독서리서치레이더투자 프레임워크
로그인 / 회원가입
← 읽기로 돌아가기
뉴스주제 · OpenAI Codex중대2 분 소요DisconfirmAI 편집부

OpenAI Engineers Charlie Guo & Gabriel Chua Demonstrate Codex Workflows at AI Engineer Conference: From Slack Context to Repeatable Software Factory

At the AI Engineer conference, OpenAI's Charlie Guo and Gabriel Chua demonstrated how to use Codex for software development through a series of examples. They showed how to generate a macOS translation app from Slack context and explored mechanisms like plugins, subagents, and automation hooks to turn single requests into repeatable development processes. The video offers concrete operational perspectives on AI engineering practices.

2026-10-06 10:00 GMT+8

In a talk published on October 6, 2026, at the AI Engineer conference, OpenAI engineers Charlie Guo and Gabriel Chua detailed the application of Codex in real-world software development. They showcased a core case: four minutes after receiving a capture of a Slack conversation, Codex produced a macOS live translation app. This process highlighted how context, plugins, and supervision work together, with the conversation supplying the idea, plugins providing development practices, and a live German translation testing the result.

Beyond rapid prototyping, the two engineers demonstrated more complex projects, including turning repository history into a shareable site about the Agents SDK, requesting an IKEA-style repository visualization from a phone, downloading dashboard data through computer use, and building a Google feedback form via a Chrome extension. They specifically distinguished between browser control for local testing and access to applications where a user is already signed in.

For longer-term projects, Guo and Chua introduced how to set verifiable completion criteria using Goals, while dividing work and exposing blockers through subagents, visible threads, audits, and progress dashboards. Remote threads handed browser testing to a local machine, and hooks added deterministic checks at specific workflow points. Automations connected these pieces, such as waiting for server provisioning, reviewing Slack feedback, or starting a separate worktree to address a bug.

로그인 / 회원가입
독서리서치레이더투자 프레임워크

The recurring question in the talk is how to turn a successful individual request into a repeatable process with useful checks and human input where needed. For engineers looking to optimize their AI-assisted programming workflows, this resource provides specific practical references on Codex integration, plugin usage, and automated supervision.

출처

  • youtube.com↗
주제

OpenAI Codex

OpenAI Codex正从通用编程助手演变为特定行业的工作流引擎,尤其在金融服务领域展现出深度整合能力。美国投资机构Benefit Street Partners的分析师利用Codex在一天内构建了自动化金融分析工具,而Franklin …

4 단계2 건업데이트됨 2026-11-07 01:14

현재까지의 과정

  1. 2025-05-16OpenAI发布Codex研究预览版,定位为基于云的软件工程代理,支持并行处理任务并集成于ChatGPT界面。openai.com ↗
  2. 2026-10-23OpenAI发布视频案例,展示Benefit Street Partners分析师Anant Kumar使用Codex构建自动化工具,用于比较SEC文件中的贷款估值并生成可视化网站。youtube.com ↗
  3. 2026-10-27在AI Engineer大会上,OpenAI工程师Charlie Guo和Gabriel Chua演示了如何利用Codex结合Slack上下文及插件机制,构建可重复的软件工厂工作流。youtube.com ↗

아직 해결되지 않은 문제

  • Codex在处理非结构化金融文档时的准确率是否已满足合规审计要求?
  • 除了金融领域,Codex在医疗或法律等其他高门槛行业的标准化工作流落地情况如何?

이 스레드의 다른 내용

  • OpenAI Case Study: Benefit Street Partners Analyst Builds Financial Analysis Tools with Codex2026-10-24
전체 주제 읽기 →
리서치 계속하기 →