2 - V_oa * delta_CO2) / zone.volume; return zone.co2_ppm + (dCO2_dt * delta_t_seconds); } } These models execute every simulation step, updating the entire building state: async function simulateStep(twin, timestep_minutes) { const delta_t = timestep_minutes * 60; // Convert to seconds // Update each zone for (const zone of twin.zones) { zone.temperature = ZoneThermalModel.calculateTemperatureChange(zone, delta_t); zone.co2_ppm = AirQualityModel.calculateCO2Change(zone, delta_t); } // Update equipment based on zone demands for (const vav of twin.vavs) { updateVAVOperation(vav, twin.zones); } for (const ahu of twin.ahus) { updateAHUOperation(ahu, twin.vavs); } updateChillerOperation(twin.chiller, twin.ahus); updateBoilerOperation(twin.boiler, twin.ahus); // Calculate system KPIs twin.kpis = calculateSystemKPIs(twin); // Detect alerts twin.alerts = detectAnomalies(twin); // Persist updated state await saveTwinState(twin); return twin; } 3D Visualization with React and Three.js The frontend renders an interactive 3D building view that updates in real-time as conditions change. Using React Three Fiber simplifies Three.js integration with React's component model: // frontend/src/components/BuildingView3D.jsx import { Canvas } from '@react-three/fiber'; import { OrbitControls } from '@react-three/drei'; export function BuildingView3D({ twinState }) { return ( {/* Render building floors */} {twinState.zones.map(zone => ( selectZone(zone.id)} /> ))} {/* Render equipment */} {twinState.ahus.map(ahu => ( ))} ); } function ZoneMesh({ zone, onClick }) { const color = getTemperatureColor(zone.temperature, zone.setpoint); return ( ); } function getTemperatureColor(current, setpoint) { const deviation = current - setpoint; if (Math.abs(deviation) < 1) return '#00ff00'; // Green: comfortable if (Math.abs(deviation) < 3) return '#ffff00'; // Yellow: acceptable return '#ff0000'; // Red: uncomfortable } This visualization immediately shows building state at a glance, operators see "hot spots" in red, comfortable zones in green, and can click any area for detailed metrics. Integrating AI Copilot for Natural Language Control The AI copilot transforms building data into conversational insights. Instead of navigating multiple screens, operators simply ask questions: // backend/src/routes/copilot.js import { FoundryLocalClient } from 'foundry-local-sdk'; const foundry = new FoundryLocalClient({ endpoint: process.env.FOUNDRY_LOCAL_ENDPOINT }); router.post('/api/copilot/chat', async (req, res) => { const { message } = req.body; // Load current building state const twin = await loadTwinState(); // Build context for AI const context = buildBuildingContext(twin); const completion = await foundry.chat.completions.create({ model: 'phi-4', messages: [ { role: 'system', content: `You are an HVAC operations assistant for a 3-floor office building. Current Building State: ${context} Answer questions about equipment status, comfort conditions, and energy usage. Provide specific, actionable information based on the current data. Do not speculate beyond provided information.` }, { role: 'user', content: message } ], temperature: 0.3, max_tokens: 300 }); res.json({ response: completion.choices[0].message.content, model: 'phi-4', timestamp: new Date().toISOString() }); }); function buildBuildingContext(twin) { const alerts = twin.alerts.filter(a => a.active); const zoneStatus = twin.zones.map(z => `${z.name}: ${z.temperature.toFixed(1)}°F (setpoint: ${z.setpoint}°F), CO₂: ${z.co2_ppm}ppm, ${z.occupancy} people` ); return ` Zones: ${zoneStatus.join('\n')} Active Alerts: ${alerts.length} ${alerts.map(a => `- ${a.severity}: ${a.message}`).join('\n')} Energy: ${twin.kpis.total_power_kw.toFixed(1)} kW Chiller: ${twin.chiller.percent_load}% load, ${twin.chiller.cop.toFixed(2)} COP `.trim(); } Example interactions: User: "Why is the third floor conference room warm?" AI: "The Executive Suite on Floor 3 is currently 75.2°F, 3 degrees above the 72°F setpoint. This is due to high occupancy (8 people) and VAV-F3-EXEC operating at reduced airflow (285 CFM vs 450 CFM capacity). AHU-2 is supplying adequate cool air at 55°F. Recommend checking VAV damper position—it may be partially stuck." User: "What's our current energy usage?" AI: "Total building power consumption is 47.3 kW. Breakdown: Chiller (24.1 kW, 51%), AHU fans (12.8 kW, 27%), Pumps (7.2 kW, 15%), Other (3.2 kW, 7%). Chiller is operating at 62% load with a COP of 4.8, which is efficient for current conditions." User: "Activate demand response level 2" AI: "I cannot directly control building systems for safety reasons. To activate DR Level 2, use the Control Panel and click 'Demand Response' → 'Level 2'. This will raise cooling setpoints by 3°F and reduce auxiliary loads, targeting 15% energy reduction." The AI provides grounded, specific answers citing actual equipment IDs and metrics. It refuses to directly execute control commands, instead guiding operators to explicit control interfaces, a critical safety pattern for building systems. Fault Injection for Testing and Training Real building operations experience equipment failures, stuck dampers, sensor drift, communication losses. The digital twin includes comprehensive fault injection capabilities to train operators and test control logic: // backend/src/simulator/fault-injector.js const FAULT_CATALOG = { chillerFailure: { description: 'Chiller compressor failure', apply: (twin) => { twin.chiller.status = 'FAULT'; twin.chiller.cooling_output = 0; twin.alerts.push({ id: 'chiller-fault', severity: 'CRITICAL', message: 'Chiller compressor failure - no cooling available', equipment: 'CHILLER-01' }); } }, stuckVAVDamper: { description: 'VAV damper stuck at current position', apply: (twin, vavId) => { const vav = twin.vavs.find(v => v.id === vavId); vav.damper_stuck = true; vav.damper_position_fixed = vav.damper_position; twin.alerts.push({ id: `vav-stuck-${vavId}`, severity: 'HIGH', message: `VAV ${vavId} damper stuck at ${vav.damper_position}%`, equipment: vavId }); } }, sensorDrift: { description: 'Temperature sensor reading 5°F high', apply: (twin, zoneId) => { const zone = twin.zones.find(z => z.id === zoneId); zone.sensor_drift = 5.0; zone.temperature_measured = zone.temperature_actual + 5.0; } }, communicationLoss: { description: 'Equipment communication timeout', apply: (twin, equipmentId) => { const equipment = findEquipmentById(twin, equipmentId); equipment.comm_status = 'OFFLINE'; equipment.stale_data = true; twin.alerts.push({ id: `comm-loss-${equipmentId}`, severity: 'MEDIUM', message: `Lost communication with ${equipmentId}`, equipment: equipmentId }); } } }; router.post('/api/twin/fault', async (req, res) => { const { faultType, targetEquipment } = req.body; const twin = await loadTwinState(); const fault = FAULT_CATALOG[faultType]; if (!fault) { return res.status(400).json({ error: 'Unknown fault type' }); } fault.apply(twin, targetEquipment); await saveTwinState(twin); res.json({ message: `Applied fault: ${fault.description}`, affectedEquipment: targetEquipment, timestamp: new Date().toISOString() }); }); Operators can inject faults to practice diagnosis and response. Training scenarios might include: "The chiller just failed during a heat wave, how do you maintain comfort?" or "Multiple VAV dampers are stuck, which zones need immediate attention?" Key Takeaways and Production Deployment Building a physics-based digital twin with AI capabilities requires balancing simulation accuracy with computational performance, providing intuitive visualization while maintaining technical depth, and enabling AI assistance without compromising safety. Key architectural lessons: Physics models enable prediction: Comparing predicted vs observed behavior identifies anomalies that simple thresholds miss 3D visualization improves spatial understanding: Operators immediately see which floors or zones need attention AI copilots accelerate diagnosis: Natural language queries get answers in seconds vs. minutes of manual data examination Fault injection validates readiness: Testing failure scenarios prepares operators for real incidents JSON state enables integration: Simple file-based state makes connecting to real BMS systems straightforward For production deployment, connect the twin to actual building systems via BACnet, Modbus, or MQTT integrations. Replace simulated telemetry with real sensor streams. Calibrate model parameters against historical building performance. Implement continuous learning where the twin's predictions improve as it observes actual building behavior. The complete implementation with simulation engine, 3D visualization, AI copilot, and fault injection system is available at github.com/leestott/DigitalTwin. Clone the repository and run the startup scripts to explore the digital twin, no building hardware required. Resources and Further Reading Smart Building HVAC Digital Twin Repository - Complete source code and simulation engine Setup and Quick Start Guide - Installation instructions and usage examples Microsoft Foundry Local Documentation - AI integration reference HVAC Simulation Documentation - Physics model details and calibration Three.js Documentation - 3D visualization framework ASHRAE Standards - Building energy modeling standardsHosted Containers and AI Agent Solutions
If you have built a proof-of-concept AI agent on your laptop and wondered how to turn it into something other people can actually use, you are not alone. The gap between a working prototype and a production-ready service is where most agent projects stall. Hosted containers close that gap faster than any other approach available today. This post walks through why containers and managed hosting platforms like Azure Container Apps are an ideal fit for multi-agent AI systems, what practical benefits they unlock, and how you can get started with minimal friction. The problem with "it works on my machine" Most AI agent projects begin the same way: a Python script, an API key, and a local terminal. That workflow is perfect for experimentation, but it creates a handful of problems the moment you try to share your work. First, your colleagues need the same Python version, the same dependencies, and the same environment variables. Second, long-running agent pipelines tie up your machine and compete with everything else you are doing. Third, there is no reliable URL anyone can visit to use the system, which means every demo involves a screen share or a recorded video. Containers solve all three problems in one step. A single Dockerfile captures the runtime, the dependencies, and the startup command. Once the image builds, it runs identically on any machine, any cloud, or any colleague's laptop. Why containers suit AI agents particularly well AI agents have characteristics that make them a better fit for containers than many traditional web applications. Long, unpredictable execution times A typical web request completes in milliseconds. An agent pipeline that retrieves context from a database, imports a codebase, runs four verification agents in sequence, and generates a report can take two to five minutes. Managed container platforms handle long-running requests gracefully, with configurable timeouts and automatic keep-alive, whereas many serverless platforms impose strict execution limits that agent workloads quickly exceed. Heavy, specialised dependencies Agent applications often depend on large packages: machine learning libraries, language model SDKs, database drivers, and Git tooling. A container image bundles all of these once at build time. There is no cold-start dependency resolution and no version conflict with other projects on the same server. Stateless by design Most agent pipelines are stateless. They receive a request, execute a sequence of steps, and return a result. This maps perfectly to the container model, where each instance handles requests independently and the platform can scale the number of instances up or down based on demand. Reproducible environments When an agent misbehaves in production, you need to reproduce the issue locally. With containers, the production environment and the local environment are the same image. There is no "works on my machine" ambiguity. A real example: multi-agent code verification To make this concrete, consider a system called Opustest, an open-source project that uses the Microsoft Agent Framework with Azure OpenAI to analyse Python codebases automatically. The system runs AI agents in a pipeline: A Code Example Retrieval Agent queries Azure Cosmos DB for curated examples of good and bad Python code, providing the quality standards for the review. A Codebase Import Agent reads all Python files from a Git repository cloned on the server. Four Verification Agents each score a different dimension of code quality (coding standards, functional correctness, known error handling, and unknown error handling) on a scale of 0 to 5. A Report Generation Agent compiles all scores and errors into an HTML report with fix prompts that can be exported and fed directly into a coding assistant. The entire pipeline is orchestrated by a FastAPI backend that streams progress updates to the browser via Server-Sent Events. Users paste a Git URL, watch each stage light up in real time, and receive a detailed report at the end. The app in action Landing page: the default Git URL mode, ready for a repository link. Local Path mode: toggling to analyse a codebase from a local directory. Repository URL entered: a GitHub repository ready for verification. Stage 1: the Code Example Retrieval Agent fetching standards from Cosmos DB. Stage 3: the four Verification Agents scoring the codebase. Stage 4: the Report Generation Agent compiling the final report. Verification complete: all stages finished with a success banner. Report detail: scores and the errors table with fix prompts. The Dockerfile The container definition for this system is remarkably simple: FROM python:3.12-slim RUN apt-get update && apt-get install -y --no-install-recommends git \ && rm -rf /var/lib/apt/lists/* WORKDIR /app COPY requirements.txt . RUN pip install --no-cache-dir -r requirements.txt COPY backend/ backend/ COPY frontend/ frontend/ RUN adduser --disabled-password --gecos "" appuser USER appuser EXPOSE 8000 CMD ["uvicorn", "backend.app:app", "--host", "0.0.0.0", "--port", "8000"] Twenty lines. That is all it takes to package a six-agent AI system with a web frontend, a FastAPI backend, Git support, and all Python dependencies into a portable, production-ready image. Notice the security detail: the container runs as a non-root user. This is a best practice that many tutorials skip, but it matters when you are deploying to a shared platform. From image to production in one command With the Azure Developer CLI ( azd ), deploying this container to Azure Container Apps takes a single command: azd up Behind the scenes, azd reads an azure.yaml file that declares the project structure, provisions the infrastructure defined in Bicep templates (a Container Apps environment, an Azure Container Registry, and a Cosmos DB account), builds the Docker image, pushes it to the registry, deploys it to the container app, and even seeds the database with sample data via a post-provision hook. The result is a publicly accessible URL serving the full agent system, with automatic HTTPS, built-in scaling, and zero infrastructure to manage manually. Microsoft Hosted Agents vs Azure Container Apps: choosing the right home Microsoft offers two distinct approaches for running AI agent workloads in the cloud. Understanding the difference is important when deciding how to host your solution. Microsoft Foundry Hosted Agent Service (Microsoft Foundry) Microsoft Foundry provides a fully managed agent hosting service. You define your agent's behaviour declaratively, upload it to the platform, and Foundry handles execution, scaling, and lifecycle management. This is an excellent choice when your agents fit within the platform's conventions: single-purpose agents that respond to prompts, use built-in tool integrations, and do not require custom server-side logic or a bespoke frontend. Key characteristics of hosted agents in Foundry: Fully managed execution. You do not provision or maintain any infrastructure. The platform runs your agent and handles scaling automatically. Declarative configuration. Agents are defined through configuration and prompt templates rather than custom application code. Built-in tool ecosystem. Foundry provides pre-built connections to Azure services, knowledge stores, and evaluation tooling. Opinionated runtime. The platform controls the execution environment, request handling, and networking. Azure Container Apps Azure Container Apps is a managed container hosting platform. You package your entire application (agents, backend, frontend, and all dependencies) into a Docker image and deploy it. The platform handles scaling, HTTPS, and infrastructure, but you retain full control over what runs inside the container. Key characteristics of Container Apps: Full application control. You own the runtime, the web framework, the agent orchestration logic, and the frontend. Custom networking. You can serve a web UI, expose REST APIs, stream Server-Sent Events, or run WebSocket connections. Arbitrary dependencies. Your container can include any system package, any Python library, and any tooling (like Git for cloning repositories). Portable. The same Docker image runs locally, in CI, and in production without modification. Why Opustest uses Container Apps Opustest requires capabilities that go beyond what a managed agent hosting platform provides: Requirement Hosted Agents (Foundry) Container Apps Custom web UI with real-time progress Not supported natively Full control via FastAPI and SSE Multi-agent orchestration pipeline Platform-managed, limited customisation Custom orchestrator with arbitrary logic Git repository cloning on the server Not available Install Git in the container image Server-Sent Events streaming Not supported Full HTTP control Custom HTML report generation Limited to platform outputs Generate and serve any content Export button for Copilot prompts Not available Custom frontend with JavaScript RAG retrieval from Cosmos DB Possible via built-in connectors Direct SDK access with full query control The core reason is straightforward: Opustest is not just a set of agents. It is a complete web application that happens to use agents as its processing engine. It needs a custom frontend, real-time streaming, server-side Git operations, and full control over how the agent pipeline executes. Container Apps provides all of this while still offering managed infrastructure, automatic scaling, and zero server maintenance. When to choose which Choose Microsoft Hosted Agents when your use case is primarily conversational or prompt-driven, when you want the fastest path to a working agent with minimal code, and when the built-in tool ecosystem covers your integration needs. Choose Azure Container Apps when you need a custom frontend, custom orchestration logic, real-time streaming, server-side processing beyond prompt-response patterns, or when your agent system is part of a larger application with its own web server and API surface. Both approaches use the same underlying AI models via Azure OpenAI. The difference is in how much control you need over the surrounding application. Five practical benefits of hosted containers for agents 1. Consistent deployments across environments Whether you are running the container locally with docker run , in a CI pipeline, or on Azure Container Apps, the behaviour is identical. Configuration differences are handled through environment variables, not code changes. This eliminates an entire category of "it works locally but breaks in production" bugs. 2. Scaling without re-architecture Azure Container Apps can scale from zero instances (paying nothing when idle) to multiple instances under load. Because agent pipelines are stateless, each request is routed to whichever instance is available. You do not need to redesign your application to handle concurrency; the platform does it for you. 3. Isolation between services If your agent system grows to include multiple services (perhaps a separate service for document processing or a background worker for batch analysis), each service gets its own container. They can be deployed, scaled, and updated independently. A bug in one service does not bring down the others. 4. Built-in observability Managed container platforms provide logging, metrics, and health checks out of the box. When an agent pipeline fails after three minutes of execution, you can inspect the container logs to see exactly which stage failed and why, without adding custom logging infrastructure. 5. Infrastructure as code The entire deployment can be defined in code. Bicep templates, Terraform configurations, or Pulumi programmes describe every resource. This means deployments are repeatable, reviewable, and version-controlled alongside your application code. No clicking through portals, no undocumented manual steps. Common concerns addressed "Containers add complexity" For a single-file script, this is a fair point. But the moment your agent system has more than one dependency, a Dockerfile is simpler to maintain than a set of installation instructions. It is also self-documenting: anyone reading the Dockerfile knows exactly what the system needs to run. "Serverless is simpler" Serverless functions are excellent for short, event-driven tasks. But agent pipelines that run for minutes, require persistent connections (like SSE streaming), and depend on large packages are a poor fit for most serverless platforms. Containers give you the operational simplicity of managed hosting without the execution constraints. "I do not want to learn Docker" A basic Dockerfile for a Python application is fewer than ten lines. The core concepts are straightforward: start from a base image, install dependencies, copy your code, and specify the startup command. The learning investment is small relative to the deployment problems it solves. "What about cost?" Azure Container Apps supports scale-to-zero, meaning you pay nothing when the application is idle. For development and demonstration purposes, this makes hosted containers extremely cost-effective. You only pay for the compute time your agents actually use. Getting started: a practical checklist If you are ready to containerise your own agent solution, here is a step-by-step approach. Step 1: Write a Dockerfile. Start from an official Python base image. Install system-level dependencies (like Git, if your agents clone repositories), then your Python packages, then your application code. Run as a non-root user. Step 2: Test locally. Build and run the image on your machine: docker build -t my-agent-app . docker run -p 8000:8000 --env-file .env my-agent-app If it works locally, it will work in the cloud. Step 3: Define your infrastructure. Use Bicep, Terraform, or the Azure Developer CLI to declare the resources you need: a container app, a container registry, and any backing services (databases, key vaults, AI endpoints). Step 4: Deploy. Push your image to the registry and deploy to the container platform. With azd , this is a single command. With CI/CD, it is a pipeline that runs on every push to your main branch. Step 5: Iterate. Change your agent code, rebuild the image, and redeploy. The cycle is fast because Docker layer caching means only changed layers are rebuilt. The broader picture The AI agent ecosystem is maturing rapidly. Frameworks like Microsoft Agent Framework, LangChain, Semantic Kernel, and AutoGen make it straightforward to build sophisticated multi-agent systems. But building is only half the challenge. The other half is running these systems reliably, securely, and at scale. Hosted containers offer the best balance of flexibility and operational simplicity for agent workloads. They do not impose the execution limits of serverless platforms. They do not require the operational overhead of managing virtual machines. They give you a portable, reproducible unit of deployment that works the same everywhere. If you have an agent prototype sitting on your laptop, the path to making it available to your team, your organisation, or the world is shorter than you think. Write a Dockerfile, define your infrastructure, run azd up , and share the URL. Your agents deserve a proper home. Hosted containers are that home. Resources Azure Container Apps documentation Microsoft Foundry Hosted Agents Azure Developer CLI (azd) Microsoft Agent Framework Docker getting started guide Opustest: AI-powered code verification (source code)Announcing the IQ Series: Foundry IQ
AI agents are rapidly becoming a new way to build applications. But for agents to be truly useful, they need access to the knowledge and context that helps them reason about the world they operate in. That’s where Foundry IQ comes in. Today we’re announcing the IQ Series: Foundry IQ, a new set of developer-focused episodes exploring how to build knowledge-centric AI systems using Foundry IQ. The series focuses on the core ideas behind how modern AI systems work with knowledge, how they retrieve information, reason across sources, synthesize answers, and orchestrate multi-step interactions. Instead of treating retrieval as a single step in a pipeline, Foundry IQ approaches knowledge as something that AI systems actively work with throughout the reasoning process. The IQ Series breaks down these concepts and shows how they come together when building real AI applications. You can explore the series and all the accompanying samples here: 👉 https://aka.ms/iq-series What is Foundry IQ? Foundry IQ helps AI systems work with knowledge in a more structured and intentional way. Rather than wiring retrieval logic directly into every application, developers can define knowledge bases that connect to documents, data sources, and other information systems. AI agents can then query these knowledge bases to gather the context they need to generate responses, make decisions, or complete tasks. This model allows knowledge to be organized, reused, and combined across applications, instead of being rebuilt for each new scenario. What's covered in the IQ Series? The Foundry IQ episodes in the IQ Series explore the key building blocks behind knowledge-driven AI systems from how knowledge enters the system to how agents ultimately query and use it. The series is released as three weekly episodes: Foundry IQ: Unlocking Knowledge for Your Agents — March 18, 2026: Introduces Foundry IQ and the core ideas behind it. The episode explains how AI agents work with knowledge and walks through the main components of the Foundry IQ that support knowledge-driven applications. Foundry IQ: Building the Data Pipeline with Knowledge Sources — March 25, 2026: Focuses on Knowledge Sources and how different types of content flow into Foundry IQ. It explores how systems such as SharePoint, Fabric, OneLake, Azure Blob Storage, Azure AI Search, and the web contribute information that AI systems can later retrieve and use. Foundry IQ: Querying the Multi-Source AI Knowledge Bases — April 1, 2026: Dives into the Knowledge Bases and how multiple knowledge sources can be organized behind a single endpoint. The episode demonstrates how AI systems query across these sources and synthesize information to answer complex questions. Each episode includes a short executive introduction, a tech talk exploring the topic in depth, and a visual recap with doodle summaries of the key ideas. Alongside the episodes, the GitHub repository provides cookbooks with sample code, summary of the episodes, and additinal learning resources, so developers can explore the concepts and apply them in their own projects. Explore the Repo All episodes and supporting materials live in the IQ Series repository: 👉 https://aka.ms/iq-series Inside the repository you’ll find: The Foundry IQ episode links Cookbooks for each episode Links to documentation and additional resources If you're building AI agents or exploring how AI systems can work with knowledge, the IQ Series is a great place to start. Watch the episodes and explore the cookbooks! We’re excited to see what you build and welcome your feedback & ideas as the series evolves.Building real-world AI automation with Foundry Local and the Microsoft Agent Framework
A hands-on guide to building real-world AI automation with Foundry Local, the Microsoft Agent Framework, and PyBullet. No cloud subscription, no API keys, no internet required. Why Developers Should Care About Offline AI Imagine telling a robot arm to "pick up the cube" and watching it execute the command in a physics simulator, all powered by a language model running on your laptop. No API calls leave your machine. No token costs accumulate. No internet connection is needed. That is what this project delivers, and every piece of it is open source and ready for you to fork, extend, and experiment with. Most AI demos today lean on cloud endpoints. That works for prototypes, but it introduces latency, ongoing costs, and data privacy concerns. For robotics and industrial automation, those trade-offs are unacceptable. You need inference that runs where the hardware is: on the factory floor, in the lab, or on your development machine. Foundry Local gives you an OpenAI-compatible endpoint running entirely on-device. Pair it with a multi-agent orchestration framework and a physics engine, and you have a complete pipeline that translates natural language into validated, safe robot actions. This post walks through how we built it, why the architecture works, and how you can start experimenting with your own offline AI simulators today. Architecture The system uses four specialised agents orchestrated by the Microsoft Agent Framework: Agent What It Does Speed PlannerAgent Sends user command to Foundry Local LLM → JSON action plan 4–45 s SafetyAgent Validates against workspace bounds + schema < 1 ms ExecutorAgent Dispatches actions to PyBullet (IK, gripper) < 2 s NarratorAgent Template summary (LLM opt-in via env var) < 1 ms User (text / voice) │ ▼ ┌──────────────┐ │ Orchestrator │ └──────┬───────┘ │ ┌────┴────┐ ▼ ▼ Planner Narrator │ ▼ Safety │ ▼ Executor │ ▼ PyBullet Setting Up Foundry Local from foundry_local import FoundryLocalManager import openai manager = FoundryLocalManager("qwen2.5-coder-0.5b") client = openai.OpenAI( base_url=manager.endpoint, api_key=manager.api_key, ) resp = client.chat.completions.create( model=manager.get_model_info("qwen2.5-coder-0.5b").id, messages=[{"role": "user", "content": "pick up the cube"}], max_tokens=128, stream=True, ) from foundry_local import FoundryLocalManager import openai manager = FoundryLocalManager("qwen2.5-coder-0.5b") client = openai.OpenAI( base_url=manager.endpoint, api_key=manager.api_key, ) resp = client.chat.completions.create( model=manager.get_model_info("qwen2.5-coder-0.5b").id, messages=[{"role": "user", "content": "pick up the cube"}], max_tokens=128, stream=True, ) The SDK auto-selects the best hardware backend (CUDA GPU → QNN NPU → CPU). No configuration needed. How the LLM Drives the Simulator Understanding the interaction between the language model and the physics simulator is central to the project. The two never communicate directly. Instead, a structured JSON contract forms the bridge between natural language and physical motion. From Words to JSON When a user says “pick up the cube”, the PlannerAgent sends the command to the Foundry Local LLM alongside a compact system prompt. The prompt lists every permitted tool and shows the expected JSON format. The LLM responds with a structured plan: { "type": "plan", "actions": [ {"tool": "describe_scene", "args": {}}, {"tool": "pick", "args": {"object": "cube_1"}} ] } The planner parses this response, validates it against the action schema, and retries once if the JSON is malformed. This constrained output format is what makes small models (0.5B parameters) viable: the response space is narrow enough that even a compact model can produce correct JSON reliably. From JSON to Motion Once the SafetyAgent approves the plan, the ExecutorAgent maps each action to concrete PyBullet calls: move_ee(target_xyz) : The target position in Cartesian coordinates is passed to PyBullet's inverse kinematics solver, which computes the seven joint angles needed to place the end-effector at that position. The robot then interpolates smoothly from its current joint state to the target, stepping the physics simulation at each increment. pick(object) : This triggers a multi-step grasp sequence. The controller looks up the object's position in the scene, moves the end-effector above the object, descends to grasp height, closes the gripper fingers with a configurable force, and lifts. At every step, PyBullet resolves contact forces and friction so that the object behaves realistically. place(target_xyz) : The reverse of a pick. The robot carries the grasped object to the target coordinates and opens the gripper, allowing the physics engine to drop the object naturally. describe_scene() : Rather than moving the robot, this action queries the simulation state and returns the position, orientation, and name of every object on the table, along with the current end-effector pose. The Abstraction Boundary The critical design choice is that the LLM knows nothing about joint angles, inverse kinematics, or physics. It operates purely at the level of high-level tool calls ( pick , move_ee ). The ActionExecutor translates those tool calls into the low-level API that PyBullet provides. This separation means the LLM prompt stays simple, the safety layer can validate plans without understanding kinematics, and the executor can be swapped out without retraining or re-prompting the model. Voice Input Pipeline Voice commands follow three stages: Browser capture: MediaRecorder captures audio, client-side resamples to 16 kHz mono WAV Server transcription: Foundry Local Whisper (ONNX, cached after first load) with automatic 30 s chunking Command execution: transcribed text goes through the same Planner → Safety → Executor pipeline The mic button (🎤) only appears when a Whisper model is cached or loaded. Whisper models are filtered out of the LLM dropdown. Web UI in Action Pick command Describe command Move command Reset command Performance: Model Choice Matters Model Params Inference Pipeline Total qwen2.5-coder-0.5b 0.5 B ~4 s ~5 s phi-4-mini 3.6 B ~35 s ~36 s qwen2.5-coder-7b 7 B ~45 s ~46 s For interactive robot control, qwen2.5-coder-0.5b is the clear winner: valid JSON for a 7-tool schema in under 5 seconds. The Simulator in Action Here is the Panda robot arm performing a pick-and-place sequence in PyBullet. Each frame is rendered by the simulator's built-in camera and streamed to the web UI in real time. Overview Reaching Above the cube Gripper detail Front interaction Side layout Get Running in Five Minutes You do not need a GPU, a cloud account, or any prior robotics experience. The entire stack runs on a standard development machine. # 1. Install Foundry Local winget install Microsoft.FoundryLocal # Windows brew install foundrylocal # macOS # 2. Download models (one-time, cached locally) foundry model run qwen2.5-coder-0.5b # Chat brain (~4 s inference) foundry model run whisper-base # Voice input (194 MB) # 3. Clone and set up the project git clone https://github.com/leestott/robot-simulator-foundrylocal cd robot-simulator-foundrylocal .\setup.ps1 # or ./setup.sh on macOS/Linux # 4. Launch the web UI python -m src.app --web --no-gui # → http://localhost:8080 Once the server starts, open your browser and try these commands in the chat box: "pick up the cube": the robot grasps the blue cube and lifts it "describe the scene": returns every object's name and position "move to 0.3 0.2 0.5": sends the end-effector to specific coordinates "reset": returns the arm to its neutral pose If you have a microphone connected, hold the mic button and speak your command instead of typing. Voice input uses a local Whisper model, so your audio never leaves the machine. Experiment and Build Your Own The project is deliberately simple so that you can modify it quickly. Here are some ideas to get started. Add a new robot action The robot currently understands seven tools. Adding an eighth takes four steps: Define the schema in TOOL_SCHEMAS ( src/brain/action_schema.py ). Write a _do_<tool> handler in src/executor/action_executor.py . Register it in ActionExecutor._dispatch . Add a test in tests/test_executor.py . For example, you could add a rotate_ee tool that spins the end-effector to a given roll/pitch/yaw without changing position. Add a new agent Every agent follows the same pattern: an async run(context) method that reads from and writes to a shared dictionary. Create a new file in src/agents/ , register it in orchestrator.py , and the pipeline will call it in sequence. Ideas for new agents: VisionAgent: analyse a camera frame to detect objects and update the scene state before planning. CostEstimatorAgent: predict how many simulation steps an action plan will take and warn the user if it is expensive. ExplanationAgent: generate a step-by-step natural language walkthrough of the plan before execution, allowing the user to approve or reject it. Swap the LLM python -m src.app --web --model phi-4-mini Or use the model dropdown in the web UI; no restart is needed. Try different models and compare accuracy against inference speed. Smaller models are faster but may produce malformed JSON more often. Larger models are more accurate but slower. The retry logic in the planner compensates for occasional failures, so even a small model works well in practice. Swap the simulator PyBullet is one option, but the architecture does not depend on it. You could replace the simulation layer with: MuJoCo: a high-fidelity physics engine popular in reinforcement learning research. Isaac Sim: NVIDIA's GPU-accelerated robotics simulator with photorealistic rendering. Gazebo: the standard ROS simulator, useful if you plan to move to real hardware through ROS 2. The only requirement is that your replacement implements the same interface as PandaRobot and GraspController . Build something completely different The pattern at the heart of this project (LLM produces structured JSON, safety layer validates, executor dispatches to a domain-specific engine) is not limited to robotics. You could apply the same architecture to: Home automation: "turn off the kitchen lights and set the thermostat to 19 degrees" translated into MQTT or Zigbee commands. Game AI: natural language control of characters in a game engine, with the safety agent preventing invalid moves. CAD automation: voice-driven 3D modelling where the LLM generates geometry commands for OpenSCAD or FreeCAD. Lab instrumentation: controlling scientific equipment (pumps, stages, spectrometers) via natural language, with the safety agent enforcing hardware limits. From Simulator to Real Robot One of the most common questions about projects like this is whether it could control a real robot. The answer is yes, and the architecture is designed to make that transition straightforward. What Stays the Same The entire upper half of the pipeline is hardware-agnostic: The LLM planner generates the same JSON action plans regardless of whether the target is simulated or physical. It has no knowledge of the underlying hardware. The safety agent validates workspace bounds and tool schemas. For a real robot, you would tighten the bounds to match the physical workspace and add checks for obstacle clearance using sensor data. The orchestrator coordinates agents in the same sequence. No changes are needed. The narrator reports what happened. It works with any result data the executor returns. What Changes The only component that must be replaced is the executor layer, specifically the PandaRobot class and the GraspController . In simulation, these call PyBullet's inverse kinematics solver and step the physics engine. On a real robot, they would instead call the hardware driver. For a Franka Emika Panda (the same robot modelled in the simulation), the replacement options include: libfranka: Franka's C++ real-time control library, which accepts joint position or torque commands at 1 kHz. ROS 2 with MoveIt: A robotics middleware stack that provides motion planning, collision avoidance, and hardware abstraction. The move_ee action would become a MoveIt goal, and the framework would handle trajectory planning and execution. Franka ROS 2 driver: Combines libfranka with ROS 2 for a drop-in replacement of the simulation controller. The ActionExecutor._dispatch method maps tool names to handler functions. Replacing _do_move_ee , _do_pick , and _do_place with calls to a real robot driver is the only code change required. Key Considerations for Real Hardware Safety: A simulated robot cannot cause physical harm; a real robot can. The safety agent would need to incorporate real-time collision checking against sensor data (point clouds from depth cameras, for example) rather than relying solely on static workspace bounds. Perception: In simulation, object positions are known exactly. On a real robot, you would need a perception system (cameras with object detection or fiducial markers) to locate objects before grasping. Calibration: The simulated robot's coordinate frame matches the URDF model perfectly. A real robot requires hand-eye calibration to align camera coordinates with the robot's base frame. Latency: Real actuators have physical response times. The executor would need to wait for motion completion signals from the hardware rather than stepping a simulation loop. Gripper feedback: In PyBullet, grasp success is determined by contact forces. A real gripper would provide force or torque feedback to confirm whether an object has been securely grasped. The Simulation as a Development Tool This is precisely why simulation-first development is valuable. You can iterate on the LLM prompts, agent logic, and command pipeline without risk to hardware. Once the pipeline reliably produces correct action plans in simulation, moving to a real robot is a matter of swapping the lowest layer of the stack. Key Takeaways for Developers On-device AI is production-ready. Foundry Local serves models through a standard OpenAI-compatible API. If your code already uses the OpenAI SDK, switching to local inference is a one-line change to base_url . Small models are surprisingly capable. A 0.5B parameter model produces valid JSON action plans in under 5 seconds. For constrained output schemas, you do not need a 70B model. Multi-agent pipelines are more reliable than monolithic prompts. Splitting planning, validation, execution, and narration across four agents makes each one simpler to test, debug, and replace. Simulation is the safest way to iterate. You can refine LLM prompts, agent logic, and tool schemas without risking real hardware. When the pipeline is reliable, swapping the executor for a real robot driver is the only change needed. The pattern generalises beyond robotics. Structured JSON output from an LLM, validated by a safety layer, dispatched to a domain-specific engine: that pattern works for home automation, game AI, CAD, lab equipment, and any other domain where you need safe, structured control. You can start building today. The entire project runs on a standard laptop with no GPU, no cloud account, and no API keys. Clone the repository, run the setup script, and you will have a working voice-controlled robot simulator in under five minutes. Ready to start building? Clone the repository, try the commands, and then start experimenting. Fork it, add your own agents, swap in a different simulator, or apply the pattern to an entirely different domain. The best way to learn how local AI can solve real-world problems is to build something yourself. Source code: github.com/leestott/robot-simulator-foundrylocal Built with Foundry Local, Microsoft Agent Framework, PyBullet, and FastAPI.Request for Best Practices on Using Microsoft Agent 365
Hello Community, I am seeking guidance on best practices for effectively using Microsoft Agent 365. Specifically, I am interested in recommendations related to governance, security and access control, agent monitoring, and integration with Microsoft 365 services. If you have practical experience or proven approaches in these areas, your insights would be greatly appreciated. Thank you, Mohammad Shohal Bhuiyan
