Uploaded October 2026 | Updated November 2026, 2 hours ago
Conoce los fundamentos de MCP, sus elementos primitivos y los componentes que conforman su arquitectura, para entender cómo este protocolo conecta aplicaciones de IA con herramientas y fuentes de datos externas.
🔗 Aprende más accediendo a los recursos:
https://aka.ms/MCPrepo
https://aka.ms/IntroMCP
https://aka.ms/MCPtools
https://aka.ms/MCPagents
📌 Este evento es parte de una serie, aprende más aquí: https://aka.ms/mcpafondo
0:05 - Introducción de la sesión y bienvenida del equipo de Microsoft Reactor.
0:53 - Presentación de Rodrigo Díaz Concha y agenda de la serie.
3:01 - ¿Qué es MCP? Origen, propósito y estandarización.
7:42 - Analogía de MCP: El conector USB.
8:46 - Arquitectura técnica: JSON RPC 2.0 y el papel de las herramientas, recursos y prompts.
16:26 - Ecosistema MCP: SDKs, clientes (hosts) y herramientas de desarrollo.
22:26 - Arquitectura detallada: Host, cliente, servidor y tipos de transporte (local vs. remoto).
28:16 - Capas del protocolo (datos y transporte).
30:17 - Concepto de Stateless (sin estado) y el método Server Discover.
36:39 - Demostración práctica con Fabio Robotics y el MCP Inspector.
44:48 - Evolución: Eliminación del handshake en versiones recientes.
50:11 - Primitivos de MCP: Tools, resources y prompts explicados a fondo.
54:17 - Proceso de elicitación (Multi-round Trip Requests).
57:48 - Capa de transporte: Cuándo usar Standard IO frente a HTTP.
#MicrosoftReactor #LearnConnectBuild #MCP #Agents
[eventID:27599]
Conoce los fundamentos de MCP, sus elementos primitivos y los componentes que conforman su arquitectura, para entender cómo este protocolo conecta aplicaciones de IA con herramientas y fuentes de datos externas.
🔗 Aprende más accediendo a los recursos:
https://aka.ms/MCPrepo
https://aka.ms/IntroMCP
https://aka.ms/MCPtools
https://aka.ms/MCPagents
📌 Este evento es parte de una serie, aprende más aquí: https://aka.ms/mcpafondo
0:05 - Introducción de la sesión y bienvenida del equipo de Microsoft Reactor.
0:53 - Presentación de Rodrigo Díaz Concha y agenda de la serie.
3:01 - ¿Qué es MCP? Origen, propósito y estandarización.
7:42 - Analogía de MCP: El conector USB.
8:46 - Arquitectura técnica: JSON RPC 2.0 y el papel de las herramientas, recursos y prompts.
16:26 - Ecosistema MCP: SDKs, clientes (hosts) y herramientas de desarrollo.
22:26 - Arquitectura detallada: Host, cliente, servidor y tipos de transporte (local vs. remoto).
28:16 - Capas del protocolo (datos y transporte).
30:17 - Concepto de Stateless (sin estado) y el método Server Discover.
36:39 - Demostración práctica con Fabio Robotics y el MCP Inspector.
44:48 - Evolución: Eliminación del handshake en versiones recientes.
50:11 - Primitivos de MCP: Tools, resources y prompts explicados a fondo.
54:17 - Proceso de elicitación (Multi-round Trip Requests).
57:48 - Capa de transporte: Cuándo usar Standard IO frente a HTTP.
#MicrosoftReactor #LearnConnectBuild #MCP #Agents
[eventID:27599]
![A IA vai acabar com o meu emprego? Vamos falar sobre isso
Não faltam grandes promessas e previsões assustadoras sobre IA.
Esta é uma conversa prática sobre o que preocupa profissionais de dados, o que realmente está mudando e como podemos nos preparar sem fingir que temos todas as respostas.
Para mais informações sobre o Data Days e tudo o que ele tem a oferecer, acesse https://aka.ms/DataDays
📌 Este evento faz parte de uma série. Saiba mais aqui: https://aka.ms/AIatWork/UnderstandIt/y
#MicrosoftReactor #LearnConnectBuild #Fabric #AI #DataDays
[eventID:27728] A IA vai acabar com o meu emprego? Vamos falar sobre isso](https://i.ytimg.com/vi/BGkLMA0qnMA/mqdefault.jpg)
![Quizás ya estés usando más IA de lo que crees
La IA ya está apareciendo en las herramientas que los profesionales de datos usan todos los días, a veces de formas que son fáciles de pasar por alto.
Veremos qué podrías tener ya disponible, dónde puede ayudarte la IA y dónde sigue siendo necesario aplicar tu propio criterio.
Aquí tienes los marcadores de capítulo para esta sesión:
0:00:00 - Introducción y bienvenida
0:01:27 - Información del evento y código de conducta
0:03:47 - Presentación de los ponentes: Gastón Cruz y Walter Calcaño
0:09:49 - Oportunidades de certificación y grupos de estudio
0:13:54 - Paneles de usuarios y comunidad
0:15:38 - Campeonato mundial de Dataviz
0:17:29 - ¿Qué es realmente la Inteligencia Artificial? Definición y contexto
0:19:57 - Integración de IA en el flujo de trabajo diario
0:22:18 - Pregunta interactiva: ¿Con qué frecuencia usas IA?
0:28:46 - ¿Es IA? Excel y el autocompletado
0:33:08 - Sugerencias de código en SQL y Python
0:38:46 - GitHub Copilot en la terminal
0:41:59 - CLI de Fabric y comandos en lenguaje natural
0:45:00 - Formato condicional: ¿Es IA o una regla?
0:49:17 - Gestión del correo y detección de spam
0:52:42 - Subtítulos y resúmenes de reuniones con IA
0:54:54 - Inventario de herramientas con IA integrada
0:59:42 - Consideraciones sobre licencias y configuración
1:00:56 - La importancia del criterio humano y la validación
1:03:36 - Reflexiones finales y conclusiones
[eventID:27750] Quizás ya estés usando más IA de lo que crees](https://i.ytimg.com/vi/BQyctblaAEo/mqdefault.jpg)
![AI Agents That Know Your Business (Option 2)
What if your AI agents actually understood your business?
Trusted data, governed semantics, and business context can turn generic AI into experiences grounded in the way your organization really works. The result: answers and insights that are more relevant, more useful, and ready to put to work.
📌 This event is part of a series. Learn more here:
https://aka.ms/DataDays/FabConRecap/y
https://aka.ms/DataDays/IntoCerts/y
https://aka.ms/AIatWork/UnderstandIt/y
https://aka.ms/AIatWork/BuildIt/y
https://aka.ms/AIatWork/ShowIt/y
Introduction and Housekeeping: (0:00 - 1:02)
Speaker Introductions: (1:12 - 3:43)
Certifications and Community Resources: (4:01 - 6:31)
Understanding Fabric IQ Framework: (6:36 - 12:00)
Demonstration: Microsoft Copilot and Fabric IQ: (13:57 - 17:02)
Customizing Copilot with Skills: (17:02 - 20:00)
Copilot and Work IQ Demonstration: (20:10 - 23:20)
Governance, Compliance, and Information Protection: (27:02 - 30:19)
FabCon and SQL Conf Announcements: (30:21 - 31:54)
Context Offering for AI (Templates and Topics): (31:54 - 38:15)
Sneak Peek Features (Pivot Tables and Auto Models): (38:21 - 42:30)
Specialist Data Agents: (42:40 - 47:50)
Microsoft Foundry and Observability: (47:50 - 51:30)
Feedback Monitoring and Future Features: (52:40 - 56:32)
OptiGuide and Optimization Models: (57:17 - 1:00:15)
Roadmap and Conclusion: (1:00:16 - 1:04:03)
[eventID:27704] AI Agents That Know Your Business (Option 2)](https://i.ytimg.com/vi/BY1JG8WojeI/mqdefault.jpg)
![What the Heck Is Fabric IQ?
ACFabric IQ sounds important, but what is it actually doing? We’ll break down how it uses business context to help AI understand your data, how Copilot fits in, and what grounded answers could look like in real work. Bring your questions.
For more information on Data Days and all it has to offer, visit https://aka.ms/DataDays
📌 This event is part of a series. Learn more here:
https://aka.ms/DataDays/FabConRecap/y
https://aka.ms/DataDays/IntoCerts/y
https://aka.ms/AIatWork/UnderstandIt/y
https://aka.ms/AIatWork/BuildIt/y
https://aka.ms/AIatWork/ShowIt/y
[eventID:27721] What the Heck Is Fabric IQ?](https://i.ytimg.com/vi/CAeZS8dKPeI/mqdefault.jpg)
![De MCP a agentes A2A en Microsoft Fabric: Qué vamos a construir
Veremos qué vamos a construir durante los 12 episodios: un sistema donde MCP permite conectar herramientas y datos, mientras que A2A permite que distintos agentes colaboren entre sí.
También definiremos el caso práctico, los componentes principales y el resultado final esperado.
🔗 Aprende más accediendo a los recursos:
https://aka.ms/FabricMCPservers
https://aka.ms/FabricCoreMCPServertools
https://aka.ms/FabricCoreMCPServer
https://aka.ms/SkillsforMSFTFabric
https://aka.ms/InstallSkillsforFabric
https://aka.ms/A2AandMCPComparison
https://aka.ms/GitHubSpecKit/y
https://aka.ms/Codexbestpractices
https://aka.ms/OpenAIAgentSkills
📌 Este evento es parte de una serie, aprende más aquí:
https://aka.ms/MCPaA2AFabric/y
#MicrosoftReactor #LearnConnectBuild #MicrosoftFabric #MCP #Agents #OpenAI #Codex #DeveloperTools
[eventID:27817] De MCP a agentes A2A en Microsoft Fabric: Qué vamos a construir](https://i.ytimg.com/vi/CB9SPXmxyto/mqdefault.jpg)
![Microsoft Fabric at Scale: Build, Deploy, and Govern (Option 2)
AI is changing what it means to build at scale. Microsoft Fabric brings development, deployment, security, and governance together so teams can move faster without losing control. See what a modern data foundation looks like when it’s built for today and ready for what AI makes possible next.
📌 This event is part of a series. Learn more here:
https://aka.ms/DataDays/FabConRecap/y
https://aka.ms/DataDays/IntoCerts/y
https://aka.ms/AIatWork/UnderstandIt/y
https://aka.ms/AIatWork/BuildIt/y
https://aka.ms/AIatWork/ShowIt/y
0:00 Introduction and Welcome
3:17 Series Overview: Fabric at Scale
5:40 The Role of AI in Scaling Governance and Security
12:20 Demo: Tenant Administration and Governance
15:26 Understanding the OneLake Catalog and Policies
17:09 Security: Information Protection and DLP
19:58 Capacity Administration: Challenges and New Features
23:21 Demo: Capacity Health and Monitor Hub
29:16 Data and AI Developer Observability
31:12 Demo: Monitoring Hub and Operations Agents
34:57 Automation and Developer Experience
38:58 Demo: Fabric Skills in GitHub Copilot and Fabric
44:45 Deployment Plans and CI/CD Enhancements
49:54 OneLake Catalog: Consumption and Integration
55:04 Demo: Business User Discovery and AI Grounding
59:07 Summary and Final Takeaways
1:00:09 Closing Remarks and Upcoming Sessions
[eventID:27690] Microsoft Fabric at Scale: Build, Deploy, and Govern (Option 2)](https://i.ytimg.com/vi/CcFeTz2Gwdg/mqdefault.jpg)

![AI Genius | Operate & Scale: Self-Healing ZeroOps and Enterprise-Wide Modernization
Building AI workflows is only the beginning.
In this session, youll see how organizations are leveraging Azure SRE Agent, Copilot Modernize, and operational intelligence tools to automate incident resolution, modernize legacy applications, and continuously improve engineering efficiency.
Learn how AI-powered operations are enabling teams to scale innovation while reducing operational overhead.
📌 This session is part of a series. Explore the full series here: https://aka.ms/AIGenius6/y
0:00 Introduction and Agenda
1:57 Modernization Strategy
4:08 Modernization Tooling Landscape
6:43 Demo 1: Azure Migrate and Assessment
10:55 Agentic App Modernization
15:31 Demo 2: Assessment to Azure
41:14 Security and Operations at Scale
45:01 Demo 3: Operate with SRE Agent
52:09 Conclusion and Q&A
[eventID:27641] AI Genius | Operate & Scale: Self-Healing ZeroOps and Enterprise-Wide Modernization](https://i.ytimg.com/vi/DRV6mSEwg_g/mqdefault.jpg)
![Stop Reporting the Plan. Start Planning in Fabric
Reporting tells you what already happened. Planning is about deciding what happens next.
We’ll work through a practical scenario that connects actuals, forecasts, decisions, and action inside Fabric.
For more information on Data Days and all it has to offer, visit https://aka.ms/DataDays
📌 This event is part of a series. Learn more here: https://aka.ms/AIatWork/BuildIt/y
#MicrosoftReactor #LearnConnectBuild #Fabric #DataDays
[eventID:27716] Stop Reporting the Plan. Start Planning in Fabric](https://i.ytimg.com/vi/EFyRiXC21-4/mqdefault.jpg)
![Lets Learn GitHub Copilot SDK (한국어)
GitHub Copilot SDK로 에이전트형 애플리케이션을 구축하는 방법을 초보도 쉽게 배울 수 있는 라이브스트림에 참여해 보세요! 직접 에이전트 루프를 구현할 필요가 없습니다.
모델 API를 직접 호출하는 것과 달리, SDK는 Copilot 에이전트에 프로그래밍 방식으로 접근하며, 여기에는 대화 관리, 계획, 도구 오케스트레이션, 스트리밍 이벤트 및 세션 상태를 포함합니다.
이번 세션에서는 클라이언트, 세션, 프롬프트, 에이전트 런타임을 살펴봅니다.
멀티 턴 대화를 생성하는 방법, 실시간 응답 스트리밍, 애플리케이션 펑션을 도구로 노출하는 방법, MCP 서버를 통한 외부 기능 연결, 그리고 훅과 퍼미션 핸들러를 통한 에이전트 동작 제어 방법을 배우게 됩니다.
또한 Copilot SDK 대신 인터랙티브 Copilot CLI를 언제 사용해야 하는지도 쉽게 이해할 수 있도록 도와드립니다. CLI는 터미널에서 개발 작업에 사용하고, Copilot의 에이전트 기능을 자신의 애플리케이션이나 서비스에 통합하려면 SDK를 사용합니다.
GitHub Copilot SDK를 써 본적이 없다구요? 괜찮습니다! 오셔서 느껴보세요!
00:00:00 GitHub Copilot SDK 소개
00:02:17 GitHub Copilot SDK 개요 및 아키텍처
00:04:51 프로그래밍 언어 지원 및 클라이언트 설정
00:06:42 배포 환경 및 사용 사례
00:14:25 실습 워크숍: 박물관 전시 애플리케이션 시작하기
00:27:51 스트리밍 응답 구현
00:36:08 시스템 메시지 및 에이전트 동작 구성
00:49:51 도구 추가 및 사실 조회 기능 구현
01:01:24 응답의 구조적 검증
01:15:06 연구를 위한 위키백과 통합
01:32:46 최종 HTML 박물관 보고서 구축
01:42:40 결론 및 워크숍 마무리
[eventID:27618] Lets Learn GitHub Copilot SDK (한국어)](https://i.ytimg.com/vi/EJ9AVKlPnbg/mqdefault.jpg)
![Build AI-powered soccer insights apps with AKS and ACA
Learn how to build and deploy AI-powered applications that analyze football match and player data using AKS and ACA.
Using Premier League-inspired scenarios such as identifying team play styles, analyzing counterattacks, or uncovering player performance patterns, well walk through a reference architecture for developing, deploying, and operating AI applications and agents on Azure.
Attendees will leave with practical guidance and ideas they can extend into their hackathon projects.
📌 This event is part of a series. Learn more here: https://aka.ms/PremierLeagueHack
0:00 Introduction and housekeeping
1:13 Premier League hackathon details and goals
2:56 Live demo of the football results dashboard
4:49 Exploring 150 years of international football data
8:19 Presentation agenda
9:17 Reference architecture overview (AKS and ACA)
11:29 Application data flow and ingestion process
12:33 Deterministic code vs. Microsoft Foundry logic
14:43 Security and Microsoft Entra ID implementation
18:01 Reviewing the Azure resource group and components
20:41 Data sources and handling in the repository
27:06 Challenges in data reconciliation and naming
31:13 AKS versus ACA infrastructure comparison
38:03 Scaling, revisions, and rolling updates
42:41 Building the app with GitHub Copilot
43:40 Reviewing the generation prompt structure
57:00 Final thoughts, hackathon resources, and Q&A
#MicrosoftReactor #LearnConnectBuild #PremierLeagueHackathon
[eventID:27536] Build AI-powered soccer insights apps with AKS and ACA](https://i.ytimg.com/vi/EQ187ohgCbo/mqdefault.jpg)