We just launched Sites into Codex! Software creation was always about more than writing code. Sites in Codex fundamentally gives the power of end-to-end software creation to every user, no matter their technical fluency. These Sites are fully deployed to a URL, private to workspaces, come with authentication, can have static files, and can store dynamic data in databases. It is in preview for business and enterprise teams and will be rolling out to all workspaces over the next day. Give it a try by typing @ Sites into Codex and ask it to build anything! This project took a massive amount of effort across hundreds of people at OpenAI - proud that we were able to get this out and excited to see what you all build with it!

Codex is getting easier to automate and customize around your code. 🪝 Hooks customize the Codex loop with scripts that run at key points in a task: • Run validators before or after work • Scan prompts for secrets • Log conversations to internal systems • Create memories or customize behavior by repo or directory ⚙️ Programmatic access tokens provide scoped credentials for Business and Enterprise teams: • Create tokens from ChatGPT workspace settings • Use them in CI, release workflows, and internal automations • Set expirations or revoke access when needed • Keep usage tied back to the workspace

You've been asking for this one... Now in preview: Codex in the ChatGPT mobile app. Start new work, review outputs, steer execution, and approve next steps, all from the ChatGPT mobile app. Codex will keep running on your laptop, Mac mini, or devbox.

You can now keep codex going for days. With GPT-5.5 it will build an entire OS kernel for you if you ask, or find critical bugs in a codebase, or optimize your database schemas, or… the options are endless.

With GPT-5.5, Codex now gets more of the job done across the browser, files, docs, and your computer. We've expanded browser use so Codex can interact with web apps, and test flows, click through pages, capture screenshots, and iterate on what it sees until it completes the task.

We’re updating our ChatGPT Pro and Plus subscriptions to better support the growing use of Codex. We’re introducing a new $100/month Pro tier. This new tier offers 5x more Codex usage than Plus and is best for longer, high-effort Codex sessions. In ChatGPT, this new Pro tier still offers access to all Pro features, including the exclusive Pro model and unlimited access to Instant and Thinking models. To celebrate the launch, we’re increasing Codex usage for a limited time through May 31st so that Pro $100 subscribers get up to 10x usage of ChatGPT Plus on Codex to build your most ambitious ideas.

My absolute favourite combo lately has been @OpenAIDevs Codex with @cursor_ai Composer 2. They compliment each other well. Also feel like Composer 2 needs a shout out for how well it generates good looking UI fast.

Automations are now GA. You can now: • Set the model and reasoning level • Choose if runs happen in a worktree or existing branch • Reuse workflows with templates Automations are great for recurring tasks — daily repo briefings, issue triage, PR comment follow-up, and more.

Introducing the Google Workspace CLI: github.com/googleworkspace/c… - built for humans and agents. Google Drive, Gmail, Calendar, and every Workspace API. 40 agent skills included.

My one complaint with GPT-5.3-Codex so far is it EATS tokens like crazy, especially compared to GPT-5.2-Codex on the same reasoning level. I am burning through usage in the Codex app at an alarming rate despite there being 2x limits until April. Still a 10/10 model though.

Introducing the Codex app—a powerful command center for building with agents. Now available on macOS. openai.com/codex/

📣 How we built the Codex agent loop Ever wonder what Codex does between your prompt and its response? Each turn assembles inputs, runs inference, executes tools, and feeds the results back into context until the loop ends openai.com/index/unrolling-t…

Introducing Agentation: a visual feedback tool for agents. Available now: ~npm i agentation Click elements, add notes, copy markdown. Your agent gets element paths, selectors, positions, and everything else it needs to find and fix things. Link to full docs below ↓

Tools that make marketing more accessible to devs are always a huge win in my book

Gemini 3 Pro with @antigravity does not get anywhere near enough love. It's easily the best combination I've seen to generate beautiful looking sites / dashboards in one shot. It will also use Nano Banana to generate assets as well. Highly recommend trying it out!

This is awesome and can confirm it works after trying it. It's yet another reason we don't always need insanely complex AI workflows to get solid results. Sometimes it just comes down to providing a little bit of extra context or guidance to the model.

Real question before starting any new project these days: can this be vibe coded in an hour? I’m increasingly building quick solutions myself instead of hunting for tools. Depends on complexity for sure, but it’s happening a lot.

Introducing Cowork: Claude Code for the rest of your work. Cowork lets you complete non-technical tasks much like how developers use Claude Code.

One of my favourite use cases with AI is to have it generate me a comprehensive manual testing checklist for my projects. It makes it a lot easier as a solo dev on a project to ensure you've tested everything imo.