ReadingResearchRadarInvestment framework
Sign in / Sign up
← Back to reading
NewsMaterial2 min readDisconfirmAI Editorial

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.

Sign in / Sign up
ReadingResearchRadarInvestment framework

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.

Sources

  • youtube.com↗
Continue researching →