# The Golden Age of AI Engineering — Alexander Embiricos, Romain Huet — session 2026-06-30T16:25:00.000Z → 2026-06-30T16:45:00.000Z

_3 transcript lines · 11 slides · source: full recording_

## Transcript

They could reuse the parts that make sense to them, or change entirely all the rest and make different choices. I know for instance they were trying to see how we did, like sign in with chatGPT, and so they could look at the code and and learn from it. We think it's better than having developers reverse engineering how it builds, and how we launch. But now let's say, speaking of subscriptions, that we'd want to go a level higher, and how you bring this harness into an app, And how do you let people sign in with their existing codex subscription, for instance? Well, it turns out we had the same problem ourselves, because we wanted to build a VSCode extension and the codex app. And we wanted to have a unified way to actually control this harness. So we built App Server, and we also made that open source. And the App Server is not kind of a community adapter, it's really the path that we use for our own products, and you can use it too. Toma, for instance, here, AKA Dimilian on X, he built his own native app for codex called codex monitor before we even launched the codex app. Because he could build that using the app server. And now he works on our team and he actually builds codex for iOS. And moving up the stack, at the app layer we also want to make sure that innovation is not blocked on our own ideas, and so we build extensible primitives here, like the in app browser that we showed on the screen, and plugins. So if you take for instance browser use and computer use, these were built as plugins using the same extension points that we have available for

## Slides

### 00:09:44

# Engineering the future of AI
[Flow diagram showing four steps: Plan, Build, Review, Deploy]

### 00:10:10

# Engineering the future of AI

## Feedback on AI Tools (Twitter Posts)

### Post 1: Codex Compaction
- **@deepfates** (Mar 30,

### 00:10:36

# AI Engineer World's Fair

## Participating Companies / Sponsors
- Weights & Biases
- snyk
- CODERII
- Airbyte
- CLOUDFLARE
-

### 00:10:59

## Engineering **the future** of AI
### AGI that benefits all of humanity

### 00:11:26

# AGI that benefits all of humanity
## Engineering the future of AI
### AI Engineer World's Fair
### Presented by Microsoft

### 00:11:49

# Engineering the future of AI
- Chat
- Hands on

### 00:17:41

# AI Engineer World's Fair
## Presented by Microsoft

- Plugins
- App
- App Server
- **Codex Harness**
- Responses API
- Models

###

### 00:17:47

## Build an open ecosystem

- Plugins
- App
- **App Server**
- Codex Harness
- Responses API
- Models

## Engineering the future of AI

[Diagram showing a vertical stack of six components, with 'App Server' highlighted in blue.]

### 00:17:52

### Build an open ecosystem

- Plugins
- App
- **App Server**
- Codex Harness
- Responses API
- Models

### Engineering the future of AI

[Diagram showing a vertical stack of six components: Plugins, App, App Server, Codex Harness, Responses API, and Models, with App Server highlighted.]

### 00:18:01

# Engineering the future of AI

## Architecture Layers
- Plugins
- App
- **App Server**
- Codex Harness
- Responses API
- Models

## Codex Monitor

### 00:18:08

# Engineering the future of AI

## Build an open ecosystem

- Plugins
- App
- App Server
- Codex Harness
- Responses API
- Models

[Diagram showing a vertical stack of six rectangular components: Plugins, App, App Server, Codex Harness, Responses API, and Models, from top to bottom.]