OpenAI Gave Us a Glimpse Into Their AI Coding Playbook

Was this newsletter forwarded to you? Sign up to get it in your inbox.

Four OpenAI engineers built the Android version of the image generation app Sora in 28 days. Naturally, they built it using Codex, their AI coding agent.

Partway through that sprint, one of those engineers, RJ Marsan, shattered his wrist in a bike race, leaving him unable to type. So he cobbled together a speech-to-text system and started talking to Codex instead of typing commands himself.

That forced constraint—having to tell the computer what to do rather than execute the instructions via his keyboard—taught him something the rest of the team eventually adopted: Treating Codex like a new coworker you’re onboarding delivers stronger results than treating it like a tool you’re configuring (Codex doesn’t remember previous conversations automatically). “Every session is onboarding this new coworker [anew].”

Marsan and Alexander Embiricos, who leads the Codex product team, joined us for Every’s first-ever Codex Camp to share this and other insights learned building Sora with Codex and how generally to think about working with AI.

Here’s what we learned.

Key takeaways

1. Onboard your AI like a new hire. Start with quick, interactive prompts. Build trust. Let it learn your preferences. Then delegate longer tasks.
2. Don’t overload context. If you’d overwhelm a coworker with 6,000 facts about your codebase, you’ll overwhelm the AI too. Give it what it needs for the task at hand.
3. Narrow beats broad. An agent with one focused job outperforms a generalist trying to catch everything.
4. It doesn’t get easier—you go faster. AI tools shift the bottleneck; they don’t eliminate it. Architecture and code review become more important, not less.

Make your team AI‑native

Scattered tools slow teams down. Every Teams gives your whole organization full access to Every and our AI apps—Sparkle to organize files, Spiral to write well, Cora to manage email, and Monologue for smart dictation—plus our daily newsletter, subscriber‑only livestreams, Discord, and course discounts. One subscription to keep your company at the AI frontier. Trusted by 200+ AI-native companies—including The Browser Company, Portola, and Stainless.

Create your team

Want to sponsor Every? Click here.

How to think about working with AI

Building Codex changed how the OpenAI team thinks about AI agents...

Become a paid subscriber to Every to unlock this piece and learn about:

1. Why OpenAI’s team created three specialized AI “police” roles instead of one catch-all code reviewer
2. The counterintuitive discovery about how much context actually helps—or hurts—an AI agent
3. The research step most developers skip—and why it causes AI-generated code to fail in hard-to-trace ways