Uploaded October 2026 | Updated November 2026, 2 hours ago
En esta sesión configuraremos un proyecto y un repositorio en Azure DevOps, instalaremos Microsoft Power Platform Build Tools y crearemos una conexión de servicio segura con los entornos de Power Platform.
🔗 Aprende más accediendo a los recursos: https://aka.ms/PowerPlatformParaAzureDevOps
📌 Este evento es parte de una serie, aprende más aquí: https://aka.ms/PowerPlatformALM/y
Codigo:
trigger: none
pool:
vmImage: 'windows-latest'
jobs:
job: ValidarDEV
displayName: 'Validar Devops_Dev (Desarrollo)'
steps:
task: PowerPlatformToolInstaller@2
displayName: 'Instalar Power Platform CLI'
task: PowerPlatformWhoAmi@2
displayName: 'WhoAmI contra DEV'
inputs:
authenticationType: 'PowerPlatformSPN'
PowerPlatformSPN: 'Devops_Dev'
job: ValidarPROD
displayName: 'Validar Devops_prod (Devops_Prod)'
steps:
task: PowerPlatformToolInstaller@2
displayName: 'Instalar Power Platform CLI'
task: PowerPlatformWhoAmi@2
displayName: 'WhoAmI contra PROD'
inputs:
authenticationType: 'PowerPlatformSPN'
PowerPlatformSPN: 'Devops_prod'
0:00:00 - Introducción y bienvenida
0:01:43 - Recapitulación: Conexiones de Azure DevOps
0:03:26 - Servicios principales de Azure DevOps
0:08:02 - Ciclo de vida real del trabajo en Azure DevOps
0:10:46 - ¿Por qué usar control de versiones?
0:13:53 - Vocabulario esencial de Git
0:16:32 - Dinámica de trabajo: Clon, Pull y Push
0:20:36 - Creación de un repositorio en Azure DevOps
0:24:55 - Anatomía de un pipeline en YAML
0:27:52 - Métodos de ejecución de pipelines
0:31:01 - Configuración y prueba de conexiones
0:42:50 - Solución de errores comunes
0:45:49 - Estructura recomendada para proyectos
0:48:15 - Próximos pasos y aprobaciones
0:49:55 - Sesión de preguntas y respuestas
#MicrosoftReactor #LearnConnectBuild #Devops, #PowerPlatform, #ALM
[eventID:27568]
En esta sesión configuraremos un proyecto y un repositorio en Azure DevOps, instalaremos Microsoft Power Platform Build Tools y crearemos una conexión de servicio segura con los entornos de Power Platform.
🔗 Aprende más accediendo a los recursos: https://aka.ms/PowerPlatformParaAzureDevOps
📌 Este evento es parte de una serie, aprende más aquí: https://aka.ms/PowerPlatformALM/y
Codigo:
trigger: none
pool:
vmImage: 'windows-latest'
jobs:
job: ValidarDEV
displayName: 'Validar Devops_Dev (Desarrollo)'
steps:
task: PowerPlatformToolInstaller@2
displayName: 'Instalar Power Platform CLI'
task: PowerPlatformWhoAmi@2
displayName: 'WhoAmI contra DEV'
inputs:
authenticationType: 'PowerPlatformSPN'
PowerPlatformSPN: 'Devops_Dev'
job: ValidarPROD
displayName: 'Validar Devops_prod (Devops_Prod)'
steps:
task: PowerPlatformToolInstaller@2
displayName: 'Instalar Power Platform CLI'
task: PowerPlatformWhoAmi@2
displayName: 'WhoAmI contra PROD'
inputs:
authenticationType: 'PowerPlatformSPN'
PowerPlatformSPN: 'Devops_prod'
0:00:00 - Introducción y bienvenida
0:01:43 - Recapitulación: Conexiones de Azure DevOps
0:03:26 - Servicios principales de Azure DevOps
0:08:02 - Ciclo de vida real del trabajo en Azure DevOps
0:10:46 - ¿Por qué usar control de versiones?
0:13:53 - Vocabulario esencial de Git
0:16:32 - Dinámica de trabajo: Clon, Pull y Push
0:20:36 - Creación de un repositorio en Azure DevOps
0:24:55 - Anatomía de un pipeline en YAML
0:27:52 - Métodos de ejecución de pipelines
0:31:01 - Configuración y prueba de conexiones
0:42:50 - Solución de errores comunes
0:45:49 - Estructura recomendada para proyectos
0:48:15 - Próximos pasos y aprobaciones
0:49:55 - Sesión de preguntas y respuestas
#MicrosoftReactor #LearnConnectBuild #Devops, #PowerPlatform, #ALM
[eventID:27568]
![Fabric IQ y Ontología MCP: la capa semántica que entiende tu negocio
La sesión final lleva la serie al nivel más avanzado: la semántica empresarial como fundamento de todos los agentes.
Fabric IQ (GA desde Build 2026) es la capa de contexto compartido que unifica Data Agents, modelos semánticos y Ontologías sobre OneLake.
Aprenderás qué es una Ontología en Fabric, cómo define entidades, relaciones, propiedades y reglas de negocio vinculadas a datos en vivo, y cómo exponerla como servidor MCP para que cualquier agente externo — Claude, Copilot, agentes de Foundry — pueda fundamentar su razonamiento en ella sin reescribir integraciones.
Construiremos un flujo multi-agente completo donde el orquestador consulta la Ontología vía MCP para entender el negocio, delega al Data Agent para los datos, y entrega respuestas consistentes y gobernadas.
Cerraremos con una hoja de ruta práctica: qué está GA, qué está en Preview, y cómo planificar la adopción en tu organización hoy mismo. Los últimos 15 minutos serán Q&A abierto.
Trae tu caso de uso real — los últimos 15 minutos son para arquitectura personalizada y preguntas abiertas.
¿Qué es Fabric IQ?
https://learn.microsoft.com/fabric/iq/overview/?wt.mc_id=youtube_27357_organicsocial_reactor
📌 Este evento es parte de una serie, aprende más aquí: https://aka.ms/AgentesFabric
0:04 Introducción y Bienvenida
3:36 Conceptos clave: Fabric IQ, Ontología y MCP
9:17 Caso práctico: Cadena de Frío
13:10 Arquitectura y Orquestación de Agentes
14:00 Configuración en Visual Studio Code
17:15 Mejores prácticas para modelos semánticos
20:00 Diferencias entre origen en Lakehouse vs. Modelo Semántico
34:02 Roadmap oficial y conceptos de Data Agents
41:36 Creación de ontologías (Automática vs. Manual)
55:31 Configuración de MCP en Codex
1:13:05 Demostración: Consultas con prompts
1:16:35 Conclusión, cierre y Q&A
[eventID:27357] Fabric IQ y Ontología MCP: la capa semántica que entiende tu negocio](https://i.ytimg.com/vi/os4zRz3esyM/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
Introduction and Housekeeping: (0:00 - 3:00)
AI Genius Season 5 Overview: (3:00 - 4:40)
Building Blocks of Agentic Workflows: (4:40 - 7:00)
Demo: Retail Analytics Assistant: (7:00 - 9:10)
Conceptualizing Agentic Workflows: (9:10 - 13:30)
Architecture of the Retail Assistant: (13:30 - 17:40)
Phase 1: Session & Client Setup: (17:40 - 21:15)
Phase 2: Understanding Events: (21:15 - 29:10)
Phase 3: Connecting Tools (MCP): (29:10 - 36:15)
Phase 4: Session Persistence: (36:15 - 39:50)
Phase 5: Advanced MCP Integration: (39:50 - 43:30)
Deployment Options & Security: (43:30 - 50:50)
Resources & Q&A: (50:50 - 58:05)
[eventID:27464] Build with AI: GitHub Copilot SDK for Building Agentic Workflows](https://i.ytimg.com/vi/pWZZrB-kaFU/mqdefault.jpg)
![Model Mondays - Train and customize open models with Fireworks on Foundry
More than 90% of enterprise data resides in internal systems and records. In this session, learn how Fireworks brings model customization to Azure AI Foundry as a first-party service.
Deploy open models from the Foundry catalog, train them on your data, and serve them through your Azure subscription using existing identity, governance, and billing controls.
0:00 Introduction and Housekeeping
0:53 Welcome to Model Mondays
2:16 Weekly Highlights in Foundry
9:38 Introduction to Fireworks on Foundry
11:38 Why Customers Choose Open Models
12:38 Fireworks Architecture and Integration
14:48 Model Catalog and Deployment Overview
17:18 Customer Journey and Setup
27:06 Deep Dive: Training and Customization
30:00 Bring Your Own Weights BYOW
33:20 Building Agentic Systems
36:00 Coding and Customer Support Agent Patterns
38:18 Cybersecurity Agent Patterns
39:57 Customer Story: GenSpark
41:05 Live Demos
47:01 Q&A Session
52:56 Hackathon Announcement
54:40 Conclusion and Next Session
- Explore the Resources https://github.com/microsoft/model-mondays
- Read the Newsletter https://aka.ms/model-mondays/newsletter
- Continue the conversation on the Discord https://aka.ms/model-mondays/discord
[event ID:27576] Model Mondays - Train and customize open models with Fireworks on Foundry](https://i.ytimg.com/vi/pmz_6Sg0QAY/mqdefault.jpg)
![Building Digital Teammates in Microsoft Teams
Want to build AI agents that work alongside people in Microsoft Teams? This session covers how to design, build and run collaborative agents that fit naturally into the way teams already work.
Well go through best practices for building agents that help people collaborate in chats, channels and meetings. Then well show you how to use the Teams SDK and the Developer Portal to build, configure and run your agent from start to finish. Youll also learn which Teams features work best for different types of agents, so you can pick the right approach for your scenario.
📌 This event is part of a series. Learn more here:
https://aka.ms/BeyondTheAgentSeries/y
#MicrosoftReactor #LearnConnectBuild #MicrosoftTeams #TeamsSDK #WorkIQ
[eventID:27790] Building Digital Teammates in Microsoft Teams](https://i.ytimg.com/vi/q7WYX5j5WMI/mqdefault.jpg)
![Bicep 101: Learning the Fundamentals of Microsofts Infrastructure as Code Language
Teams that manage Azure through the portal or with scripts often cannot repeat a deployment exactly or review a change before it happens.
This session teaches the fundamentals of Bicep to people who are new to infrastructure as code. I am a product manager at Microsoft on Azure Bicep and owning Deployment Stacks.
Bicep is Azures native infrastructure as code language, and it is stateless, so there is no state file to manage.
In the demo I write a Bicep file in VS Code, use IntelliSense and the linter to catch mistakes as I type, and deploy it with the Azure CLI. I then use Azure Verified Modules, which provide ready-made Bicep modules for common resources, and deploy the environment as a deployment stack, which manages a group of resources as a single unit.
Before each change, Stacks What-If shows exactly which resources will be created, modified, or deleted, and deny settings block deletes made outside the stack.
The result is a first Bicep deployment you can repeat, review, and build on. Everything runs live from VS Code and the Azure CLI.
What attendees will learn: - How to write and deploy a Bicep file in VS Code with the Azure CLI. - How Azure Verified Modules provide ready-made Bicep modules for common resources. - How a deployment stack and Stacks What-If let you see and control every change to an environment.
[eventID:278140] Bicep 101: Learning the Fundamentals of Microsofts Infrastructure as Code Language](https://i.ytimg.com/vi/qR9bZyueGgo/mqdefault.jpg)
![IA no Trabalho: O que isso significa de verdade para profissionais de dados?
A IA está aparecendo em todo lugar. Mas o que isso realmente muda para quem trabalha com dados todos os dias?
Vamos conversar sobre o que já está mudando, o que provavelmente não vai mudar e no que profissionais de dados deveriam prestar atenção agora.
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
0:00 - Introdução e Boas-vindas
2:12 - Apresentação dos palestrantes (Armando Lacerda e Brendel Gomes)
4:45 - Moderadores do chat e interações ao vivo
6:18 - Agenda da série Data Days
7:16 - Importância das certificações Microsoft
8:18 - Grupos de estudo e feedback da comunidade
10:35 - Competição de Dataviz
11:19 - IA no trabalho: O medo da substituição
12:23 - Como você está usando a IA hoje? (Enquete)
14:38 - A IA pode escrever SQL/Códigos? Impacto no dia a dia
17:18 - O que mudou no trabalho com dados em 1 ano?
20:50 - O que realmente mudou no trabalho diário (Copilot e Fabric)
24:32 - Habilidades que a IA não substitui (Criatividade e Regras de Negócio)
30:50 - A importância de dar contexto e temperar a IA
32:32 - Confiança, privacidade e segurança (LGPD/RGPD)
38:34 - Como a IA se encaixa no fluxo de trabalho com Microsoft Fabric
44:13 - Agentes de IA: Confiabilidade e tomada de decisão
49:45 - Entendendo o Fabric IQ
53:20 - Soft skills e a importância da comunicação
55:50 - Tornando-se mais valioso com produtividade extra
58:08 - Dicas de carreira e o que estudar agora
1:00:57 - O que faremos de diferente a partir de hoje
#MicrosoftReactor #LearnConnectBuild #Fabric #AI #DataDays
[eventID:27726] IA no Trabalho: O que isso significa de verdade para profissionais de dados?](https://i.ytimg.com/vi/qT-iP1d325w/mqdefault.jpg)
![Del insight a la acción: crea una app para un problema real de trabajo
Empecemos con un problema que las personas realmente tienen en el trabajo y construyamos algo útil para resolverlo.
Pasaremos de los datos y el insight a una Fabric App funcionando, mostrando las decisiones, los trade-offs y las lecciones que surgen por el camino.
[eventID:27757] Del insight a la acción: crea una app para un problema real de trabajo](https://i.ytimg.com/vi/qaywfBfme6M/mqdefault.jpg)
![From Tribal Knowledge to Code: Custom Skills for GitHub Copilot Modernization
Every application contains business rules, architectural patterns, internal frameworks, and development standards that generic AI cannot fully understand.
Without that context, modernization efforts can produce inconsistent results and require significant manual review.
Learn how GitHub Copilot Modernization custom skills help organizations bring their institutional knowledge directly into the modernization process.
See how custom skills can encode business logic, software factory patterns, and governance requirements to generate more consistent, accurate, and production-ready outcomes across applications and teams. Through a live demonstration, youll see how custom skills transform modernization workflows by turning tribal knowledge into reusable guidance that scales across projects.
Join us to learn how to preserve organizational expertise while accelerating application modernization with AI.
Key Takeaway: Custom skills help organizations modernize faster while ensuring AI-generated changes align with their unique standards, practices, and business requirements.
0:00:02 - Welcome and Introduction
0:00:54 - Modernization Skills and Tribal Knowledge
0:02:43 - Five Key Takeaways
0:04:15 - Demo 1: Modernizing Libraries (Newtonsoft to System.Text.Json)
0:11:15 - Demo 2: Codifying Tribal Knowledge into Skills
0:15:10 - Understanding the Skill Definition Structure
0:21:30 - Demo 3: Testing and Refining Skills
0:31:08 - Demo 4: Troubleshooting and Fixing Regression Bugs
0:40:20 - Demo 5: Reusing Skills for New Features
0:47:15 - Behind the Scenes: Managing Skill Workflows
0:50:40 - Recap: Tools for Modernization (Prompts, Skills, Tests)
0:51:37 - Next Steps: Building a Team Practice
0:53:00 - Resources and Official Documentation
[eventID:27594] From Tribal Knowledge to Code: Custom Skills for GitHub Copilot Modernization](https://i.ytimg.com/vi/qm-VbLDoMFU/mqdefault.jpg)
![Model Mondays - Voice Agents Upgraded: New Speech Models and Agent Experience In Foundry
Speech models let applications understand and generate spoken language, powering experiences like transcription, real-time voice interaction, and accessible conversational interfaces.
In this episode, well walk through a live demo in the Foundry playground that shows how to build, test, monitor, and optimize a voice agent from start to finish. Well also cover the latest development in speech-to-text, text-to-speech, and speech-to-speech models in Azure Speech in Microsoft Foundry, including new MAI models, and how they make voice agents more natural and responsive.
Repo - https://aka.ms/model-mondays
Resources: https://aka.ms/model-mondays/collection
0:00:00 - Introduction and Code of Conduct
0:00:54 - Model Mondays: Welcome and Overview
0:01:54 - Weekly News Highlights: New Models and Infrastructure
0:07:16 - Voice Agents in Microsoft Foundry: Overview and Capabilities
0:14:14 - Live Demo: Building a Voice Agent for Finance
0:34:07 - Audio Models in Microsoft AI: Transcription and Speech
0:44:48 - Speech Models in Foundry: Architectures and Pipelines
0:51:09 - Customer Use Cases and Implementation Q&A
1:00:32 - Wrap-up and Next Episode Announcement
- Explore the Resources
https://github.com/microsoft/model-mondays
- Read the Newsletter https://aka.ms/model-mondays/newsletter
- Continue the conversation on the Discord https://aka.ms/model-mondays/discord
[eventID: 27565] Model Mondays - Voice Agents Upgraded: New Speech Models and Agent Experience In Foundry](https://i.ytimg.com/vi/rBFQLt3StVI/mqdefault.jpg)
![Talvez você já esteja usando mais IA do que imagina
A IA já está aparecendo nas ferramentas que profissionais de dados usam todos os dias, às vezes de formas que nem percebemos.
Vamos explorar o que talvez já esteja disponível para você, onde a IA pode ajudar e onde o seu próprio julgamento continua sendo essencial.
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:27729] Talvez você já esteja usando mais IA do que imagina](https://i.ytimg.com/vi/rFQJN53piws/mqdefault.jpg)
![The Agent Harness: From GitHub Copilot to Production AI
What if the secret to building better AI agents isnt a bigger model, but a better harness?
In this episode of New Breakpoint, Graeme Foster explores the GitHub Copilot SDK and the emerging agent harness pattern thats powering a new generation of AI experiences.
Discover how planning, tool use, code execution and reasoning come together to help agents solve real-world problems and learn how these capabilities can be extended beyond the IDE into hosted, governed and enterprise-ready solutions.
Key takeaways:
Understand the agent harness pattern and why modern AI systems are about more than just models, combining tools, planning, execution and orchestration to achieve complex goals.
Explore the GitHub Copilot SDK in action, including how agents can analyse data, execute code, interact with files and leverage external tools to complete end-to-end workflows.
Learn how to take agents into production with hosted experiences, identity, governance and integration with Foundry, enabling scalable and enterprise-ready AI solutions.
0:04 Introduction to New Breakpoint
0:58 Meet Graeme Foster and the Agent Harness
5:07 Redefining Complex Agentic Systems
7:33 What Is an Agent Harness?
15:05 GitHub Copilot SDK and Agent Examples
22:10 The .NET Development Experience
26:45 Using Skills for Progressive Disclosure
32:09 Data Analysis with the Claims Tool
40:46 Deploying to Microsoft Foundry
48:33 Identity and Governance for Agents
52:05 Closing Thoughts and Future Outlook
[eventID:27595] The Agent Harness: From GitHub Copilot to Production AI](https://i.ytimg.com/vi/rTGX69aa-z8/mqdefault.jpg)