Essential Microsoft Resources for MVPs & the Tech Community from the AI Tour
Unlock the power of Microsoft AI with redeliverable technical presentations, hands-on workshops, and open-source curriculum from the Microsoft AI Tour! Whether you’re a Microsoft MVP, Developer, or IT Professional, these expertly crafted resources empower you to teach, train, and lead AI adoption in your community. Explore top breakout sessions covering GitHub Copilot, Azure AI, Generative AI, and security best practices—designed to simplify AI integration and accelerate digital transformation. Dive into interactive workshops that provide real-world applications of AI technologies. Take it a step further with Microsoft’s Open-Source AI Curriculum, offering beginner-friendly courses on AI, Machine Learning, Data Science, Cybersecurity, and GitHub Copilot—perfect for upskilling teams and fostering innovation. Don’t just learn—lead. Access these resources, host impactful training sessions, and drive AI adoption in your organization. Start sharing today! Explore now: Microsoft AI Tour Resources.
Getting Started with the AI Dev Gallery
March Update: The Gallery is now available on the Microsoft Store! The AI Dev Gallery is a new open-source project designed to inspire and support developers in integrating on-device AI functionality into their Windows apps. It offers an intuitive UX for exploring and testing interactive AI samples powered by local models. Key features include: Quickly explore and download models from well-known sources on GitHub and HuggingFace. Test different models with interactive samples over 25 different scenarios, including text, image, audio, and video use cases. See all relevant code and library references for every sample. Switch between models that run on CPU and GPU depending on your device capabilities. Quickly get started with your own projects by exporting any sample to a fresh Visual Studio project that references the same model cache, preventing duplicate downloads. Part of the motivation behind the Gallery was exposing developers to the host of benefits that come with on-device AI. Some of these benefits include improved data security and privacy, increased control and parameterization, and no dependence on an internet connection or third-party cloud provider. Requirements Device Requirements Minimum OS Version: Windows 10, version 1809 (10.0; Build 17763) Architecture: x64, ARM64 Memory: At least 16 GB is recommended Disk Space: At least 20GB free space is recommended GPU: 8GB of VRAM is recommended for running samples on the GPU Using the Gallery The AI Dev Gallery has can be navigated in two ways: The Samples View The Models View Navigating Samples In this view, samples are broken up into categories (Text, Code, Image, etc.) and then into more specific samples, like in the Translate Text pictured below: On clicking a sample, you will be prompted to choose a model to download if you haven’t run this sample before: Next to the model you can see the size of the model, whether it will run on CPU or GPU, and the associated license. Pick the model that makes the most sense for your machine. You can also download new models and change the model for a sample later from the sample view. Just click the model drop down at the top of the sample: The last thing you can do from the Sample pane is view the sample code and export the project to Visual Studio. Both buttons are found in the top right corner of the sample, and the code view will look like this: Navigating Models If you would rather navigate by models instead of samples, the Gallery also provides the model view: The model view contains a similar navigation menu on the right to navigate between models based on category. Clicking on a model will allow you to see a description of the model, the versions of it that are available to download, and the samples that use the model. Clicking on a sample will take back over to the samples view where you can see the model in action. Deleting and Managing Models If you need to clear up space or see download details for the models you are using, you can head over the Settings page to manage your downloads: From here, you can easily see every model you have downloaded and how much space on your drive they are taking up. You can clear your entire cache for a fresh start or delete individual models that you are no longer using. Any deleted model can be redownload through either the models or samples view. Next Steps for the Gallery The AI Dev Gallery is still a work in progress, and we plan on adding more samples, models, APIs, and features, and we are evaluating adding support for NPUs to take the experience even further If you have feedback, noticed a bug, or any ideas for features or samples, head over to the issue board and submit an issue. We also have a discussion board for any other topics relevant to the Gallery. The Gallery is an open-source project, and we would love contribution, feedback, and ideation! Happy modeling!Understanding Small Language Modes
Small Language Models (SLMs) bring AI from the cloud to your device. Unlike Large Language Models that require massive compute and energy, SLMs run locally, offering speed, privacy, and efficiency. They’re ideal for edge applications like mobile, robotics, and IoT.AI Toolkit for Visual Studio Code: October 2024 Update Highlights
The AI Toolkit’s October 2024 update revolutionizes Visual Studio Code with game-changing features for developers, researchers, and enthusiasts. Explore multi-model integration, including GitHub Models, ONNX, and Google Gemini, alongside custom model support. Dive into multi-modal capabilities for richer AI testing and seamless multi-platform compatibility across Windows, macOS, and Linux. Tailored for productivity, the enhanced Model Catalog simplifies choosing the best tools for your projects. Try it now and share feedback to shape the future of AI in VS Code!Getting Started - Generative AI with Phi-3-mini: A Guide to Inference and Deployment
Getting started with Microsoft Phi-3-mini - Inference Phi-3-mini models, Discover how Phi-3-mini, a new series of models from Microsoft, enables deployment of Large Language Models (LLMs) on edge devices and IoT devices. Learn how to use Semantic Kernel, Ollama/LlamaEdge, and ONNX Runtime to access and infer phi3-mini models, and explore the possibilities of generative AI in various application scenariosBuilding 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 standardsGitHub Copilot SDK and Hybrid AI in Practice: Automating README to PPT Transformation
Introduction In today's rapidly evolving AI landscape, developers often face a critical choice: should we use powerful cloud-based Large Language Models (LLMs) that require internet connectivity, or lightweight Small Language Models (SLMs) that run locally but have limited capabilities? The answer isn't either-or—it's hybrid models—combining the strengths of both to create AI solutions that are secure, efficient, and powerful. This article explores hybrid model architectures through the lens of GenGitHubRepoPPT, demonstrating how to elegantly combine Microsoft Foundry Local, GitHub Copilot SDK, and other technologies to automatically generate professional PowerPoint presentations from GitHub README files. 1. Hybrid Model Scenarios and Value 1.1 What Are Hybrid Models? Hybrid AI Models strategically combine locally-running Small Language Models (SLMs) with cloud-based Large Language Models (LLMs) within the same application, selecting the most appropriate model for each task based on its unique characteristics. Core Principles: Local Processing for Sensitive Data: Privacy-critical content analysis happens on-device Cloud for Value Creation: Complex reasoning and creative generation leverage cloud power Balancing Cost and Performance: High-frequency, simple tasks run locally to minimize API costs 1.2 Typical Hybrid Model Use Cases Use Case Local SLM Role Cloud LLM Role Value Proposition Intelligent Document Processing Text extraction, structural analysis Content refinement, format conversion Privacy protection + Professional output Code Development Assistant Syntax checking, code completion Complex refactoring, architecture advice Fast response + Deep insights Customer Service Systems Intent recognition, FAQ handling Complex issue resolution Reduced latency + Enhanced quality Content Creation Platforms Keyword extraction, outline generation Article writing, multilingual translation Cost control + Creative assurance 1.3 Why Choose Hybrid Models? Three Core Advantages: Privacy and Security Sensitive data never leaves local devices Compliant with GDPR, HIPAA, and other regulations Ideal for internal corporate documents and personal information Cost Optimization Reduces cloud API call frequency Local models have zero usage fees Predictable operational costs Performance and Reliability Local processing eliminates network latency Partial functionality in offline environments Cloud models ensure high-quality output 2. Core Technology Analysis 2.1 Large Language Models (LLMs): Cloud Intelligence Representatives What are LLMs? Large Language Models are deep learning-based natural language processing models, typically with billions to trillions of parameters. Through training on massive text datasets, they've acquired powerful language understanding and generation capabilities. Representative Models: Claude Sonnet 4.5: Anthropic's flagship model, excelling at long-context processing and complex reasoning GPT-5.2 Series: OpenAI's general-purpose language models Gemini: Google's multimodal large models LLM Advantages: ✅ Exceptional text generation quality ✅ Powerful contextual understanding ✅ Support for complex reasoning tasks ✅ Continuous model updates and optimization Typical Applications: Professional document writing (technical reports, business plans) Code generation and refactoring Multilingual translation Creative content creation 2.2 Small Language Models (SLMs) and Microsoft Foundry Local 2.2.1 SLM Characteristics Small Language Models typically have 1B-7B parameters, designed specifically for resource-constrained environments. Mainstream SLM Model Families: Microsoft Phi Family (Phi Family): Inference-optimized efficient models Alibaba Qwen Family (Qwen Family): Excellent Chinese language capabilities Mistral Series: Outstanding performance with small parameter counts SLM Advantages: ⚡ Low-latency response (millisecond-level) 💰 Zero API costs 🔒 Fully local, data stays on-device 📱 Suitable for edge device deployment 2.2.2 Microsoft Foundry Local: The Foundation of Local AI Foundry Local is Microsoft's local AI runtime tool, enabling developers to easily run SLMs on Windows or macOS devices. Core Features: OpenAI-Compatible API # Using Foundry Local is like using OpenAI API from openai import OpenAI from foundry_local import FoundryLocalManager manager = FoundryLocalManager("qwen2.5-7b-instruct") client = OpenAI( base_url=manager.endpoint, api_key=manager.api_key ) Hardware Acceleration Support CPU: General computing support GPU: NVIDIA, AMD, Intel graphics acceleration NPU: Qualcomm, Intel AI-specific chips Apple Silicon: Neural Engine optimization Based on ONNX Runtime Cross-platform compatibility Highly optimized inference performance Supports model quantization (INT4, INT8) Convenient Model Management # View available models foundry model list # Run a model foundry model run qwen2.5-7b-instruct-generic-cpu:4 # Check running status foundry service ps Foundry Local Application Value: 🎓 Educational Scenarios: Students can learn AI development without cloud subscriptions 🏢 Enterprise Environments: Process sensitive data while maintaining compliance 🧪 R&D Testing: Rapid prototyping without API cost concerns ✈️ Offline Environments: Works on planes, subways, and other no-network scenarios 2.3 GitHub Copilot SDK: The Express Lane from Agent to Business Value 2.3.1 What is GitHub Copilot SDK? GitHub Copilot SDK, released as a technical preview on January 22, 2026, is a game-changer for AI Agent development. Unlike other AI SDKs, Copilot SDK doesn't just provide API calling interfaces—it delivers a complete, production-grade Agent execution engine. Why is it revolutionary? Traditional AI application development requires you to build: ❌ Context management systems (multi-turn conversation state) ❌ Tool orchestration logic (deciding when to call which tool) ❌ Model routing mechanisms (switching between different LLMs) ❌ MCP server integration ❌ Permission and security boundaries ❌ Error handling and retry mechanisms Copilot SDK provides all of this out-of-the-box, letting you focus on business logic rather than underlying infrastructure. 2.3.2 Core Advantages: The Ultra-Short Path from Concept to Code Production-Grade Agent Engine: Battle-Tested Reliability Copilot SDK uses the same Agent core as GitHub Copilot CLI, which means: ✅ Validated in millions of real-world developer scenarios ✅ Capable of handling complex multi-step task orchestration ✅ Automatic task planning and execution ✅ Built-in error recovery mechanisms Real-World Example: In the GenGitHubRepoPPT project, we don't need to hand-write the "how to convert outline to PPT" logic—we simply tell Copilot SDK the goal, and it automatically: Analyzes outline structure Plans slide layouts Calls file creation tools Applies formatting logic Handles multilingual adaptation # Traditional approach: requires hundreds of lines of code for logic def create_ppt_traditional(outline): slides = parse_outline(outline) for slide in slides: layout = determine_layout(slide) content = format_content(slide) apply_styling(content, layout) # ... more manual logic return ppt_file # Copilot SDK approach: focus on business intent session = await client.create_session({ "model": "claude-sonnet-4.5", "streaming": True, "skill_directories": [skills_dir] }) session.send_and_wait({"prompt": prompt}, timeout=600) Custom Skills: Reusable Encapsulation of Business Knowledge This is one of Copilot SDK's most powerful features. In traditional AI development, you need to provide complete prompts and context with every call. Skills allow you to: Define once, reuse forever: # .copilot_skills/ppt/SKILL.md # PowerPoint Generation Expert Skill ## Expertise You are an expert in business presentation design, skilled at transforming technical content into easy-to-understand visual presentations. ## Workflow 1. **Structure Analysis** - Identify outline hierarchy (titles, subtitles, bullet points) - Determine topic and content density for each slide 2. **Layout Selection** - Title slide: Use large title + subtitle layout - Content slides: Choose single/dual column based on bullet count - Technical details: Use code block or table layouts 3. **Visual Optimization** - Apply professional color scheme (corporate blue + accent colors) - Ensure each slide has a visual focal point - Keep bullets to 5-7 items per page 4. **Multilingual Adaptation** - Choose appropriate fonts based on language (Chinese: Microsoft YaHei, English: Calibri) - Adapt text direction and layout conventions ## Output Requirements Generate .pptx files meeting these standards: - 16:9 widescreen ratio - Consistent visual style - Editable content (not images) - File size < 5MB Business Code Generation Capability This is the core value of this project. Unlike generic LLM APIs, Copilot SDK with Skills can generate truly executable business code. Comparison Example: Aspect Generic LLM API Copilot SDK + Skills Task Description Requires detailed prompt engineering Concise business intent suffices Output Quality May need multiple adjustments Professional-grade on first try Code Execution Usually example code Directly generates runnable programs Error Handling Manual implementation required Agent automatically handles and retries Multi-step Tasks Manual orchestration needed Automatic planning and execution Comparison of manual coding workload: Task Manual Coding Copilot SDK Processing logic code ~500 lines ~10 lines configuration Layout templates ~200 lines Declared in Skill Style definitions ~150 lines Declared in Skill Error handling ~100 lines Automatically handled Total ~950 lines ~10 lines + Skill file Tool Calling & MCP Integration: Connecting to the Real World Copilot SDK doesn't just generate code—it can directly execute operations: 🗃️ File System Operations: Create, read, modify files 🌐 Network Requests: Call external APIs 📊 Data Processing: Use pandas, numpy, and other libraries 🔧 Custom Tools: Integrate your business logic 3. GenGitHubRepoPPT Case Study 3.1 Project Overview GenGitHubRepoPPT is an innovative hybrid AI solution that combines local AI models with cloud-based AI agents to automatically generate professional PowerPoint presentations from GitHub repository README files in under 5 minutes. Technical Architecture: 3.2 Why Adopt a Hybrid Model? Stage 1: Local SLM Processes Sensitive Data Task: Analyze GitHub README, extract key information, generate structured outline Reasons for choosing Qwen-2.5-7B + Foundry Local: Privacy Protection README may contain internal project information Local processing ensures data doesn't leave the device Complies with data compliance requirements Cost Effectiveness Each analysis processes thousands of tokens Cloud API costs are significant in high-frequency scenarios Local models have zero additional fees Performance Qwen-2.5-7B excels at text analysis tasks Outstanding Chinese support Acceptable CPU inference latency (typically 2-3 seconds) Stage 2: Cloud LLM + Copilot SDK Creates Business Value Task: Create well-formatted PowerPoint files based on outline Reasons for choosing Claude Sonnet 4.5 + Copilot SDK: Automated Business Code Generation Traditional approach pain points: Need to hand-write 500+ lines of code for PPT layout logic Require deep knowledge of python-pptx library APIs Style and formatting code is error-prone Multilingual support requires additional conditional logic Copilot SDK solution: Declare business rules and best practices through Skills Agent automatically generates and executes required code Zero-code implementation of complex layout logic Development time reduced from 2-3 days to 2-3 hours Ultra-Short Path from Intent to Execution Comparison: Different ways to implement "Generate professional PPT" 3. Production-Grade Reliability and Quality Assurance Battle-tested Agent engine: Uses the same core as GitHub Copilot CLI Validated in millions of real-world scenarios Automatically handles edge cases and errors Consistent output quality: Professional standards ensured through Skills Automatic validation of generated files Built-in retry and error recovery mechanisms 4. Rapid Iteration and Optimization Capability Scenario: Client requests PPT style adjustment The GitHub Repo https://github.com/kinfey/GenGitHubRepoPPT 4. Summary 4.1 Core Value of Hybrid Models + Copilot SDK The GenGitHubRepoPPT project demonstrates how combining hybrid models with Copilot SDK creates a new paradigm for AI application development. Privacy and Cost Balance The hybrid approach allows sensitive README analysis to happen locally using Qwen-2.5-7B, ensuring data never leaves the device while incurring zero API costs. Meanwhile, the value-creating work—generating professional PowerPoint presentations—leverages Claude Sonnet 4.5 through Copilot SDK, delivering quality that justifies the per-use cost. From Code to Intent Traditional AI development required writing hundreds of lines of code to handle PPT generation logic, layout selection, style application, and error handling. With Copilot SDK and Skills, developers describe what they want in natural language, and the Agent automatically generates and executes the necessary code. What once took 3-5 days now takes 3-4 hours, with 95% less code to maintain. Automated Business Code Generation Copilot SDK doesn't just provide code examples—it generates complete, executable business logic. When you request a multilingual PPT, the Agent understands the requirement, selects appropriate fonts, generates the implementation code, executes it with error handling, validates the output, and returns a ready-to-use file. Developers focus on business intent rather than implementation details. 4.2 Technology Trends The Shift to Intent-Driven Development We're witnessing a fundamental change in how developers work. Rather than mastering every programming language detail and framework API, developers are increasingly defining what they want through declarative Skills. Copilot SDK represents this future: you describe capabilities in natural language, and AI Agents handle the code generation and execution automatically. Edge AI and Cloud AI Integration The evolution from pure cloud LLMs (powerful but privacy-concerning) to pure local SLMs (private but limited) has led to today's hybrid architectures. GenGitHubRepoPPT exemplifies this trend: local models handle data analysis and structuring, while cloud models tackle complex reasoning and professional output generation. This combination delivers fast, secure, and professional results. Democratization of Agent Development Copilot SDK dramatically lowers the barrier to building AI applications. Senior engineers see 10-20x productivity gains. Mid-level engineers can now build sophisticated agents that were previously beyond their reach. Even junior engineers and business experts can participate by writing Skills that capture domain knowledge without deep technical expertise. The future isn't about whether we can build AI applications—it's about how quickly we can turn ideas into reality. References Projects and Code GenGitHubRepoPPT GitHub Repository - Case study project Microsoft Foundry Local - Local AI runtime GitHub Copilot SDK - Agent development SDK Copilot SDK Getting Started Tutorial - Official quick start Deep Dive: Copilot SDK Build an Agent into Any App with GitHub Copilot SDK - Official announcement GitHub Copilot SDK Cookbook - Practical examples Copilot CLI Official Documentation - CLI tool documentation Learning Resources Edge AI for Beginners - Edge AI introductory course Azure AI Foundry Documentation - Azure AI documentation GitHub Copilot Extensions Guide - Extension development guideEngineering a Local-First Agentic Podcast Studio: A Deep Dive into Multi-Agent Orchestration
The transition from standalone Large Language Models (LLMs) to Agentic Orchestration marks the next frontier in AI development. We are moving away from simple "prompt-and-response" cycles toward a paradigm where specialized, autonomous units—AI Agents—collaborate to solve complex, multi-step problems. As a Technology Evangelist, my focus is on building these production-grade systems entirely on the edge, ensuring privacy, speed, and cost-efficiency. This technical guide explores the architecture and implementation of The AI Podcast Studio. This project demonstrates the seamless integration of the Microsoft Agent Framework, Local Small Language Models (SLMs), and VibeVoice to automate a complete tech podcast pipeline. I. The Strategic Intelligence Layer: Why Local-First? At the core of our studio is a Local-First philosophy. While cloud-based LLMs are powerful, they introduce friction in high-frequency, creative pipelines. By using Ollama as a model manager, we run SLMs like Qwen-3-8B directly on user hardware. 1. Architectural Comparison: Local vs. Cloud Choosing the deployment environment is a fundamental architectural decision. For an agentic podcasting workflow, the edge offers distinct advantages: Dimension Local Models (e.g., Qwen-3-8B) Cloud Models (e.g., GPT-5.2) Latency Zero/Ultra-low: Instant token generation without network "jitter". Variable: Dependent on network stability and API traffic. Privacy Total Sovereignty: Creative data and drafts never leave the local device. Shared Risk: Data is processed on third-party servers. Cost Zero API Fees: One-time hardware investment; free to run infinite tokens. Pay-as-you-go: Costs scale with token count and frequency of calls. Availability Offline: The studio remains functional without an internet connection. Online Only: Requires a stable, high-speed connection. 2. Reasoning and Tool-Calling on the Edge To move beyond simple chat, we implement Reasoning Mode, utilizing Chain-of-Thought (CoT) prompting. This allows our local agents to "think" through the podcast structure before writing. Furthermore, we grant them "superpowers" through Tool-Calling, allowing them to execute Python functions for real-time web searches to gather the latest news. II. The Orchestration Engine: Microsoft Agent Framework The true complexity of this project lies in Agent Orchestration—the coordination of specialized agents to work as a cohesive team. We distinguish between Agents, who act as "Jazz Musicians" making flexible decisions, and Workflows, which act as the "Orchestra" following a predefined score. 1. Advanced Orchestration Patterns Drawing from the WorkshopForAgentic architecture, the studio utilizes several sophisticated patterns: Sequential: A strict pipeline where the output of the Researcher flows into the Scriptwriter. Concurrent (Parallel): Multiple agents search different news sources simultaneously to speed up data gathering. Handoff: An agent dynamically "transfers" control to another specialist based on the context of the task. Magentic-One: A high-level "Manager" agent decides which specialist should handle the next task in real-time. III. Implementation: Code Analysis (Workshop Patterns) To maintain a production-grade codebase, we follow the modular structure found in the WorkshopForAgentic/code directory. This ensures that agents, clients, and workflows are decoupled and maintainable. 1. Configuration: Connecting to Local SLMs The first step is initializing the local model client using the framework's Ollama integration. # Based on WorkshopForAgentic/code/config.py from agent_framework.ollama import OllamaChatClient # Initialize the local client for Qwen-3-8B # Standard Ollama endpoint on localhost chat_client = OllamaChatClient( model_id="qwen3:8b", endpoint="http://localhost:11434" ) 2. Agent Definition: Specialized Roles Each agent is a ChatAgent instance defined by its persona and instructions. # Based on WorkshopForAgentic/code/agents.py from agent_framework import ChatAgent # The Researcher Agent: Responsible for web discovery researcher_agent = client.create_agent( name="SearchAgent", instructions="You are my assistant. Answer the questions based on the search engine.", tools=[web_search], ) # The Scriptwriter Agent: Responsible for conversational narrative generate_script_agent = client.create_agent( name="GenerateScriptAgent", instructions=""" You are my podcast script generation assistant. Please generate a 10-minute Chinese podcast script based on the provided content. The podcast script should be co-hosted by Lucy (the host) and Ken (the expert). The script content should be generated based on the input, and the final output format should be as follows: Speaker 1: …… Speaker 2: …… Speaker 1: …… Speaker 2: …… Speaker 1: …… Speaker 2: …… """ ) 3. Workflow Setup: The Sequential Pipeline For a deterministic production line, we use the WorkflowBuilder to connect our agents. # Based on WorkshopForAgentic/code/workflow_setup.py from agent_framework import WorkflowBuilder # Building the podcast pipeline search_executor = AgentExecutor(agent=search_agent, id="search_executor") gen_script_executor = AgentExecutor(agent=gen_script_agent, id="gen_script_executor") review_executor = ReviewExecutor(id="review_executor", genscript_agent_id="gen_script_executor") # Build workflow with approval loop # search_executor -> gen_script_executor -> review_executor # If not approved, review_executor -> gen_script_executor (loop back) workflow = ( WorkflowBuilder() .set_start_executor(search_executor) .add_edge(search_executor, gen_script_executor) .add_edge(gen_script_executor, review_executor) .add_edge(review_executor, gen_script_executor) # Loop back for regeneration .build() ) IV. Multimodal Synthesis: VibeVoice Technology The "Future Bytes" podcast is brought to life using VibeVoice, a specialized technology from Microsoft Research designed for natural conversational synthesis. Conversational Rhythm: It automatically handles natural turn-taking and speech cadences. High Efficiency: By operating at an ultra-low 7.5 Hz frame rate, it significantly reduces the compute power required for high-fidelity audio. Scalability: The system supports up to 4 distinct voices and can generate up to 90 minutes of continuous audio. V. Observability and Debugging: DevUI Building multi-agent systems requires deep visibility into the agentic "thinking" process. We leverage DevUI, a specialized web interface for testing and tracing: Interactive Tracing: Developers can watch the message flow and tool-calling in real-time. Automatic Discovery: DevUI auto-discovers agents defined within the project structure. Input Auto-Generation: The UI generates input fields based on workflow requirements, allowing for rapid iteration. VI. Technical Requirements for Edge Deployment Deploying this studio locally requires specific hardware and software configurations to handle simultaneous LLM and TTS inference: Software: Python 3.10+, Ollama, and the Microsoft Agent Framework. Hardware: 16GB+ RAM is the minimum requirement; 32GB is recommended for running multiple agents and VibeVoice concurrently. Compute: A modern GPU/NPU (e.g., NVIDIA RTX or Snapdragon X Elite) is essential for smooth inference. Final Perspective: From Coding to Directing The AI Podcast Studio represents a significant shift toward Agentic Content Creation. By mastering these orchestration patterns and leveraging local EdgeAI, developers move from simply writing code to directing entire ecosystems of intelligent agents. This "local-first" model ensures that the future of creativity is private, efficient, and infinitely scalable. Download sample Here Resource EdgeAI for Beginners - https://github.com/microsoft/edgeai-for-beginners Microsoft Agent Framework - https://github.com/microsoft/agent-framework Microsoft Agent Framework Samples - https://github.com/microsoft/agent-framework-samplesIf You're Building AI on Azure, ECS 2026 is Where You Need to Be
Let me be direct: there's a lot of noise in the conference calendar. Generic cloud events. Vendor showcases dressed up as technical content. Sessions that look great on paper but leave you with nothing you can actually ship on Monday. ECS 2026 isn't that. As someone who will be on stage at Cologne this May, I can tell you the European Collaboration Summit combined with the European AI & Cloud Summit and European Biz Apps Summit is one of the few events I've seen where engineers leave with real, production-applicable knowledge. Three days. Three summits. 3,000+ attendees. One of the largest Microsoft-focused events in Europe, and it keeps getting better. If you're building AI systems on Azure, designing cloud-native architectures, or trying to figure out how to take your AI experiments to production — this is where the conversation is happening. What ECS 2026 Actually Is ECS 2026 runs May 5–7 at Confex in Cologne, Germany. It brings together three co-located summits under one roof: European Collaboration Summit — Microsoft 365, Teams, Copilot, and governance European AI & Cloud Summit — Azure architecture, AI agents, cloud security, responsible AI European BizApps Summit — Power Platform, Microsoft Fabric, Dynamics For Azure engineers and AI developers, the European AI & Cloud Summit is your primary destination. But don't ignore the overlap, some of the most interesting AI conversations happen at the intersection of collaboration tooling and cloud infrastructure. The scale matters here: 3,000+ attendees, 100+ sessions, multiple deep-dive tracks, and a speaker lineup that includes Microsoft executives, Regional Directors, and MVPs who have built, broken, and rebuilt production systems. The Azure + AI Track - What's Actually On the Agenda The AI & Cloud Summit agenda is built around real technical depth. Not "intro to AI" content, actual architecture decisions, patterns that work, and lessons from things that didn't. Here's what you can expect: AI Agents and Agentic Systems This is where the energy is right now, and ECS is leaning in. Expect sessions covering how to design agent workflows, chain reasoning steps, handle memory and state, and integrate with Azure AI services. Marco Casalaina, VP of Products for Azure AI at Microsoft, is speaking if you want to understand the direction of the Azure AI platform from the people building it, this is a direct line. Azure Architecture at Scale Cloud-native patterns, microservices, containers, and the architectural decisions that determine whether your system holds up under real load. These sessions go beyond theory you'll hear from engineers who've shipped these designs at enterprise scale. Observability, DevOps, and Production AI Getting AI to production is harder than the demos suggest. Sessions here cover monitoring AI systems, integrating LLMs into CI/CD pipelines, and building the operational practices that keep AI in production reliable and governable. Cloud Security and Compliance Security isn't optional when you're putting AI in front of users or connecting it to enterprise data. Tracks cover identity, access patterns, responsible AI governance, and how to design systems that satisfy compliance requirements without becoming unmaintainable. Pre-Conference Deep Dives One underrated part of ECS: the pre-conference workshops. These are extended, hands-on sessions typically 3–6 hours that let you go deep on a single topic with an expert. Think of them as intensive short courses where you can actually work through the material, not just watch slides. If you're newer to a particular area of Azure AI, or you want to build fluency in a specific pattern before the main conference sessions, these are worth the early travel. The Speaker Quality Is Different Here The ECS speaker roster includes Microsoft executives, Microsoft MVPs, and Regional Directors, people who have real accountability for the products and patterns they're presenting. You'll hear from over 20 Microsoft speakers: Marco Casalaina — VP of Products, Azure AI at Microsoft Adam Harmetz — VP of Product at Microsoft, Enterprise Agent And dozens of MVPs and Regional Directors who are in the field every day, solving the same problems you are. These aren't keynote-only speakers — they're in the session rooms, at the hallway track, available for real conversations. The Hallway Track Is Not a Cliché I know "networking" sounds like a corporate afterthought. At ECS it genuinely isn't. When you put 3,000 practitioners, engineers, architects, DevOps leads, security specialists in one venue for three days, the conversations between sessions are often more valuable than the sessions themselves. You get candid answers to "how are you actually handling X in production?" that you won't find in documentation. The European Microsoft community is tight-knit and collaborative. ECS is where that community concentrates. Why This Matters Right Now We're in a period where AI development is moving fast but the engineering discipline around it is still maturing. Most teams are figuring out: How to move from AI prototype to production system How to instrument and observe AI behaviour reliably How to design agent systems that don't become unmaintainable How to satisfy security and compliance requirements in AI-integrated architectures ECS 2026 is one of the few places where you can get direct answers to these questions from people who've solved them — not theoretically, but in production, on Azure, in the last 12 months. If you go, you'll come back with practical patterns you can apply immediately. That's the bar I hold events to. ECS consistently clears it. Register and Explore the Agenda Register for ECS 2026: ecs.events Explore the AI & Cloud Summit agenda: cloudsummit.eu/en/agenda Dates: May 5–7, 2026 | Location: Confex, Cologne, Germany Early registration is worth it the pre-conference workshops fill up. And if you're coming, find me, I'll be the one talking too much about AI agents and Azure deployments. See you in Cologne.Build 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 Local
