Uploaded September 2026 | Updated November 2026, 3 hours ago
세션 소개
AI는 소프트웨어 개발 방식을 빠르게 바꾸고 있습니다. 개발자는 AI와 함께 협업하며 코드를 작성하고, 반복 작업을 줄이며, 개발 속도를 높이고 있습니다.
이번 세션에서는 GitHub Copilot이 지원하는 새로운 AI-Native 개발 워크플로우를 실시간 데모와 함께 살펴봅니다.
이슈 관리부터 코드 작성, 변경 사항 검토, Pull Request 생성까지 AI와 함께 개발하는 과정을 직접 확인하며, 아이디어를 실제 코드로 구현하는 과정을 더욱 빠르고 효율적으로 만드는 방법을 소개합니다.
세션에서는 이런 내용을 다룹니다
- AI-Native 개발 방식이 가져온 소프트웨어 개발의 변화
- GitHub Copilot을 활용한 이슈 관리, 코드 작성, Pull Request 워크플로우
- AI를 활용해 코드 작성과 반복 개발을 더욱 빠르게 수행하는 방법
- 개발 전 과정에서 AI와 효과적으로 협업한 사례
주요 기술
- GitHub Copilot App
- GitHub Copilot (Chat & CLI)
- AI-Native 개발 워크플로우
- Cloud 및 Local Sandbox
- AI 기반 코드 생성 및 반복 개발
추천 대상
- AI-Native 개발 방식을 도입하고 싶은 개발자
- GitHub Copilot을 개발 업무에 활용하고 있는 엔지니어
- AI를 활용해 개발 생산성을 높이고 싶은 소프트웨어 개발자
- 최신 AI 기반 개발 경험에 관심 있는 모든 개발자
0:02:53 오프닝 및 세션 소개
0:03:32 AI 네이티브 개발 워크플로우 개요
0:06:08 에이전트 기반 엔지니어링 시스템 이해
0:14:16 AI 활용과 개발 생산성 및 신뢰성 이슈
0:18:35 실습을 위한 준비 및 프로젝트 환경 설정
0:21:05 AI 네이티브 코딩을 위한 5가지 기본 규칙
0:30:12 이슈 기반 AI 에이전트 활용 데모
0:43:36 풀 리퀘스트 검토 및 코드 리뷰
0:54:36 고급 활용: 스쿼드(Squad) 및 플릿(Fleet) 컨셉
1:04:18 실제 사례: 팀즈 메시지 기반 이슈 생성
1:07:53 Q&A 및 마무리
[eventID:27479]
세션 소개
AI는 소프트웨어 개발 방식을 빠르게 바꾸고 있습니다. 개발자는 AI와 함께 협업하며 코드를 작성하고, 반복 작업을 줄이며, 개발 속도를 높이고 있습니다.
이번 세션에서는 GitHub Copilot이 지원하는 새로운 AI-Native 개발 워크플로우를 실시간 데모와 함께 살펴봅니다.
이슈 관리부터 코드 작성, 변경 사항 검토, Pull Request 생성까지 AI와 함께 개발하는 과정을 직접 확인하며, 아이디어를 실제 코드로 구현하는 과정을 더욱 빠르고 효율적으로 만드는 방법을 소개합니다.
세션에서는 이런 내용을 다룹니다
- AI-Native 개발 방식이 가져온 소프트웨어 개발의 변화
- GitHub Copilot을 활용한 이슈 관리, 코드 작성, Pull Request 워크플로우
- AI를 활용해 코드 작성과 반복 개발을 더욱 빠르게 수행하는 방법
- 개발 전 과정에서 AI와 효과적으로 협업한 사례
주요 기술
- GitHub Copilot App
- GitHub Copilot (Chat & CLI)
- AI-Native 개발 워크플로우
- Cloud 및 Local Sandbox
- AI 기반 코드 생성 및 반복 개발
추천 대상
- AI-Native 개발 방식을 도입하고 싶은 개발자
- GitHub Copilot을 개발 업무에 활용하고 있는 엔지니어
- AI를 활용해 개발 생산성을 높이고 싶은 소프트웨어 개발자
- 최신 AI 기반 개발 경험에 관심 있는 모든 개발자
0:02:53 오프닝 및 세션 소개
0:03:32 AI 네이티브 개발 워크플로우 개요
0:06:08 에이전트 기반 엔지니어링 시스템 이해
0:14:16 AI 활용과 개발 생산성 및 신뢰성 이슈
0:18:35 실습을 위한 준비 및 프로젝트 환경 설정
0:21:05 AI 네이티브 코딩을 위한 5가지 기본 규칙
0:30:12 이슈 기반 AI 에이전트 활용 데모
0:43:36 풀 리퀘스트 검토 및 코드 리뷰
0:54:36 고급 활용: 스쿼드(Squad) 및 플릿(Fleet) 컨셉
1:04:18 실제 사례: 팀즈 메시지 기반 이슈 생성
1:07:53 Q&A 및 마무리
[eventID:27479]
![AI Genius | Measure & Benchmark: Azure AI Foundry, Continuous Evaluation and IQ
Great AI workflows are not built on intuition alone.
Learn how to leverage Azure AI Foundry, automated evaluations, and Intelligence Quality (IQ) practices to assess model performance, reliability, and business impact.
Discover how continuous evaluation loops help teams optimize quality, speed, and cost while deploying AI solutions with confidence.
📌 This session is part of a series. Explore the full series here: https://aka.ms/AIGenius6/y
0:03:42 Introduction to AI Genius
0:04:34 Six Important Principles for Agent Development
0:07:56 Model Choice and Considerations
0:13:20 Grounding Your Agent with Microsoft IQs
0:23:48 Observability and Seeing Inside the Agent
0:28:58 Automated Evaluations
0:40:15 Agent Optimizer
0:49:46 Continuous Evaluation and CI/CD Pipelines
[eventID:27640] AI Genius | Measure & Benchmark: Azure AI Foundry, Continuous Evaluation and IQ](https://i.ytimg.com/vi/X9st3vAem0I/mqdefault.jpg)
![Ship with AI: Review, Secure, and Deploy with Confidence
Building software is only part of the journey. Delivering secure, reliable applications at scale requires confidence across the entire development lifecycle.
In this session, youll learn how to bring AI into real team workflows, from code review and security validation to CI/CD and automated merging. Through live demonstrations, youll see how AI helps improve quality, strengthen security, and maintain consistency across every stage of development, enabling teams to confidently ship AI-powered and agent-driven systems.
You Will Learn
• How AI enhances code review and development quality
• How to incorporate AI into security and compliance workflows
• How to automate deployment processes using modern CI/CD practices
• How to confidently ship AI-powered applications at scale
Technologies Used
• GitHub Copilot Code Review
• Agent Merge
• GitHub Actions (CI/CD)
• AI-assisted security review
• End-to-end development lifecycle automation
Who Should Attend
• Developers responsible for code quality and deployment
• DevOps and platform engineers managing CI/CD workflows
• Engineering teams building AI-powered applications
• Anyone interested in using AI to review, secure, and ship software with confidence
0:00:00 - Introduction and housekeeping
0:02:26 - Speaker introduction and session overview
0:04:42 - The AI trust and security gap
0:05:38 - Supply chain risks and OASP concerns
0:07:31 - Best practices: Introducing patch delays
0:09:28 - Hardening CI/CD pipelines
0:10:11 - High-profile security incidents (SolarWinds, Log4j)
0:12:25 - Mapping the AI-assisted pipeline
0:13:16 - Demo: Feature request and workflow automation
0:17:15 - Walkthrough of the demonstration sequence
0:20:14 - Live demo: GitHub repository and site setup
0:24:00 - Creating an issue and using GitHub Copilot
0:31:00 - Configuring Agent Merge and reviewing changes
0:40:02 - Reviewing AI-generated code and security findings
0:45:18 - Enabling security settings and Advanced Security
0:47:35 - Debugging failed pipeline deployments
0:48:46 - Using Dependabot for dependency updates
0:52:13 - Validating successful deployment and site update
0:53:50 - Final overview of security changes and workflow permissions
0:56:07 - Summary of key takeaways and next steps
0:57:33 - Resources, feedback, and certifications
[eventID:27465] Ship with AI: Review, Secure, and Deploy with Confidence](https://i.ytimg.com/vi/XaoojoTQHJc/mqdefault.jpg)
![Fabric Apps en acción: mira lo que creó la comunidad
La mejor manera de entender Fabric Apps es ver lo que las personas están creando con ellas.
Miembros de la comunidad compartirán sus apps, los problemas que intentaban resolver, lo que funcionó y lo que aprendieron mientras las construían.
[eventID:27758] Fabric Apps en acción: mira lo que creó la comunidad](https://i.ytimg.com/vi/XbJgT_K9Dxs/mqdefault.jpg)
![Diseña y mejora tus procesos con Copilot: del proceso actual a una mejor forma de trabajar
Todos tenemos procesos que repetimos: preparar un reporte, gestionar una solicitud, atender un requerimiento o coordinar una actividad.
Pero antes de automatizar un proceso con IA, necesitamos entender cómo funciona y preguntarnos si realmente es la mejor forma de hacerlo. En esta sesión práctica utilizaremos Microsoft Copilot como compañero para analizar y rediseñar un proceso.
A partir de un caso sencillo, construiremos prompts que nos ayuden a identificar actividades, actores, información necesaria, puntos de fricción y oportunidades de mejora.
🔗 Aprende más accediendo a los recursos:
https://aka.ms/PromptAssitant
https://aka.ms/PromptGalleryLearn
📌 Este evento es parte de una serie, aprende más aquí: https://aka.ms/BuildWithCopilot/serie
0:00 Intro y bienvenida
0:48 Código de conducta
1:11 Introducción al tema: Diseñar y mejorar procesos con Copilot
2:07 Presentación de la ponente: Amal Vitori
3:13 ¿Qué es un proceso? Anatomía y componentes clave
6:37 Tabla periódica de elementos de un proceso bien documentado
10:12 7 pasos para crear o mejorar un proceso
12:12 Caso práctico: Elaboración de informe semanal
14:43 Introducción al estándar BPMN
16:27 Símbolos esenciales del modelado BPMN
18:03 Estrategia de prompts para modelar con Copilot
21:37 Guía paso a paso en Copilot: Práctica
25:12 Paso 1: Documentación del caso en Copilot
31:02 Paso 2: Diagnóstico de puntos de fricción
32:29 Paso 3: Rediseño del proceso
35:05 Paso 4: Creación del diagrama BPMN
37:21 Optimización: ¿Cómo puede ayudar un asistente?
48:47 Resumen del ejercicio realizado
51:17 Sesión de preguntas y cierre
#MicrosoftReactor #LearnConnectBuild #Copilot
[eventID:27607] Diseña y mejora tus procesos con Copilot: del proceso actual a una mejor forma de trabajar](https://i.ytimg.com/vi/XcAwu8SwyiE/mqdefault.jpg)
![Copilot Dev Camp Summit – Winter Edition 2026
Copilot Dev Camp Summit – Winter Edition 2026 is a global, community-driven event designed for developers and makers to explore the latest innovations in Microsoft 365 Copilot and extensibility.
Join us for a curated set of sessions, live demos, and real-world insights covering topics such as declarative agents, custom engines, and integration patterns—alongside inspiring stories from the community.
Whether youre building your first Copilot experience or scaling advanced scenarios, the Summit offers practical guidance, hands-on learning, and opportunities to connect with experts and peers worldwide.
Learn more about Copilot Dev Camp https://aka.ms/copilotdevcamp
[eventID:27483] Copilot Dev Camp Summit – Winter Edition 2026](https://i.ytimg.com/vi/YNq1l4k2_sc/mqdefault.jpg)
![Fabric Apps na prática: veja o que a comunidade criou
A melhor maneira de entender Fabric Apps é ver o que as pessoas estão criando com eles.
Membros da comunidade vão mostrar seus apps, os problemas que estavam tentando resolver, o que funcionou e o que aprenderam enquanto criavam.
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/ShowIt/y
#MIcrosoftReactor #LearnConnectBuild #Fabric #DataDays #AI
[eventID:27739] Fabric Apps na prática: veja o que a comunidade criou](https://i.ytimg.com/vi/YOi8Zky-xD0/mqdefault.jpg)
![Deployment Stacks: Azures Standard for Infrastructure as Code, Drift Detection, and Governance
Once an Azure environment is deployed, it rarely stays the way the code describes it: people change settings in the portal, delete resources by hand, and leave old resources running.
Deployment stacks are Azures standard for managing infrastructure as code across that lifecycle, with drift detection and governance built in.
I am a product manager at Microsoft on Azure Bicep and owning Deployment Stacks. Bicep is Azures native infrastructure as code language and a stateless alternative to Terraform, so there is no state file to store, secure, or keep in sync.
A deployment stack is a resource that manages a group of resources as a single unit across its lifecycle. In the demo I deploy an environment from Bicep as a deployment stack, then change a security rule and delete a resource in the portal. Stacks What-If with the same template lists those changes, and one more deployment puts the environment back. I then set deny settings so managed resources cannot be changed or deleted outside the stack, and choose whether resources removed from the template are detached or deleted.
When the environment is no longer needed, a single delete removes everything the stack manages. Everything runs live from the Azure CLI. The tools are Azure specific; the practices apply to any infrastructure as code workflow.
What attendees will learn:
- How a deployment stack manages an Azure environment as one unit, from the first deployment to the final delete.
- How to find drift with Stacks What-If and bring the environment back to what the code describes.
- How to govern changes with deny settings, and choose what happens to resources removed from the template.
[eventID:27816] Deployment Stacks: Azures Standard for Infrastructure as Code, Drift Detection, and Governance](https://i.ytimg.com/vi/YglQXrZjmL0/mqdefault.jpg)
![Replacing Azure Communication Services Without Rebuilding Your Application
In this webinar, youll learn what Infobip and Microsoft have prepared to make your ACS migration smooth - from signup and onboarding with Infobip, to configuring your connection points back to your Azure solution, all the way to sending your first message through Infobip instead of ACS. Along the way, youll see why Infobip is a natural next step for ACS customers: global reach, feature parity with what you rely on today, and a migration path built to minimize changes to your existing solution. Youll get a firsthand look at the tools available to help you prepare your solutions for a graceful migration away from ACS.
[eventID:27742] Replacing Azure Communication Services Without Rebuilding Your Application](https://i.ytimg.com/vi/_ZtcIMGIpkU/mqdefault.jpg)
![De datos sin procesar a datos preparados para IA: Spark en Fabric
La IA solo es útil si los datos que hay detrás también lo son.
En esta sesión, utilizaremos Spark en Fabric para tomar datos sin procesar, limpiarlos y transformarlos, y crear una base que una solución de IA o analytics pueda utilizar de verdad.
[eventID:27755] De datos sin procesar a datos preparados para IA: Spark en Fabric](https://i.ytimg.com/vi/_rNiSR-IUbg/mqdefault.jpg)
![From GitHub to GPU: Build an Open Source AI App with Copilot, Azure Linux, and AKS
What does it take to turn an AI idea into a real, scalable application without hiding the infrastructure behind a black box?
Well start with an open source GitHub repository and use GitHub Copilot to understand, adapt, and operate a complete AI workload. We deploy Ray and KubeRay on Azure Kubernetes Service (AKS), run LLM batch inference on an NVIDIA GPU, and explore how Azure Linux provides a lightweight, secure container host for the Kubernetes nodes under the hood.
Along the way, well connect the layers that make the application work using containers, Kubernetes resources, GPU scheduling, and open source operators.
Well also explore autoscaling, network isolation, authentication, metrics, dashboards, and cost-aware management. Leave with a reusable GitHub repo and a clear roadmap for building open source AI systems on Azure.
🔗 Learn more by exploring the resources: https://aka.ms/MicrosoftAzureOpenSourceBlog
📌 This event is part of a series. Learn more here: https://aka.ms/AIwithOpenSourceSeries/y
0:00 Introduction and housekeeping
0:50 Welcome and overview of the AI stack
3:14 Project repository and dashboard introduction
5:34 How GitHub Copilot was used to build the app
14:16 What is Ray and why use it on Kubernetes?
16:37 Intro to KubeRay and GPU scheduling
19:12 Building the platform with AKS and T4 GPUs
23:25 Anatomy of a GPU Ray cluster
26:22 Running GPU tests: Interactive vs. Declarative
27:54 Demo: VS Code dashboard and live inference
34:25 Understanding autoscaling layers
40:50 Metrics, observability, and dashboard breakdown
43:40 Network security and access policies
46:27 Authentication with cluster tokens
48:26 Gotchas and challenges from the POC
49:26 Cost awareness and billing tips
52:05 Summary of known issues and roadmap
55:12 Final roadmap to production
#MicrosoftReactor #LearnConnectBuild #OpenSource #Linux #Kubernetes #AIapps
[eventID:27664] From GitHub to GPU: Build an Open Source AI App with Copilot, Azure Linux, and AKS](https://i.ytimg.com/vi/_uybxmIaQiw/mqdefault.jpg)
![AI @Work: Community Builders in Action
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.
📌 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:27725] AI @Work: Community Builders in Action](https://i.ytimg.com/vi/aDFvcZGlCSk/mqdefault.jpg)