Uploaded August 2026 | Updated September 2026, 2 weeks ago
What happens when you take AI out of the lab and deploy it in the Australian outback? Join Microsoft MVP Daniel Brown live from the opal fields of Coober Pedy, South Australia, as he explores how OpalAI was built to use artificial intelligence to help identify opal-bearing material during mining operations. Using OpalAI as a real-world case study, we'll explore the journey from collecting and preparing field data through to building an AI solution with Microsoft Azure, integrating AI into an application, and deploying it in a challenging real-world environment. We'll examine the practical engineering challenges that emerge outside controlled environments, including changing lighting conditions, dust, camera positioning, false positives, confidence thresholds and model improvement. The session will culminate in a live field demonstration, running material through OpalAI from an active opal claim in Coober Pedy to see whether AI can identify potential opal in real time. Developers will leave with practical lessons for designing, building and deploying AI applications that connect software, AI and the physical world, together with Microsoft resources for continuing their learning.
What happens when you take AI out of the lab and deploy it in the Australian outback? Join Microsoft MVP Daniel Brown live from the opal fields of Coober Pedy, South Australia, as he explores how OpalAI was built to use artificial intelligence to help identify opal-bearing material during mining operations. Using OpalAI as a real-world case study, we'll explore the journey from collecting and preparing field data through to building an AI solution with Microsoft Azure, integrating AI into an application, and deploying it in a challenging real-world environment. We'll examine the practical engineering challenges that emerge outside controlled environments, including changing lighting conditions, dust, camera positioning, false positives, confidence thresholds and model improvement. The session will culminate in a live field demonstration, running material through OpalAI from an active opal claim in Coober Pedy to see whether AI can identify potential opal in real time. Developers will leave with practical lessons for designing, building and deploying AI applications that connect software, AI and the physical world, together with Microsoft resources for continuing their learning.
![Secure by Design: Building Security into Every Commit with GitHub Copilot
Security isnt just the security teams job.
In this episode of New Breakpoint, Michelle Sandford is joined by George Coldham, Cloud Solution Architect at Microsoft, to explore how developers can use GitHub and GitHub Copilot to make security a natural part of their everyday workflow.
Through a live demo, George shows how to identify exposed secrets, detect vulnerable dependencies, improve code quality, and leverage AI-powered tools to address issues before they reach production.
Whether youre an experienced developer or just getting started, youll learn practical ways to build more secure applications while maintaining speed and productivity, and why human accountability remains critical in AI-assisted development.
Learn more about the series: https://aka.ms/NewBreakpoint/r
Check out the resources: https://aka.ms/new-breakpoint/log
00:00 Introduction
03:49 Demo Application Overview
09:21 Security Is Everyones Responsibility
12:23 Discovering an XSS Vulnerability
20:13 Using GitHub Copilot to Fix Security Issues
22:24 Testing and Validating the Fix
26:08 Pull Requests, Reviews & Branch Protection
31:24 Security & Quality Dashboard
33:24 Code Scanning, Secret Scanning & Dependabot
34:33 Copilot Autofix and Security Remediation
37:10 Managing Package Vulnerabilities
44:04 Secret Management & Push Protection
49:38 CI/CD Security Validation
51:20 GitHub Copilot Optimization Tips
55:22 Security-First Development Practices
57:28 Closing & Resources
[eventID:27494] Secure by Design: Building Security into Every Commit with GitHub Copilot](https://i.ytimg.com/vi/DyGumvvyYy8/mqdefault.jpg)
![Build AI-powered soccer insights apps with cloud-native Azure Databases
Learn how to build and deploy AI-powered applications that analyze football match and player data using cloud-native Azure Databases.
Using Premier League-inspired scenarios such as identifying team play styles, analyzing counterattacks, or uncovering player performance patterns, well walk through a reference architecture that pairs operational data in Azure SQL, PostgreSQL, and Cosmos DB with vector search and retrieval to ground your models in real match data.
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/Pre
ierLeagueHack
🔗 Learn more by exploring the resources:
https://aka.ms/AzureCosmosDBnoSQL
https://aka.ms/datadrivenappsqldb
https://aka.ms/azure-database-postgresql
#MicrosoftReactor #LearnConnectBuild #PremierLeagueHackathon
[eventID:27555] Build AI-powered soccer insights apps with cloud-native Azure Databases](https://i.ytimg.com/vi/EQ187ohgCbo/mqdefault.jpg)

[eventID:27507] Beyond Chatbots: Build Your First Production Agent with Microsoft Foundry](https://i.ytimg.com/vi/ExJXHCkeO4A/mqdefault.jpg)
![Designing Better Data Models with an AI Coding Agent
Part of the Modern AI Apps with Azure Cosmos DB Series.
Data modeling is one of the hardest parts of building distributed applications, and its easy to get wrong early. This session explores how an agent can help design containers, partition keys, relationships, and access patterns for Azure Cosmos DB while teaching developers how to validate those recommendations.
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/
#azurecosmosdb #aicoding
[eventID:27240] Designing Better Data Models with an AI Coding Agent](https://i.ytimg.com/vi/F2RKDp65WUw/mqdefault.jpg)
![Build a Recruiter AI Agent Using Outlook, SharePoint, and Microsoft Teams
In this practical technical session, you will learn how to build an intelligent Recruiter AI agent that automates resource enquiries using Microsoft Outlook, SharePoint, and Microsoft Teams.
The Recruiter AI agent will process incoming resource requirement emails, understand the recruiter’s request, securely search resumes stored in a SharePoint knowledge base, identify suitable candidates, compose a contextual email response, and schedule a Microsoft Teams meeting with the sender.
**During the session, you will learn how to:**
• Trigger the Recruiter AI agent when a resource enquiry is received in Outlook.
• Extract job requirements, skills, experience, and other relevant information from incoming emails.
• Create contextual prompts based on the recruiter’s requirements.
• Configure a SharePoint folder containing resumes as the agent’s knowledge base.
• Search and retrieve relevant candidate profiles from SharePoint.
• Connect knowledge sources and external tools with an AI agent.
• Manage the complete workflow from email receipt to candidate recommendation.
• Apply access control, data security, governance, error handling, and human approval to recruitment workflows.
The session will also include an end-to-end demonstration in which the Recruiter AI agent receives a resource enquiry, searches the SharePoint resume repository, selects relevant candidate profiles, sends a response to the requester, and books a follow-up meeting in Microsoft Teams.
By the end of the session, participants will understand the complete architecture and implementation approach for building an enterprise-ready Recruiter AI agent that connects organizational knowledge with email and meeting-management tools.
[event ID:27535] Build a Recruiter AI Agent Using Outlook, SharePoint, and Microsoft Teams](https://i.ytimg.com/vi/FMIF3f9HtCY/mqdefault.jpg)
![Inside the Mind of a Dataviz World Champion
What does a Dataviz World Champion actually do differently? It’s not just design skills. It’s how they think, how they spot the story, and how they turn data into something people feel. Join recent finalists Santhana Lakshmi Ponnurasan and Michał Jezik as they break down how they approach dashboards from the first spark of an idea to the final polished result.
Real examples, real decisions, real insight. Come see how champions think—and walk away inspired to level up your own work.
📍This session is a part of a series. Learn more here:
https://aka.ms/datadayslive/viz
#MSFTReactor #dataviz #learnconnectbuild
[eventid:27363] Inside the Mind of a Dataviz World Champion](https://i.ytimg.com/vi/FXQHDVfl5ek/mqdefault.jpg)
![De “tô só começando” para “caramba, eu fiz isso”
Acha que contest é só pra quem já manda muito? Nada disso. Esse é o seu ponto de partida.
Nessa sessão, a gente vai mostrar como contests mais acessíveis podem ser uma das formas mais rápidas e divertidas de aprender Microsoft Fabric, Power BI, SQL e AI. Sem precisar de horas e horas, sem pressão de fazer perfeito. São desafios pequenos, práticos, que te colocam pra construir, testar coisas novas e evoluir quase sem perceber. Você vai sair do “tô só começando” pra “opa, olha isso aqui que eu fiz”.
E melhor ainda, você não vai fazer isso sozinho. A ideia é aprender junto, pegar inspiração no que outras pessoas estão criando e evoluir em comunidade. Chega, testa, brinca com as ideias e vê no que dá. No pior cenário, você aprende algo novo. No melhor… você se surpreende.
🔗Saiba mais sobre o Campeonato Mundial: https://aka.ms/nextworldchamps
🔗Inscreva-se no Data Days: https://aka.ms/datadays
0:05 - Introdução e boas-vindas
0:53 - Apresentação dos convidados: Dirceu Rezende e Hugo Venturini
4:48 - O que é o Data Days 2026
7:20 - Como obter a certificação Fabric gratuitamente
10:53 - Grupos de estudo e comunidades
12:18 - Feedback de produtos (User Panels)
13:35 - Cronograma das próximas lives (DP-800 e IA no SQL)
15:36 - Por que participar de concursos de Data Viz
22:40 - A importância da comunidade internacional
26:23 - Quebrando mitos sobre concursos de tecnologia
36:57 - Como concursos aceleram o seu aprendizado
51:20 - O ciclo de crescimento de um criador
55:13 - Dicas para uma inscrição vencedora em Data Viz
58:26 - Orientações para iniciantes
1:01:31 - Depoimento do campeão mundial Paulo Grijó
#microsoftreactor #learnconnectbuild #datadays
[eventID: 27378] De “tô só começando” para “caramba, eu fiz isso”](https://i.ytimg.com/vi/FactowzAc1s/mqdefault.jpg)
![Introdução ao Agentic Dev com Spec-Driven no VS Code
Introdução aos fundamentos de agentic development no Visual Studio Code com GitHub Copilot.
Nesta sessão, você irá definir o comportamento de agentes usando AGENTS.md e comparar interações baseadas em prompts com abordagens estruturadas. Implementação do primeiro setup orientado por especificação.
📌 Este evento faz parte de uma série, saiba mais aqui: https://aka.ms/AgenticDevVSCode
🔗 https://aka.ms/AgenticDevSeries/Resource
[eventID:27387] Introdução ao Agentic Dev com Spec-Driven no VS Code](https://i.ytimg.com/vi/G3PspHndPiQ/mqdefault.jpg)
![Inside Fabric Runtime 2.0: Spark 4 and Delta 4 in Action
Fabric Runtime 2.0 is a major leap forward for running Spark at scale in Microsoft Fabric.
Join members of the Microsoft product team for a deep dive into what’s new and what it means for you. You will get a clear look at the biggest innovations in Spark 4 and Delta 4, along with the Microsoft enhancements that drive better performance, reliability, and developer productivity.
This is your chance to learn directly from the people building the platform and understand how to take advantage of these changes in real-world workloads.
🔗 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
0:00 Welcome & Session Introduction
2:25 Meet the Speakers & Fabric Runtime 2.0 Overview
5:14 Agenda: Spark 4, Delta Lake & Native Execution Engine
6:08 Apache Spark 4: SQL Enhancements
12:35 Real-Time Streaming in Spark 4
17:17 Observability & Monitoring Improvements
18:58 Delta Lake 4 Overview
20:15 Type Widening & Schema Evolution
23:58 Variant Data Type for Semi-Structured Data
25:55 Identity Columns in Delta Lake
27:30 Table Layout, File Skipping & Performance
33:39 Adaptive File Sizing & Intelligent Optimization
35:01 Liquid Clustering & Auto Reclustering
40:20 Auto Compaction, Vacuum & Performance Features
42:10 Deletion Vectors & Snapshot Acceleration
44:18 Native Execution Engine Architecture
47:03 Enabling Native Execution Engine
49:55 Gluten, Velox & Query Optimization
53:35 Runtime 2.0 Native Engine Enhancements
58:36 Best Practices for Native Execution Engine
1:00:37 Anti-Patterns & Migration Guidance
1:02:42 Q&A Session
1:10:18 Feedback & Closing Remarks
#MSFTReactor #learnconnectbuild
[eventID:27281] Inside Fabric Runtime 2.0: Spark 4 and Delta 4 in Action](https://i.ytimg.com/vi/Gcyk_eJACPA/mqdefault.jpg)
![DAX agéntico: valida, genera y optimiza medidas con agentes de IA
El DAX siempre ha sido la barrera de entrada a Power BI para muchos profesionales.
En esta sesión veremos cómo los agentes conectados al Remote MCP Server usan el mismo motor de generación DAX que Copilot para Power BI, y cómo el Local MCP permite validar y ejecutar consultas DAX directamente contra el modelo para testear medidas, depurar cálculos y explorar datos sin salir del agente.
Exploraremos prompts avanzados para generar medidas complejas, patrones de inteligencia de tiempo, cálculos condicionales y medidas de tabla, y veremos los límites actuales — qué tipos de DAX generan bien los agentes y dónde todavía hay que revisar.
También cubriremos cómo optimizar el modelo semántico para mejorar la calidad de generación DAX por parte del agente, y cómo combinar Local y Remote MCP en el mismo flujo de trabajo.
DAX agéntico: valida, genera y optimiza medidas con agentes de IA: https://learn.microsoft.com/power-bi/developer/mcp/remote-mcp-server-tools/?wt.mc_id=youtube_27343_organicsocial_reactor
📌 Este evento es parte de una serie, aprende más aquí: https://aka.ms/PBIMCP
0:00:04 - Introducción y contexto de la serie
0:06:36 - Instalación de Skills de Microsoft para Fabric
0:15:56 - Configuración de rutas y variables en PowerShell
0:28:02 - Arquitectura de las Skills y archivos .MD
0:37:01 - Formas de invocar habilidades (Explícito, Automático, Persistente)
0:43:21 - Creación y configuración del archivo agents.md
0:57:04 - Demostración: Creación de relaciones con IA
1:07:43 - Conclusiones y cierre de la sesión
[eventID:27343] DAX agéntico: valida, genera y optimiza medidas con agentes de IA](https://i.ytimg.com/vi/GdbnFoOOWWk/mqdefault.jpg)
