Uploaded July 2026 | Updated September 2026, 2 weeks ago
In this episode of New Breakpoint, Michelle Sandford sits down with Aaron Powell to explore the GitHub Copilot App - a new experience that brings agentic workflows directly into your day-to-day work on GitHub. Rather than focusing purely on code, the Copilot App introduces a shift toward task-driven collaboration, enabling developers and broader technical teams to manage pull requests, issues, and backlogs through intelligent, agent-powered workflows.
Together, Michelle and Aaron take a hands-on look at how the app enables:
- Automations: creating scheduled workflows like daily pull request summaries or issue triage, tailored to your team’s needs
- Agent-driven sessions: working across repositories with isolated contexts, allowing multiple streams of work to run in parallel
- Backlog visibility: helping product owners and managers stay across issues and progress without needing to dive into code
- Interactive collaboration: reviewing changes, adding inline feedback, and steering agents in real time
- Extensibility: using skills, plugins, and canvases to customise workflows, visualise data, and even build lightweight apps
The episode also explores how the Copilot App bridges the gap between developers and non-developers, making it easier for entire teams to participate in modern, AI-powered workflows - whether you’re writing code, managing a sprint, or tracking progress on the go. If you’re looking to understand how automations, agents, and real-world workflows come together inside GitHub, this is a great place to start.
Get started with the GitHub Copilot app: awesome-copilot.github.com/learning-hub/github-copilot-app
Learn more about the series: https://aka.ms/NewBreakpoint/r
0:04 Welcome to New Breakpoint
0:28 Meet Aaron Powell and GitHub Copilot
2:07 Copilot SDK vs GitHub Copilot App
3:22 What Is the GitHub Copilot App?
5:19 First Look at the Copilot App Interface
7:13 Automations and Daily GitHub Summaries
9:30 Building Custom Automations
11:32 Copilot for Product Owners and Technical Teams
13:43 Sessions, Agents, and Workflow Management
17:06 Git Work Trees and Parallel Agent Workflows
19:30 Merge Conflicts and Multi-Agent Collaboration
21:18 Creating Sessions from Pull Requests
24:02 Code Reviews and Context-Aware Comments
28:10 Session Navigation and History Tracking
29:29 Opening Copilot Sessions in VS Code
32:27 Skills and Extensions in Copilot App
32:58 Introducing Copilot Canvas
34:21 Building Custom Canvas Experiences
35:28 Canvas Demo: Building a Snake Game
36:38 Integrating External Services and Azure DevOps
38:48 Awesome Copilot and the Learning Hub
41:05 Custom Notifications and Sound Effects
42:26 Documentation and Best Practices
44:58 How to Get the GitHub Copilot App
45:36 Mobile Access and Cloud Agents
47:05 Managing Agent Sessions from GitHub Mobile
47:42 Real-World Cloud Agent Workflow
49:41 Final Thoughts on Developer Productivity
50:07 Resources and Further Learning
50:46 Live Q&A Session
[eventID:27339]
In this episode of New Breakpoint, Michelle Sandford sits down with Aaron Powell to explore the GitHub Copilot App - a new experience that brings agentic workflows directly into your day-to-day work on GitHub. Rather than focusing purely on code, the Copilot App introduces a shift toward task-driven collaboration, enabling developers and broader technical teams to manage pull requests, issues, and backlogs through intelligent, agent-powered workflows.
Together, Michelle and Aaron take a hands-on look at how the app enables:
- Automations: creating scheduled workflows like daily pull request summaries or issue triage, tailored to your team’s needs
- Agent-driven sessions: working across repositories with isolated contexts, allowing multiple streams of work to run in parallel
- Backlog visibility: helping product owners and managers stay across issues and progress without needing to dive into code
- Interactive collaboration: reviewing changes, adding inline feedback, and steering agents in real time
- Extensibility: using skills, plugins, and canvases to customise workflows, visualise data, and even build lightweight apps
The episode also explores how the Copilot App bridges the gap between developers and non-developers, making it easier for entire teams to participate in modern, AI-powered workflows - whether you’re writing code, managing a sprint, or tracking progress on the go. If you’re looking to understand how automations, agents, and real-world workflows come together inside GitHub, this is a great place to start.
Get started with the GitHub Copilot app: awesome-copilot.github.com/learning-hub/github-copilot-app
Learn more about the series: https://aka.ms/NewBreakpoint/r
0:04 Welcome to New Breakpoint
0:28 Meet Aaron Powell and GitHub Copilot
2:07 Copilot SDK vs GitHub Copilot App
3:22 What Is the GitHub Copilot App?
5:19 First Look at the Copilot App Interface
7:13 Automations and Daily GitHub Summaries
9:30 Building Custom Automations
11:32 Copilot for Product Owners and Technical Teams
13:43 Sessions, Agents, and Workflow Management
17:06 Git Work Trees and Parallel Agent Workflows
19:30 Merge Conflicts and Multi-Agent Collaboration
21:18 Creating Sessions from Pull Requests
24:02 Code Reviews and Context-Aware Comments
28:10 Session Navigation and History Tracking
29:29 Opening Copilot Sessions in VS Code
32:27 Skills and Extensions in Copilot App
32:58 Introducing Copilot Canvas
34:21 Building Custom Canvas Experiences
35:28 Canvas Demo: Building a Snake Game
36:38 Integrating External Services and Azure DevOps
38:48 Awesome Copilot and the Learning Hub
41:05 Custom Notifications and Sound Effects
42:26 Documentation and Best Practices
44:58 How to Get the GitHub Copilot App
45:36 Mobile Access and Cloud Agents
47:05 Managing Agent Sessions from GitHub Mobile
47:42 Real-World Cloud Agent Workflow
49:41 Final Thoughts on Developer Productivity
50:07 Resources and Further Learning
50:46 Live Q&A Session
[eventID:27339]


![OpenClawNet - Automatización + Azure + Foundry
En esta sesión prepararemos el agente para producción. Agregaremos programación de tareas como servicio de fondo, integraremos Azure OpenAI y Azure AI Foundry como proveedores de modelos en la nube, construiremos dashboards de monitoreo, y escribiremos tests unitarios que verifiquen todo el stack.
Al final tendremos una plataforma de agentes completa, testeada y lista para la nube con manejo de errores de nivel producción, múltiples proveedores de modelos AI, automatización programada, y dashboards de observabilidad. Despliégala en Azure Container Apps, App Service, o ejecútala on-premises con Ollama.
Tópicos y Tecnologías Clave:
- BackgroundService para tareas de larga duración
- Integración de Azure OpenAI y selección de modelos
- Azure AI Foundry (inferencia, despliegues, evaluación)
- Patrones de testing unitarios para agentes y herramientas
- Health checks y diagnósticos del sistema
- Job queuing y tracking de estado
- Configuración para despliegues multi-ambiente (local, staging, producción)
📌 Este evento es parte de una serie, aprende más aquí: https://aka.ms/NET10GHC/es/y
Capítulos:
0:00 Introducción y presentación de OpenClaw.net
1:27 ¿Qué es OpenClaw.net? Propósito del proyecto
2:47 Agenda: Aspire, Trazas, Skills y Secretos
4:00 Recorrido por el repositorio público
4:45 Flujo de trabajo con GitHub Copilot (PRs y Code Review)
7:41 Gestión de múltiples repositorios y sincronización (Privado vs Público)
11:42 Análisis de Pull Requests con Copilot
16:03 Uso de Canvases en GitHub Copilot
21:19 Aspire en Visual Studio Code: Dashboard y monitorización
24:43 Foundry Tool Kit para la gestión en la nube
29:07 Implementación de Secret Vault (Bóveda de secretos)
32:38 Depuración en vivo con Copilot y el navegador integrado
36:46 Demostración de pruebas con Playwright
41:30 Configuración de agentes de sistema y perfiles
42:37 Gestión de memoria y retrieval en agentes
45:04 Funcionamiento de las Skills y carga de archivos
48:17 Prueba práctica: Generación de contenido con Skills y búsqueda online
51:20 Ciclo de vida y borrado de Skills
53:18 Implementación de comandos en chat: El desafío de stop
56:30 Conclusiones y próximos pasos (Despliegue)
#microsoftreactor #learnconnectbuild
[eventID:26926] OpenClawNet - Automatización + Azure + Foundry](https://i.ytimg.com/vi/BY94TELQv7o/mqdefault.jpg)
![Agent Framework Office Hours - June 24, 2026
These 60-minute live office hours are where you can connect with the Agent Framework team to get your questions answered live.
Find our past episodes on demand at: https://aka.ms/MAFOfficeHoursRecordings
[eventID:24346] Agent Framework Office Hours - June 24, 2026](https://i.ytimg.com/vi/Bf-gBmt75i0/mqdefault.jpg)
![Fundamentos de DevOps en la Era de AI y Agentes
En esta sesión, desglosaremos por qué los fundamentos y herramientas sólidas de DevOps son aún más importantes a medida que los agentes de programación y operaciones impulsados por IA se convierten en parte de los flujos de trabajo cotidianos. Verás cómo los agentes de desarrollo de IA modernos, como GitHub Copilot Cloud Agent y los agentes de operaciones de IA como el agente de Azure SRE pueden acelerar drásticamente la entrega cuando tus pipelines, pruebas y entornos están diseñados para soportarlos. Nos centraremos en lo que los desarrolladores deben tener implementado para integrar de manera segura y efectiva estos agentes en flujos de trabajo de CI/CD del mundo real, sin sacrificar la calidad, confiabilidad o control.
#microsoftreactor #learnconnectbuild
[eventID:27332] Fundamentos de DevOps en la Era de AI y Agentes](https://i.ytimg.com/vi/BgAvSKL9XaA/mqdefault.jpg)
![Production-Ready AI Systems: Security, Evaluation & Data Platforms
Modern AI systems require more than powerful models—they require security, evaluation, governance, and continuous improvement. This session combines lessons from production AI agent security with real-world LLM evaluation and fine-tuning workflows.
Topics may include prompt injection, tool abuse, memory poisoning, defense-in-depth architectures, custom evaluation frameworks, Azure OpenAI fine- tuning, and practical engineering lessons learned from deploying AI-powered systems.
Key Takeaways:
- Understand security challenges in AI agents
- Learn practical defense patterns for production AI
- Explore LLM evaluation methodologies
- Understand fine-tuning workflows using Azure OpenAI
- Apply production engineering best practices to AI systems
📌 This is part of a series, learn more here: https://aka.ms/ProdReadySystems/series
00:00 Intro & Housekeeping
01:50 Securing the AI Stack: Why AI Security Matters
05:00 The Four-Layer AI Security Framework
06:48 Layer 1: Model Security (Prompt Injection, Jailbreaks & Output Hijacking)
10:55 Layer 2: Agent & Application Security
14:09 Layer 3: MCP & Tool Security Risks
16:06 Layer 4: Infrastructure Security Essentials
17:57 Defense in Depth & Security Checklist
19:42 Resources & Final Takeaways on AI Security
20:43 LLM-Driven Merge Conflict Resolution Introduction
22:21 Why Merge Conflicts Are Still a Major Developer Challenge
28:23 Fine-Tuning LLMs for Merge Conflict Resolution
29:40 Key Fine-Tuning Insights & Lessons Learned
33:31 Evaluating Merge Resolution Models
34:42 Python Tips, Structured Outputs & Development Best Practices
39:00 Handling Large Files & Token Limits
40:46 Q&A Transition
42:07 Agent Security in Practice: Real-World Risks & Attacks
43:26 Hugging Face Security Incident Case Study
47:44 OWASP Top Risks for LLM Applications
54:05 Live Demo: Testing & Defending Against Prompt Injection
56:17 Excessive Permissions, Data Exposure & Supply Chain Risks
59:30 Token Abuse, Rate Limiting & Secure Agent Design
01:01:09 Evaluations, Red Teaming & Reliability Testing
01:03:09 Slides, Q&A & Resources
01:03:46 Closing Remarks & Event Survey
[eventID:27335] Production-Ready AI Systems: Security, Evaluation & Data Platforms](https://i.ytimg.com/vi/Bo0XKu7bZ54/mqdefault.jpg)
![Model Mondays - Spotlight On: MAI Models
At Microsoft Build, we announced a family of seven new models developed in-house at Microsoft AI. These models form a new multimodal ecosystem designed to work across a variety of real-world tasks - with models to support image, voice, transcription, coding, and reasoning.
Join us as we talk to the Microsoft AI models team about whats new in the MAI family, how this works under the hood, and what we can do to use them more effectively for building AI agents.
🔎 Explore the resources: https://aka.ms/model-mondays
📢 Continue the conversation on the Discord: https://aka.ms/model-mondays/discord
📖 Read the Newsletter: https://aka.ms/model-mondays/newsletter
📌 This session is a part of a series! Learn more here: https://aka.ms/model-mondays/rsvp
00:00 Welcome & Stream Introduction
01:05 Model Mondays Returns: Microsoft AI Models Spotlight
03:10 Microsoft AI Vision: Token Efficiency & Trustworthy Models
07:11 How MAI Models Power Microsoft Products and Foundry
11:01 Hill Climbing, Reinforcement Learning & Excel Agent Training
17:20 Building MAI Code Models for GitHub Copilot
22:17 Live Demo: Generating a Web App from Scratch
24:08 Enhancing Existing Apps with AI Coding Assistance
30:10 Sneak Peek: Native Image Understanding in MAI Code 1.1 Flash
34:14 Exploring MAI Image Models, Character Consistency & Latest AI News
54:18 Wrap-Up and Next Weeks Cohere Models Preview
#MSFTReactor #learnconnectbuild
[eventID:27393] Model Mondays - Spotlight On: MAI Models](https://i.ytimg.com/vi/C7SUG4s7aLo/mqdefault.jpg)

![Certifícate SQL+AI (DP-800): Diseña y Desarrolla Soluciones SQL como un Profesional
Esta sesión se centra en la parte de “construir” del DP-800: cómo diseñar y desarrollar soluciones de bases de datos que funcionen en cargas reales y que estén alineadas con lo que evalúa el examen. Recorreremos las habilidades clave del desarrollador, desde elegir los objetos y patrones correctos hasta escribir SQL sólido y mantenible.
💡 Esta sesión es parte de una serie—aprende más: https://aka.ms/datadayslive/sp-y
0:00 Welcome & Introduction
1:50 Meet the Speakers
3:45 Data Days, Certifications & Community Resources
8:49 DP-800 Exam Overview
14:45 Database Design & SQL Platforms
25:30 SQL Programmability Objects (Views, Stored Procedures, Functions & Triggers)
39:47 Advanced SQL Development (CTEs, Window Functions, JSON & Graphs)
46:41 AI-Assisted SQL Development (GitHub Copilot, Fabric Copilot & MCP)
58:43 DP-800 Exam Preparation Tips & Key Takeaways
1:02:04 Feedback Survey & Closing Remarks
[eventID:27403] Certifícate SQL+AI (DP-800): Diseña y Desarrolla Soluciones SQL como un Profesional](https://i.ytimg.com/vi/CPJB_-ZbRZo/mqdefault.jpg)

