AI Apps & Agents Dev Days

加入 Microsoft Reactor 并实时与开发人员互动

准备好开始使用 AI 和最新技术了吗？ Microsoft Reactor 提供活动、培训和社区资源，帮助开发人员、企业家和初创公司利用 AI 技术等。 快加入我们吧！

AI Apps & Agents Dev Days

加入 Microsoft Reactor 并实时与开发人员互动

准备好开始使用 AI 和最新技术了吗？ Microsoft Reactor 提供活动、培训和社区资源，帮助开发人员、企业家和初创公司利用 AI 技术等。 快加入我们吧！

返回

AI Apps & Agents Dev Days

  • 形式:
  • alt##Livestream直播

主题: 适用于 AI 的基础结构, 代理

语言: 英语

  • 此系列中的活动:
  • 15

Brought to you by Microsoft and NVIDIA

Step into a builder’s playground where ideas turn into working AI experiences. AI Apps & Agents Dev Days​ isn’t about slides, it’s about building. Each month, we tackle real-world challenges, share patterns that work, and experiment with what’s next in AI-driven apps and agent design. Bring your curiosity, your code, and your questions. Leave with something you can show off, and a reason to come back for more.​

即将举办的活动

单击下面的活动以了解详细信息并注册各个活动。

所有时间采用 - 协调世界时

1月

22

星期四

2026

Build a Deep Research Agent for Enterprise Data with Scalable Performance

5:00 下午 - 6:00 下午 (UTC)

Brought to you by Microsoft and NVIDIA Move beyond foundational concepts and dive into production-grade deployment of enterprise research agents. This session explores advanced architecture patterns for scaling NVIDIA AI-Q Blueprints and Nemotron models on Azure Kubernetes Services (AKS), focusing on real-world optimization strategies, performance tuning, and operational best practices. Learn how to leverage NVIDIA NIM microservices alongside Nemotron's open-source models to build intelligent agents that reason across complex enterprise data, with practical insights on cost optimization, reliability, and multi-agent orchestration in Kubernetes environments

  • 形式:
  • alt##Livestream直播

主题: 适用于 AI 的基础结构

语言: 英语

详细信息

1月

23

星期五

2026

Build a Deep Research Agent for Enterprise Data with Scalable Performance

2:00 上午 - 3:00 上午 (UTC)

Brought to you by Microsoft and NVIDIA Move beyond foundational concepts and dive into production-grade deployment of enterprise research agents. This session explores advanced architecture patterns for scaling NVIDIA AI-Q Blueprints and Nemotron models on Azure Kubernetes Services (AKS), focusing on real-world optimization strategies, performance tuning, and operational best practices. Learn how to leverage NVIDIA NIM microservices alongside Nemotron's open-source models to build intelligent agents that reason across complex enterprise data, with practical insights on cost optimization, reliability, and multi-agent orchestration in Kubernetes environments

  • 形式:
  • alt##Livestream直播

主题: 适用于 AI 的基础结构

语言: 英语

详细信息

2月

10

星期二

2026

Build a Voice-Enabled AI Agent in Minutes

5:00 下午 - 6:00 下午 (UTC)

Brought to you by Microsoft & NVIDIA Join us and learn how to build a production‑ready, voice‑enabled AI agent with GitHub Copilot and Microsoft Foundry, showcased through a hands‑on demo. Upgrade a Python podcast‑editing app using NVIDIA Parakeet for high‑accuracy local ASR and NVIDIA Nemotron on Azure for concise summaries, titles, and structured outputs. We’ll share proven patterns for model selection, evaluation, chaining, orchestration, responsible guardrails, and automated DevOps deployment—plus the developer metrics that matter (latency, throughput, errors, memory and GPU usage)—so you leave with a reusable blueprint for real applications.

  • 形式:
  • alt##Livestream直播

主题: 代理

语言: 英语

详细信息

2月

11

星期三

2026

Build a Voice-Enabled AI Agent in Minutes

2:00 上午 - 3:00 上午 (UTC)

Brought to you by Microsoft and NVIDIA Join us and learn how to build a production‑ready, voice‑enabled AI agent with GitHub Copilot and Microsoft Foundry, showcased through a hands‑on demo. Upgrade a Python podcast‑editing app using NVIDIA Parakeet for high‑accuracy local ASR and NVIDIA Nemotron on Azure for concise summaries, titles, and structured outputs. We'll share proven patterns for model selection, evaluation, chaining, orchestration, responsible guardrails, and automated DevOps deployment---plus the developer metrics that matter (latency, throughput, errors, memory and GPU usage)---so you leave with a reusable blueprint for real applications.

  • 形式:
  • alt##Livestream直播

主题: 适用于 AI 的基础结构

语言: 英语

详细信息

3月

11

星期三

2026

Coordinating Secure GPU-Accelerated Agents with Foundry Control Plane on Azure

4:00 下午 - 5:00 下午 (UTC)

Brought to you by Microsoft and NVIDIA Coordinating Secure GPU-Accelerated Agents with Foundry Control Plane on Azure GPU-accelerated agents enable advanced AI workflows, but coordinating them securely and reliably requires clear separation between control and execution. In this joint session, Microsoft and NVIDIA present a hybrid multi-agent architecture where Foundry Agent Service coordinates GPU-backed agents running on Azure Container Apps. Using a document processing scenario with multiple open-source models including NVIDIA Nemotron models, we show how Foundry agents route requests, apply security controls, and monitor execution across GPU workloads, producing consistent and explainable results suitable for production environments. 🔔 This session will be presented in two time zones. For our later stream, click here

  • 形式:
  • alt##Livestream直播

主题: 适用于 AI 的基础结构

语言: 英语

详细信息

3月

12

星期四

2026

Coordinating Secure GPU-Accelerated Agents with Foundry Control Plane on Azure

1:00 上午 - 2:00 上午 (UTC)

Brought to you by Microsoft and NVIDIA Coordinating Secure GPU-Accelerated Agents with Foundry Control Plane on Azure GPU-accelerated agents enable advanced AI workflows, but coordinating them securely and reliably requires clear separation between control and execution. In this joint session, Microsoft and NVIDIA present a hybrid multi-agent architecture where Foundry Agent Service coordinates GPU-backed agents running on Azure Container Apps. Using a document processing scenario with multiple open-source models including NVIDIA Nemotron models, we show how Foundry agents route requests, apply security controls, and monitor execution across GPU workloads, producing consistent and explainable results suitable for production environments. 🔔 This session will be presented in two time zones. For our earlier stream, click here

  • 形式:
  • alt##Livestream直播

主题: 适用于 AI 的基础结构

语言: 英语

详细信息

主讲人

  • Anton Slutsky

    • Solutions Architect - CSP GTM

    NVIDIA

  • Diego Casati

    • Principal Solution Engineer

    Microsoft

  • Harmke Alkemade

    • Solutions Architect

    NVIDIA

  • Bruno Capuano

    • Principal Cloud Advocate

    Microsoft

  • Don Chouinard

    • AI Product & Marketing Leader

    NVIDIA

  • Brian Benz

    • Principal Cloud Advocate

    Microsoft

  • Pamela Fox

    • Principal Cloud Advocate in Python

    Microsoft

  • Stephen McCullough

    • Solutions Architect – Cloud AI

    NVIDIA

  • Anthony Shaw

    • Python Advocacy Lead

    Microsoft

  • Gwyneth Peña-Siguenza

    • Cloud Advocate

    Microsoft

此系列中的过去活动

所有时间采用 - 协调世界时

10月

20

星期一

2025

Run open models on Serverless GPUs (EMEA)

4:00 下午 - 5:00 下午 (UTC)

Brought to you by Microsoft and NVIDIA​ ​ Join this live session to learn how to deploy OpenAI’s GPT-OSS models on serverless GPUs using NVIDIA NIM. We’ll show how to spin up gpt-oss on demand and demonstrate scenarios that use its reasoning and tool-calling abilities. Learn how NVIDIA NIM simplifies the journey from experimentation to deploying enterprise AI applications on Azure Container Apps, with pre-optimized models and industry-standard APIs. Discover how to scale open models efficiently while unlocking new agentic workflows.

  • 形式:
  • alt##Livestream直播

主题: 适用于 AI 的基础结构

语言: 英语

观看点播

10月

21

星期二

2025

Run open models on Serverless GPUs (AMER)

8:00 下午 - 9:00 下午 (UTC)

Brought to you by Microsoft and NVIDIA​ ​ Join this live session to learn how to deploy OpenAI’s GPT-OSS models on serverless GPUs using NVIDIA NIM. We’ll show how to spin up gpt-oss on demand and demonstrate scenarios that use its reasoning and tool-calling abilities. Learn how NVIDIA NIM simplifies the journey from experimentation to deploying enterprise AI applications on Azure Container Apps, with pre-optimized models and industry-standard APIs. Discover how to scale open models efficiently while unlocking new agentic workflows.

  • 形式:
  • alt##Livestream直播

主题: 适用于 AI 的基础结构

语言: 英语

观看点播

10月

22

星期三

2025

Run open models on Serverless GPUs (APAC)

4:00 上午 - 5:00 上午 (UTC)

Brought to you by Microsoft and NVIDIA​ ​ Join this live session to learn how to deploy OpenAI’s GPT-OSS models on serverless GPUs using NVIDIA NIM. We’ll show how to spin up gpt-oss on demand and demonstrate scenarios that use its reasoning and tool-calling abilities. Learn how NVIDIA NIM simplifies the journey from experimentation to deploying enterprise AI applications on Azure Container Apps, with pre-optimized models and industry-standard APIs. Discover how to scale open models efficiently while unlocking new agentic workflows.

  • 形式:
  • alt##Livestream直播

主题: 适用于 AI 的基础结构

语言: 英语

观看点播

11月

11

星期二

2025

Accelerating AI model performance (EMEA)

6:00 下午 - 7:00 下午 (UTC)

Join this live session to explore what drives performance in modern AI systems with experts from Microsoft and NVIDIA. We’ll break down how latency and throughput shape responsiveness in large language models and share techniques you can use to improve performance. Learn how hardware, batching, model size, and inference optimizations affect system efficiency, and see benchmarking in action across different configurations in Azure. Discover how to unlock new levels of model performance through advanced infrastructure from Azure and NVIDIA.

  • 形式:
  • alt##Livestream直播

主题: 适用于 AI 的基础结构

语言: 英语

观看点播

11月

13

星期四

2025

Accelerating AI model performance (AMER)

12:00 上午 - 1:00 上午 (UTC)

Join this live session to explore what drives performance in modern AI systems with experts from Microsoft and NVIDIA. We’ll break down how latency and throughput shape responsiveness in large language models and share techniques you can use to improve performance. Learn how hardware, batching, model size, and inference optimizations affect system efficiency, and see benchmarking in action across different configurations in Azure. Discover how to unlock new levels of model performance through advanced infrastructure from Azure and NVIDIA.

  • 形式:
  • alt##Livestream直播

主题: 适用于 AI 的基础结构

语言: 英语

观看点播

11月

13

星期四

2025

Accelerating AI Model Performance (APAC)

4:00 上午 - 5:00 上午 (UTC)

Join this live session to explore what drives performance in modern AI systems with experts from Microsoft and NVIDIA. We’ll break down how latency and throughput shape responsiveness in large language models and share techniques you can use to improve performance. Learn how hardware, batching, model size, and inference optimizations affect system efficiency, and see benchmarking in action across different configurations in Azure. Discover how to unlock new levels of model performance through advanced infrastructure from Azure and NVIDIA.

  • 形式:
  • alt##Livestream直播

主题: 适用于 AI 的基础结构

语言: 英语

观看点播

12月

16

星期二

2025

Scale and Orchestrate Multi-Agent Systems Effortlessly (EMEA)

4:00 下午 - 5:00 下午 (UTC)

Explore how to leverage multi-agent systems in your applications to optimize operations, automate recommendations, and enhance customer experience. The solution utilizes Microsoft Agent Framework, OpenAI ChatKit and NVIDIA Nemotron model on Microsoft Foundry to seamlessly connect with store databases, integrate human oversight, and deploy scalable chat agents. This approach enables real-time analytics, predictive insights, and personalized interactions, resulting in improved decision-making, operational efficiency, and a superior user experience for both application developers and users.

  • 形式:
  • alt##Livestream直播

主题: 适用于 AI 的基础结构

语言: 英语

观看点播

12月

16

星期二

2025

Scale and Orchestrate Multi-Agent Systems Effortlessly (APAC)

11:00 下午 - 12:00 上午 (UTC)

Explore how to leverage multi-agent systems in your applications to optimize operations, automate recommendations, and enhance customer experience. The solution utilizes Microsoft Agent Framework, OpenAI ChatKit and NVIDIA Nemotron model on Microsoft Foundry to seamlessly connect with store databases, integrate human oversight, and deploy scalable chat agents. This approach enables real-time analytics, predictive insights, and personalized interactions, resulting in improved decision-making, operational efficiency, and a superior user experience for both application developers and users.

  • 形式:
  • alt##Livestream直播

主题: 适用于 AI 的基础结构

语言: 英语

观看点播

12月

18

星期四

2025

Scale and Orchestrate Multi-Agent Systems Effortlessly (AMER)

5:00 下午 - 6:00 下午 (UTC)

Explore how to leverage multi-agent systems in your applications to optimize operations, automate recommendations, and enhance customer experience. The solution utilizes Microsoft Agent Framework, OpenAI ChatKit and NVIDIA Nemotron model on Microsoft Foundry to seamlessly connect with store databases, integrate human oversight, and deploy scalable chat agents. This approach enables real-time analytics, predictive insights, and personalized interactions, resulting in improved decision-making, operational efficiency, and a superior user experience for both application developers and users.

  • 形式:
  • alt##Livestream直播

主题: 适用于 AI 的基础结构

语言: 英语

观看点播

此系列中的过去活动

所有时间采用 - 协调世界时

10月

20

星期一

2025

Run open models on Serverless GPUs (EMEA)

4:00 下午 - 5:00 下午 (UTC)

Brought to you by Microsoft and NVIDIA​ ​ Join this live session to learn how to deploy OpenAI’s GPT-OSS models on serverless GPUs using NVIDIA NIM. We’ll show how to spin up gpt-oss on demand and demonstrate scenarios that use its reasoning and tool-calling abilities. Learn how NVIDIA NIM simplifies the journey from experimentation to deploying enterprise AI applications on Azure Container Apps, with pre-optimized models and industry-standard APIs. Discover how to scale open models efficiently while unlocking new agentic workflows.

  • 形式:
  • alt##Livestream直播

主题: 适用于 AI 的基础结构

语言: 英语

观看点播

10月

21

星期二

2025

Run open models on Serverless GPUs (AMER)

8:00 下午 - 9:00 下午 (UTC)

Brought to you by Microsoft and NVIDIA​ ​ Join this live session to learn how to deploy OpenAI’s GPT-OSS models on serverless GPUs using NVIDIA NIM. We’ll show how to spin up gpt-oss on demand and demonstrate scenarios that use its reasoning and tool-calling abilities. Learn how NVIDIA NIM simplifies the journey from experimentation to deploying enterprise AI applications on Azure Container Apps, with pre-optimized models and industry-standard APIs. Discover how to scale open models efficiently while unlocking new agentic workflows.

  • 形式:
  • alt##Livestream直播

主题: 适用于 AI 的基础结构

语言: 英语

观看点播

10月

22

星期三

2025

Run open models on Serverless GPUs (APAC)

4:00 上午 - 5:00 上午 (UTC)

Brought to you by Microsoft and NVIDIA​ ​ Join this live session to learn how to deploy OpenAI’s GPT-OSS models on serverless GPUs using NVIDIA NIM. We’ll show how to spin up gpt-oss on demand and demonstrate scenarios that use its reasoning and tool-calling abilities. Learn how NVIDIA NIM simplifies the journey from experimentation to deploying enterprise AI applications on Azure Container Apps, with pre-optimized models and industry-standard APIs. Discover how to scale open models efficiently while unlocking new agentic workflows.

  • 形式:
  • alt##Livestream直播

主题: 适用于 AI 的基础结构

语言: 英语

观看点播

11月

11

星期二

2025

Accelerating AI model performance (EMEA)

6:00 下午 - 7:00 下午 (UTC)

Join this live session to explore what drives performance in modern AI systems with experts from Microsoft and NVIDIA. We’ll break down how latency and throughput shape responsiveness in large language models and share techniques you can use to improve performance. Learn how hardware, batching, model size, and inference optimizations affect system efficiency, and see benchmarking in action across different configurations in Azure. Discover how to unlock new levels of model performance through advanced infrastructure from Azure and NVIDIA.

  • 形式:
  • alt##Livestream直播

主题: 适用于 AI 的基础结构

语言: 英语

观看点播

11月

13

星期四

2025

Accelerating AI model performance (AMER)

12:00 上午 - 1:00 上午 (UTC)

Join this live session to explore what drives performance in modern AI systems with experts from Microsoft and NVIDIA. We’ll break down how latency and throughput shape responsiveness in large language models and share techniques you can use to improve performance. Learn how hardware, batching, model size, and inference optimizations affect system efficiency, and see benchmarking in action across different configurations in Azure. Discover how to unlock new levels of model performance through advanced infrastructure from Azure and NVIDIA.

  • 形式:
  • alt##Livestream直播

主题: 适用于 AI 的基础结构

语言: 英语

观看点播

11月

13

星期四

2025

Accelerating AI Model Performance (APAC)

4:00 上午 - 5:00 上午 (UTC)

Join this live session to explore what drives performance in modern AI systems with experts from Microsoft and NVIDIA. We’ll break down how latency and throughput shape responsiveness in large language models and share techniques you can use to improve performance. Learn how hardware, batching, model size, and inference optimizations affect system efficiency, and see benchmarking in action across different configurations in Azure. Discover how to unlock new levels of model performance through advanced infrastructure from Azure and NVIDIA.

  • 形式:
  • alt##Livestream直播

主题: 适用于 AI 的基础结构

语言: 英语

观看点播

12月

16

星期二

2025

Scale and Orchestrate Multi-Agent Systems Effortlessly (EMEA)

4:00 下午 - 5:00 下午 (UTC)

Explore how to leverage multi-agent systems in your applications to optimize operations, automate recommendations, and enhance customer experience. The solution utilizes Microsoft Agent Framework, OpenAI ChatKit and NVIDIA Nemotron model on Microsoft Foundry to seamlessly connect with store databases, integrate human oversight, and deploy scalable chat agents. This approach enables real-time analytics, predictive insights, and personalized interactions, resulting in improved decision-making, operational efficiency, and a superior user experience for both application developers and users.

  • 形式:
  • alt##Livestream直播

主题: 适用于 AI 的基础结构

语言: 英语

观看点播

12月

16

星期二

2025

Scale and Orchestrate Multi-Agent Systems Effortlessly (APAC)

11:00 下午 - 12:00 上午 (UTC)

Explore how to leverage multi-agent systems in your applications to optimize operations, automate recommendations, and enhance customer experience. The solution utilizes Microsoft Agent Framework, OpenAI ChatKit and NVIDIA Nemotron model on Microsoft Foundry to seamlessly connect with store databases, integrate human oversight, and deploy scalable chat agents. This approach enables real-time analytics, predictive insights, and personalized interactions, resulting in improved decision-making, operational efficiency, and a superior user experience for both application developers and users.

  • 形式:
  • alt##Livestream直播

主题: 适用于 AI 的基础结构

语言: 英语

观看点播

12月

18

星期四

2025

Scale and Orchestrate Multi-Agent Systems Effortlessly (AMER)

5:00 下午 - 6:00 下午 (UTC)

Explore how to leverage multi-agent systems in your applications to optimize operations, automate recommendations, and enhance customer experience. The solution utilizes Microsoft Agent Framework, OpenAI ChatKit and NVIDIA Nemotron model on Microsoft Foundry to seamlessly connect with store databases, integrate human oversight, and deploy scalable chat agents. This approach enables real-time analytics, predictive insights, and personalized interactions, resulting in improved decision-making, operational efficiency, and a superior user experience for both application developers and users.

  • 形式:
  • alt##Livestream直播

主题: 适用于 AI 的基础结构

语言: 英语

观看点播

本页面的部分内容可能是机器翻译或人工智能翻译.