Agent Kit Features & Benefits - Agent Kit helps developers create agents faster than ever before by visually wiring nodes instead of starting with code [1][3] - Agent Kit provides pre-built tools like file search, guard rails, and human-in-the-loop, enabling developers to model complex workflows easily [4] - Agent Kit allows for customization using widgets, enhancing the user experience beyond plain text [6][23] - Agent Kit includes pre-built guardrails for security, protecting against hallucinations and blocking PII [11][12] - Agent Kit facilitates testing and evaluation of agents directly from the builder to ensure expected behavior before deployment [16] Deployment & Integration - Agent Kit enables fully deployed and published agents in production with a workflow ID for direct execution [17] - Agent Kit offers code export for running agents in custom environments [17] - Agent Kit allows for easy integration into existing websites using components and visual customization [19][20] - Changes to agents can be deployed directly to the site without requiring code modifications [22] Use Case: Devday Website Agent - An agent powered by Agent Kit was built and deployed within the Devday website in under eight minutes to assist users in navigating the event [2][22]

AI Innovation & Urban Development - OpenAI Dev Day highlights real-world applications of AI in San Francisco, focusing on tools to solve urban issues [1] - San Francisco is positioned as a hub for AI innovation, with the city actively supporting AI development to improve daily life for residents [1] - AI is being used to create safer neighborhoods, faster city services, and better urban planning in San Francisco [1] - The City Science Lab is using AI to visualize and simulate future housing developments in San Francisco, aiming to address the housing crisis and promote informed civic discourse [15][18] Solve SF App - Solve SF is an app that allows users to report city issues by taking a photo, with AI automating the reporting process [1] - Solve SF utilizes GPT-5 to analyze photos and submit 311 reports, reducing the reporting process from 12 steps to two clicks [2] - The app has generated over 100,000 reports for San Francisco's 311 service, leading to city responses such as graffiti removal and trash cleanup [2] Voice Reach Platform - Voice Reach is a real-time outreach platform designed to help San Francisco's neighborhood street teams by using voice transcription to streamline data collection [2] - The platform uses OpenAI tools like Whisper and GPT-5 Nano to transcribe interactions and extract key details, centralizing data and improving care continuity [2][3] - Voice Reach was initially built in 36 hours by four college freshmen, demonstrating the potential for community-driven AI solutions [9] San Francisco's Progress & Economic Momentum - San Francisco reports a 30% decrease in crime and over 40% decrease in downtown crime, with car break-ins at two-decade lows [1] - The city has added nearly 400 new shelter beds this year, and the number of tents on the streets is down by a quarter since March [1] - There is more office space being leased than vacated, with AI companies expanding in San Francisco and global retailers opening new stores [1]

Agent Kit Overview - Introduces Agent Kit as a complete set of building blocks for building, deploying, and optimizing agentic workflows [1] - Agent Kit includes an agent builder for visually designing workflows, ChatKit for pre-built UI components, and updated evaluation and tracing patterns for monitoring and optimization [2][3][4] Agent Builder Features - Allows users to drag and drop nodes onto a canvas to visually design workflows [2] - Enables exporting workflows as code (JavaScript or Python) using the OpenAI Agents SDK for self-hosting [2][28] - Includes a node picker with LLMs, agent tools (like file search), and logical nodes (like while loops and if/else statements) [14] ChatKit Functionality - Provides pre-built UI components like chat interfaces, streaming, and customizable widgets for agentic workflows [3] - Simplifies UI development for complex dynamic workflows [6] - Supports features like streaming tokens, reasoning summaries, and widgets, even when self-hosting [34] Evaluation and Optimization - Offers tracing to monitor agent behavior, including agent order, duration, model details, and token usage [4][38] - Includes graders to evaluate workflow correctness and readability, with the ability to grade all workflows for a bird's eye view [39][42] - Provides a visual eval builder for optimizing individual agents, including editing prompts, adding tools, or changing the model [44][48] - Allows for automatic prompt optimization using ground truth data and grader results [51][52] Deployment and Self-Hosting - Enables deployment to OpenAI's cloud without managing servers [26][54] - Supports self-hosting by implementing the chat protocol and exporting workflows as code [26][27] - Allows switching to local tools and backends for accessing data within private clouds [30][31] Use Case: Semi-Truck Maintenance - Demonstrates a use case for a semi-truck manufacturer handling maintenance inquiries with an agentic workflow [4] - The workflow retrieves relevant maintenance procedures, identifies necessary parts, and provides instructions to maintenance engineers [9][10] - Shows how to tweak workflows, add widgets, and change prompts for improved output and user experience [13][18]

AI Coding Evolution - 软件开发正经历从终端到图形界面，再到AI辅助的快速演变 [1][2][3][4] - Cursor 旨在通过AI 自动化编码流程，重点在于模型和人机交互 [46] - Cursor 的目标是让工程师更专注于解决难题、设计系统和创造有价值的产品 [47][49] Context Engineering & Coding Agents - Context Engineering 关注于为模型提供高质量和有针对性的上下文信息，而非仅仅依赖 Prompt 技巧 [16][17] - Semantic Search 通过自动索引代码库并创建嵌入，提升代码搜索的准确性和效率 [19][20] - Semantic Search 将计算密集型任务转移到离线索引阶段，从而在运行时获得更快、更经济的响应 [22] - Cursor 发现用户更倾向于使用 GP 和 Semantic Search 相结合的方式，以获得最佳效果 [22] Cursor's Products & Features - Tab 功能每天处理超过 4 亿次请求，通过在线强化学习优化代码建议 [7] - Cursor 正在探索多种 Coding Agents 的管理界面，包括并行运行和模型竞争 [38][39][42][43] - Cursor 正在探索为 Agent 提供计算机使用权限，以便运行代码、测试并验证其正确性 [44] - Cursor 允许用户通过自定义命令和规则，共享 Prompt 和上下文信息，实现团队协作 [32][33]

[Music] [Music] Heat. [Music] Heat. Heat. Heat.[Music] [Music]. ...

Hey everyone, this is Christina from OpenAI. Welcome to Agent Builder 101. Agent Builder is a new visual tool for building AI workflows.You connect nodes and create agents without writing any code. So you can start from templates or build your own from scratch. And it also comes with built-in eval so you can test and understand how your agents perform.When you're ready, you can export the workflow as code or drop it straight into your product. Basically, it's your all-in-one space to design, test, and launc ...

Event Announcement - Sam Altman 在 DevDay 2025 上发表主题演讲，探讨挑战构建方式的理念 [1] - DevDay 2025 将发布公告、现场演示以及开发者利用 AI 重塑未来的愿景 [1] AI Development - 开发者正在利用 AI 重塑未来 [1]

[Applause] Race after race, Gabriel gave them something to believe in. The people's champion and a duck who carried him home. Well, I love to race ducklings. Gabriel, I love it.Ever since he was a kid, he wanted to be a duckling racer. His first word was quack. His second word was champion.He wasn't fast at homework, but my god, the boy could ride a duck. To be when you're older, h the best in the world. By 16, he was the best duckling racer in Sweden.And by 18, the world championship when he beat Thomas Di ...

The OpenAI Podcast is live for the first time. Host Andrew Mayne sits down with startups Cursor, Abridge, SchoolAI, and Jam.dev—each reimagining how AI can transform their industries. From healthcare and education to coding and collaboration, we explore how these builders are putting AI to work in the real world. Subscribe to the OpenAI Podcast on Spotify and Apple Podcasts ...

No content yet！ ...