Uploaded July 2026 | Updated September 2026, 2 weeks ago
Join our product experts for an interactive Q&A session on new billing capabilities in Microsoft Fabric.
With this new functionality, you can pay only for the compute you use across OneLake compute, Data Warehouse, and Spark, while automatically scaling resources up and down based on demand.
We'll cover how these new capabilities work with your existing provisioned capacity, how to optimize costs for dynamic and bursty workloads, and the governance controls available to help you stay in control of usage and spend.
Bring your questions and get practical guidance on implementing them in your organization.
📌 This session is a part of a series! Learn more here: https://aka.ms/ATE/FabricEdition
[eventID:27488]
Join our product experts for an interactive Q&A session on new billing capabilities in Microsoft Fabric.
With this new functionality, you can pay only for the compute you use across OneLake compute, Data Warehouse, and Spark, while automatically scaling resources up and down based on demand.
We'll cover how these new capabilities work with your existing provisioned capacity, how to optimize costs for dynamic and bursty workloads, and the governance controls available to help you stay in control of usage and spend.
Bring your questions and get practical guidance on implementing them in your organization.
📌 This session is a part of a series! Learn more here: https://aka.ms/ATE/FabricEdition
[eventID:27488]
![Build a Multi-Agent Career Copilot: Resume-to-Job Fit Analysis
Take the next step from a single agent to an orchestrated multi-agent workflow. Build a Resume-to-Job Fit Evaluator that processes a resume and job description, extracts requirements, scores alignment, identifies gaps, and creates a personalized learning roadmap with Microsoft Learn resources. Learnings: When a multi-agent workflow is more effective than a single agent How to split a larger task into specialized agents and reliable handoffs How to use MCP-enabled tools to enrich responses with Microsoft Learn content.
📌 This event is part of a series. Learn more here: https://aka.ms/FoundryToolkitVSCode/series
đź”— Learn more by exploring the resources:
https://aka.ms/FoundryToolkit/VSCode
https://aka.ms/FoundryToolkit/VSCode/Overview
[eventID:27524] Build a Multi-Agent Career Copilot: Resume-to-Job Fit Analysis](https://i.ytimg.com/vi/pEjeiIxr4fs/mqdefault.jpg)
![Build with AI: GitHub Copilot SDK for Building Agentic Workflows
AI can do more than assist with coding. It can help automate complex tasks and orchestrate intelligent workflows.
In this session, youll learn how to build real agent-driven workflows using GitHub Copilot SDK. Through a hands-on demonstration, youll see how AI can automate everyday development tasks, from issue management to code iteration, while coordinating tools, context, and multi-step execution. Discover how to move beyond writing code and start designing intelligent, task-driven workflows.
You Will Learn
• How to build agentic workflows using GitHub Copilot SDK
• How agents plan, reason, and execute multi-step tasks
• How to connect agents with tools, services, and external systems
• How to design intelligent workflows that automate everyday development processes
Technologies Used
• GitHub Copilot SDK
• Agent runtime (planning and multi-step execution)
• Model Context Protocol (MCP)
• Tool calling and integration
• Workflow orchestration
Who Should Attend
• Developers interested in building agent-driven solutions
• Engineers exploring GitHub Copilot SDK capabilities
• Platform and tooling builders creating intelligent workflows
• Anyone looking to move from AI-assisted coding to workflow automation
[eventID:27464] Build with AI: GitHub Copilot SDK for Building Agentic Workflows](https://i.ytimg.com/vi/pWZZrB-kaFU/mqdefault.jpg)
![¿Qué es MCP y por qué cambia todo en Microsoft Fabric?
La IA ya no solo responde preguntas: ahora ejecuta acciones sobre tus datos.
En esta sesión introductoria entenderás qué es el Model Context Protocol (MCP), por qué se ha convertido en el estándar de la industria y cómo Microsoft lo está integrando en Fabric como base de su plataforma agéntica.
Veremos la arquitectura cliente-servidor de MCP, quĂ© son los servidores Local y Remote de Fabric, y cĂłmo un agente de IA puede descubrir y operar workspaces, lakehouses y pipelines usando lenguaje natural. Sin cĂłdigo todavĂa — el objetivo es que salgas con el mapa mental completo del ecosistema.
¿Qué son los servidores MCP de Fabric?
https://learn.microsoft.com/rest/api/fabric/articles/mcp-servers/what-is-fabric-mcp-server/?wt.mc_id=youtube_27348_organicsocial_reactor
📌 Este evento es parte de una serie, aprende más aquĂ: https://aka.ms/AgentesFabric
0:00:03 - IntroducciĂłn y bienvenida
0:03:47 - ÂżQuĂ© es MCP? (TeorĂa fundamental)
0:07:26 - Diferencias entre MCP Local y Remoto
0:12:44 - Mecanismos de transporte: Stdio vs. Streameable
0:18:23 - Primitivas del MCP: Tools, Resources y Prompts
0:26:09 - Mapa de servidores MCP en Microsoft Fabric
0:33:35 - ¿Qué instalar vs. qué conectar?
0:36:00 - Consumo de recursos, CU y tokens
0:41:05 - Microsoft Data Factory MCP
0:43:07 - RTI (Real Time Intelligence) MCP
0:45:36 - Data Activator MCP
0:47:17 - Operation Agent MCP
0:57:24 - OntologĂa y su rol en la IA
1:00:11 - Cierre y prĂłximos pasos de la saga
[eventID:27348] ¿Qué es MCP y por qué cambia todo en Microsoft Fabric?](https://i.ytimg.com/vi/pjKnz7cgI5g/mqdefault.jpg)
![Building AI Agents with Microsoft Foundry and MCP Using Azure Logic Apps
Learn how to build AI agents with Microsoft Foundry and connect them to real-world business systems using the Model Context Protocol (MCP) and Azure Logic Apps.
In this session, well explore how MCP enables agents to discover and use tools, while Azure Logic Apps provides a secure, low-code way to integrate with enterprise applications and APIs. Through a live demo, youll see how to extend an AI agent beyond chat to retrieve data, automate workflows, and take action across your organization.
00:00 Welcome & Housekeeping
03:13 Session Overview: AI Agents with Microsoft Foundry, MCP & Azure Logic Apps
04:04 Speaker Introduction: Ziggy Zoleta
05:05 What Youll Build Today
05:50 What is Microsoft Foundry?
07:09 What is an AI Agent?
08:37 Understanding Model Context Protocol (MCP)
10:53 Why MCP + Azure Logic Apps Matters
12:18 Demo Architecture Overview
13:51 Creating Azure Resources & Storage
16:04 Creating a Microsoft Foundry Project
17:51 Deploying a GPT Model
19:34 Testing the Model in the Playground
20:30 Creating an Agent in Microsoft Foundry
22:16 Adding the Code Interpreter Tool
23:25 Connecting a Stock Market API
25:25 Testing Stock Price Retrieval
26:24 Creating Charts with Agent Tools
27:27 Building an Azure Logic App
30:20 Creating the Stock Storage Workflow
34:53 Testing the Logic App
36:51 Exposing the Workflow as an MCP Server
38:50 Connecting MCP to the Agent
41:04 Saving Stock Data with MCP
42:28 Multi-Stock MCP Demo
43:32 Combining API, MCP & Code
[eventID:27458] Building AI Agents with Microsoft Foundry and MCP Using Azure Logic Apps](https://i.ytimg.com/vi/q4MGGp9femg/mqdefault.jpg)
![Orchestrating Fabric Spark and Best Practices for Production-Ready Workload
Ready to take your Fabric Spark workloads from idea to production?
Join two members of the Microsoft product team as they walk through how to orchestrate Spark in Microsoft Fabric using proven, real-world best practices. This is your chance to learn directly from the people who build the product and see how these capabilities are designed to scale.
You’ll explore how to scale efficiently, improve price performance with native execution, and secure workloads with enterprise-grade features.
Walk away with a production-ready playbook, actionable steps, and AI-powered tools to confidently orchestrate Spark in Microsoft Fabric.
đź”— Register for Data Days: https://aka.ms/datadays
📍 This session is a part of a series, learn more here: https://aka.ms/DataDayslive/spark-y
Chapters:
0:00 Introduction
1:43 Agenda and Learning Pillars
3:50 Common Customer Challenges
5:01 Production Readiness & Compute Sizing
8:06 Billing Models: Fixed vs. Autoscale
15:40 Monitoring Workspace Usage
17:20 Compute Governance & Starter Pools
18:18 Security: Network, Encryption & Private Links
24:50 Performance Updates: Liquid Clustering & Native Execution
29:50 Pre-warm Clusters and Light Pools
30:51 Performance Tuning & Medallion Architecture
34:35 Adaptive Target File Sizes
37:44 Parallel Snapshot Loading & Connectivity Improvements
41:58 Identifying and Solving Data Skew
43:30 Memory Management & Avoiding Data Spills
44:40 Resource Profiles: Static vs. Auto-update
50:45 High Concurrency Mode and Orchestration
54:28 Importance of Testing & CI/CD
56:45 Early Release Channel
58:12 Library Management
59:25 JDBC/ODBC Connectivity & Livy API
1:01:28 Q&A Session
#MSFTReactor #learnconnectbuild
[eventID:27278] Orchestrating Fabric Spark and Best Practices for Production-Ready Workload](https://i.ytimg.com/vi/qNv7rSEVenY/mqdefault.jpg)
![Implementando seguridad y moderaciĂłn de contenido
Conoce las mejores prácticas para asegurar aplicaciones de IA, incluyendo filtros, moderación de contenido y estrategias para mitigar riesgos y garantizar un uso responsable.
📍https://aka.ms/Microsoft.Extensions.AI
📌 Este evento es parte de una serie, aprende más aquĂ: https://aka.ms/MEAIseries
0:07 - IntroducciĂłn y bienvenida
1:03 - Importancia de la seguridad en modelos de IA
2:12 - Conceptos teĂłricos: autenticaciĂłn, moderaciĂłn y monitoreo
3:21 - Controles y guardias de seguridad (Guardrails) en Azure AI Foundry
11:06 - Demostración: Configuración de filtros de contenido en el portal clásico
19:35 - DemostraciĂłn: ConfiguraciĂłn de controles en el nuevo portal de Foundry
31:11 - DemostraciĂłn: Uso de listas de bloqueo personalizadas (Blocklists)
38:50 - DemostraciĂłn: Manejo de excepciones en cĂłdigo
41:46 - Integraciones con proveedores de seguridad externos
45:47 - DemostraciĂłn: Evaluaciones unitarias con Microsoft.Extensions.AI
56:17 - Cierre de la sesiĂłn
#microsoftreactor #learnconnectbuild
[EventID:27064] Implementando seguridad y moderaciĂłn de contenido](https://i.ytimg.com/vi/qeHc9pRV5lw/mqdefault.jpg)

![DevOps Foundations for the AI Agentic Era
In this session, we’ll break down why solid DevOps fundamentals and tooling matter even more as AI-powered coding and operations agents become part of everyday workflows. You’ll see how modern AI dev agents—like GitHub Copilot generating code and tests—and AI ops agents—such as Azure’s SRE reliability agent—can dramatically speed up delivery when your pipelines, testing, and environments are built to support them. We’ll focus on what developers need to have in place to safely and effectively integrate these agents into real-world CI/CD workflows, without sacrificing quality, reliability, or control.
đź”— DevOps Engineer Spotlight Collection: https://www.microsoft.com/en-us/thesource-developer/Category/Group/86/devops-engineer-spotlight-collection/?wt.mc_id=youtube_27135_organicsocial_reactor
🔗 TheSource Developer Ehub: https://www.microsoft.com/en-us/thesource-developer/?wt.mc_id=youtube_27135_organicsocial_reactor
Chapter markers:
0:00 Introduction to the Agentic DevOps Era
0:34 Evolution of AI in Development
2:14 DevOps Foundations in the AI Era
3:34 Infusing AI Across the SDLC
6:11 Demo: Agentic DevOps in Practice
7:27 Project Structure & Tech Stack Overview
10:16 App Demonstration (Gift Exchange Features)
14:14 Using Agents for New Feature Development
15:34 CI/CD Workflow & Automated Testing
17:17 Platform Engineering: Environments per PR
19:00 Load Testing & Production Infrastructure
23:02 Human-in-the-loop Validation
24:02 Reviewing AI-Generated Pull Requests
27:45 Custom Agent Definitions
28:49 Integrating Accessibility Validation
30:33 Security & Quality (CodeQL & Dependabot)
33:04 Secret Scanning & Security Configuration
36:33 Environment Rules & Branch Protection
38:20 Summary & Next Steps
[eventID:27135] DevOps Foundations for the AI Agentic Era](https://i.ytimg.com/vi/rgO_-cZdVIY/mqdefault.jpg)
![Governance at Scale: Enforcing Network Security Baselines with Azure Policy & Landing Zones
This session makes the case for guardrails, not gates: governance thats built into the platform itself rather than bolted on afterward.
Well start with Azure Policy fundamentals, including policy definitions, initiatives, and effects (Deny, Audit, DeployIfNotExists, Modify), and explore how each effect type is appropriate for different governance scenarios.
From there, we move into practical network security baselines, covering policies that:
- Deny public IP creation on VMs
- Enforce mandatory NSG association on subnets
- Require specific Azure Firewall routing
- Mandate encryption in transit
The session then zooms out to the Cloud Adoption Framework Landing Zone model, showing how these individual policies are assembled into a coherent governance architecture and applied automatically at subscription vending time. This ensures every new subscription inherits the right guardrails from day one, rather than having security retrofitted later.
Well also cover:
- Management group hierarchy design
- Policy assignment scope
- Handling policy exemptions for legitimate edge cases without undermining the overall baseline
[eventID:27526] Governance at Scale: Enforcing Network Security Baselines with Azure Policy & Landing Zones](https://i.ytimg.com/vi/rpK3ryHcT5I/mqdefault.jpg)
![Let the Agent Write It—But Can It Scale?
Part of the Modern AI Apps with Azure Cosmos DB Series.
AI coding agents can generate working code quickly, but working code isnt always production-ready code. This session focuses on reviewing agent-generated Azure Cosmos DB code for scalability, RU efficiency, indexing strategy, and long-term maintainability.
Presenters:
Sajeetharan Sinnathurai - Azure Cosmos DB Principal Program Manager - https://www.linkedin.com/in/sajeetharan/
Jay Gordon - Azure Cosmos DB Senior Program Manager https://www.linkedin.com/in/jaygordon0042/
• Start with the Agent Kit — Give your coding agent the context it needs to build Cosmos DB apps the right way - https://aka.ms/CosmosDB-agentkit
• Subscribe to Azure Cosmos DB on YouTube - https://youtube.com/AzureCosmosDB
• Follow Azure Cosmos DB on X - https://twitter.com/AzureCosmosDB
• Follow Azure Cosmos DB on LinkedIn - https://www.linkedin.com/company/azure-cosmos-db/
02:52 Welcome & Session Introduction
03:17 Modern AI Apps with Azure Cosmos DB Series Overview
04:10 Repo Walkthrough & Demo Setup
05:30 Why Scaling Decisions Matter Early
06:10 Cosmos DB Scaling Fundamentals: Data Modeling, Partition Keys, RU Efficiency & Indexing
08:24 Creating Cosmos DB with AI Prompts and Entra Authentication
09:32 Seeding the Database with Sample Data
10:00 Building the Ticketing API with GitHub Copilot Agent
10:52 Choosing the Right AI Model and Understanding Costs
12:35 Understanding Application Queries and Access Patterns
15:44 Using OpenAPI for Load Testing Discovery
16:18 Examining Query Patterns and Identifying Performance Issues
17:25 Introducing Azure Cosmos DB Shell
19:47 Exploring Data with the VS Code Cosmos DB Extension
24:26 Generating Natural Language Queries Against Cosmos DB
26:00 Launching the Application and Generating Load
27:27 Using LoadGen to Stress Test the API
30:29 Measuring RU Consumption and Performance
32:09 The Four-Lens Performance Analysis Framework
35:19 Introducing Azure Cosmos DB Agent Kit
36:10 Installing Agent Kit in VS Code
37:59 Lens #1: Evaluating Data Modeling and Partition Key Design
40:14 Lens #2: Why Are These Queries So Expensive?
42:07 Lens #3: Indexing Policy Optimization
45:26 Lens #4: SDK Best Practices and Production Readiness
47:02 Letting Agent Kit Fix the Application
48:43 Baseline Performance Test (Before Optimization)
50:43 Running the Optimized Application (After Agent Kit)
53:13 RU Savings and Performance Improvements
54:03 Key Takeaways: Partition Keys, RU Costs, Indexing & SDK Design
54:42 Azure Cosmos DB Agent Kit Resources
55:25 Final Thoughts on Cosmos DB Shell and Developer Tools
56:20 Next Episode Preview: Building APIs Faster with Agentic Development
57:36 Agent Kit Roadmap, Open Source Contributions & Multi-Agent Support
58:19 Closing Remarks
#azurecosmosdb #aicoding
[eventID:27409] Let the Agent Write It—But Can It Scale?](https://i.ytimg.com/vi/rtbuubPm6r0/mqdefault.jpg)
![Composing Knowledge Bases That Reason Over Work, Business, and the Web
Learn how to design knowledge bases that span multiple domains. This session focuses on retrieval strategies that bring together work data, structured business context, and real-time web signals.
We’ll explore how to orchestrate these sources so agents can reason across them effectively, rather than treating each in isolation.
đź”— Resources: https://aka.ms/iq-series
📌 This event is a part of a series, learn more here: https://aka.ms/microsoftiqlive
#MSFTReactor #learnconnectbuild #foundryiq #serverless #knowledgebases #agentdevelopment #retrieval #datagrounding #azureaifoundry #enterpriseknowledge
[eventID:27452] Composing Knowledge Bases That Reason Over Work, Business, and the Web](https://i.ytimg.com/vi/rvDTN3GGnm8/mqdefault.jpg)