Codex Has Left The Laptop | DevDay 2026

Video authored by the channel shown, not by IANIA; all rights belong to the creator. Transcript and summary generated automatically; the original-language content is preserved.

Original language: English

Original video: Codex Has Left The Laptop | DevDay 2026 · Channel: OpenAI · 21:23 · Watch on YouTube

Topics: AI agents, Task and workflow automation, Software engineering with AI, AI developer tools

Summary

Dominic introduces new ways to use Codex across cloud environments, Slack, Teams, the desktop app, CLI, and browser, so work can continue without being tied to a laptop. He demonstrates cloud setup and task execution, access to private resources, code review, team planning in Spaces, and personal dots that monitor and advance ongoing work. The talk emphasizes choosing the interfaces and workflows that suit each team rather than adopting every feature at once. He closes by recommending Codex Cloud, Spaces, and ongoing responsibilities for dots as practical starting points.

Key points

Codex Cloud lets tasks run in prepared cloud environments instead of relying on a laptop or separately maintained machines.
Creating an environment can inspect repositories and dependencies, then generate a startup skill and script; subsequent tasks can benefit from filesystem snapshots and background updates.
Cloud tasks can use installed plugins, such as Figma, and can work with private resources through Tailscale or OIDC.
Cloud environments can be shared with a team, while personal environment variables can remain private in a vault.
Codex can be used in Slack and Teams, bringing agent work into places where teams already collaborate.
The desktop app’s code review tab supports reviewing pull requests, leaving comments, submitting feedback, asking questions, and running a Codex review.
Spaces keep plans, diagrams, task tracking, team feedback, and Codex implementation work together.
Personal dots can monitor selected discussions and take on ongoing work; @ChatGPT is intended for collaboration in shared threads.
The CLI adds an agent view, plugin mentions, diagram and LaTeX rendering, and voice mode; the browser can access cloud tasks and deployed sites.
The speaker recommends starting with Codex Cloud, Spaces, or assigning a dot an ongoing responsibility.

Chapters

Start	Chapter	Summary
00:19	Codex workflows beyond the laptop	Dominic frames the challenge of keeping up with new features and introduces running Codex tasks across different interfaces and environments.
03:32	Setting up and using Codex Cloud	He demonstrates cloud environment setup, repository preparation, a Figma-based shader task, and access to private resources through Tailscale and OIDC.
09:32	Environment configuration and team collaboration	He reviews the generated setup instructions and describes environment sharing, Slack-based collaboration, and cloud-backed pull request work.
12:13	Code review and planning with Spaces	He shows the desktop code review tools and how Spaces can hold plans, diagrams, task tracking, team feedback, and implementation work.
14:20	Dots for ongoing productivity	He demonstrates a dot tracking and reviewing a pull request from Slack, then explains how dots differ from @ChatGPT.
17:37	Codex in the CLI and browser	He tours the updated CLI and shows how cloud tasks, deployed sites, and other Codex features can be accessed in a browser.
19:46	Recommendations and closing	He summarizes how agent work has grown and recommends trying Codex Cloud, Spaces, and ongoing responsibilities for dots.

Quotes

delegating work should be as easy as just telling Codex to do something — 02:27

you should be able to use the Codex harness in whichever interface you want to use — 03:01

the dots are an extension of yourself. — 16:01

We want you to be able to use codex wherever you want and however it fits into your workflow. — 20:19

Concepts and entities

Codex, Codex Cloud, Space, Dots, Slack, Tailscale, OIDC, Figma, CLI, OpenAI

Full transcript (original language)

00:19 [applause] >> Hi everyone. My name is Dominic. I work on the developer experience here at OpenAI. Now Sam earlier launched around 20 or so new features. And between those and the roughly 300 features that we launched over the course of the last year, the building with them has drastically changed how we build things at OpenAI and how many of you built.

00:50 And I know this is incredibly hard to keep up. So over the next 25 minutes, I want to give you some practical examples how you can actually incorporate these things into your workflows. Because the fact is these features have drastically changed how we built and I believe they’re going to change how you built. But I also know that it can be not just overwhelming but confusing how to actually build these things into your workflow. And ultimately, I want you to build how And ultimately, I want to make sure that you can use Codex anywhere the way that

01:22 you want to. At the beginning of the year, I I don’t know about you all but for me, it was pretty common to like run one or two tasks. But seeing Peter um >> [clears throat] >> have this tweet uh with like I don’t know, 40 different Codexes running at the same time felt overwhelming. I could not imagine actually running that many tasks at the same time. But then we launched the Codex app and it made delegating and switching tasks so much easier. And since then, running multiple agents

01:54 at the same time is almost the norm. And as models got better and more capable, especially around computer use and long-running work, we started handing increasingly more increasingly bigger problems off to the models, often running for hours or days. And as a result, we started carrying our laptops half open just to keep them running between meetings. And to solve that, I know about you all, but like how many of you ended up buying a Mac Mini or like a Raspberry Pi or even renting

02:27 some VPSs just to keep your agents running. But more machines means that you have to deal with more upkeep, more disk space, dealing with updates, overall capacity that you need to manage, and every time you want to do more, you have to procure more. But delegating work should be as easy as just telling Codex to do something, and it picks up the work regardless of whether you have to like go and procure more computers. Cuz ultimately, you should be able to use the Codex harness in whichever

03:01 interface you want to use and choose where that work runs for you. So that you have the opportunity to adapt the workflow um to to adapt the workflow to your needs, and as agents and models become more capable, continue to keep up with that. And so today, we launched Codex Cloud, dots, and add chat GPT in Slack and in Teams. And all of these use the same agent that you’ve been using. Meaning you have access to the same tools and information through the plugins that you already installed in

03:32 your account. And it means that you can pick the features that fit your workflow without having to start from scratch. Enough talk, though. Let’s actually show you a couple of these things and how you can use them. All right. So, in the desktop app, um additionally to running tasks locally um or running them on your remote, you can now uh run tasks on Code X in the cloud using environments that either your team has already created or by

04:05 creating a new environment. When you create a new environment, you can pick the different repositories that you want the environment to have access to. We’re going to pick two of the projects from Blossom Music, the project that Holly was working on. As soon as I uh select these, Code X is actually going to begin to work on setting up this project. It will do all the preparation for you by inspecting the repository, the dependencies, and set up all of the necessary things that might be required to work on this project. This used to take a lot of

04:37 manual configuration and was often very cumbersome. As part of this, it will not just discover the dependencies, it will also write both a startup skill that teaches the agent how to use the environment, and it will uh write a startup script to make sure that it can quickly iterate on these environments. In this case, um if everything goes well, it will notice that we have iOS um and web dependencies in here both uh both at the same time. However, because this is a Linux environment, you can see here, it is noticing correctly

05:11 that it won’t be able to run the mobile application, which is fine for me because in this case, I just wanted to have access to that code so I can reference that. However, um eventually, you’ll be able to bring your own cloud environments, which means that you can actually adapt this to whatever way you want want these tasks to run while still leveraging the same capabilities of Code X Cloud. One of the things that we did put a lot of effort in as part of this is making sure that things run faster than before, which means that we put a lot of effort

05:44 into the snapshotting of the file system, making subsequent tasks faster to start up. But, it also means that we can run background updates to make sure it has the latest repo changes and run any other update scripts necessary. Now, I’m going to let this run for a bit, but I wanted to show you an example of what you can do with Codux Cloud. So, in this case, um I kicked off a task earlier where I sent it an app shot to go and implement a shader that we had designed in Figma.

06:16 So, I took an app shot like this and sent it over to my cloud environment. And from here, it worked on it, pulling all of the necessary details directly from Figma using the Figma plugin that I had installed in my account. From here, it went and actually implemented the um the shader, it tested it, and created a video that for some reason is not loading right now. Um but in order to actually play with it,

06:46 and because we have access to all of the different plugins in our environment, I went ahead and actually asked it to turn the same thing into a little playground that we can play with. So, this is deployed as a site, and from here, I’m able to test out the shader um before I actually deploy it to the site itself. I can tweak things, and then I can go and send off any additional updates to the settings back to my app. I can also the same way that I’m used to from any other cloud environ- uh any

07:18 other local environment that I might have used Coduxin before, use the app to leave comments directly on the code that was edited, inspect what has changed, and even start up a site chat if I want to have questions about the task that was just executed. The other thing um that is normally a common drawback with cloud environments is access to private resources. You might have some resources where you want

07:51 to be able to have the cloud environment access those but not expose them to the entire public internet. One of those examples is I have this little API running on this Raspberry Pi right now. It is not available to the internet. It runs on this Raspberry Pi alone. Um but I configure it my environment here to be able to use Tailscale as a VPN access. So I gave it access. Thank you. I gave I gave it an off key to my Tailscale and from here Codex can access

08:26 any of my resources on my Tailscale network. Uh at the same time we also added OIDC support. So if you want to access your cloud resources through OIDC, you can do that as well. And so I have an environment here that we can start off a task. And I can ask it to pull the API that is running on this task. And to prove to you that this is actually an API that doesn’t run um on the cloud. This is the This is the port that the API runs on. Right now it’s not responding um but if I connect my laptop to that

09:00 same Tailscale network. See. All right. We can see the API’s responding. And so if we’re going back to the task. Seems something You might have noticed we had some outages during the um keynote. There’s some devs working on it. So I don’t know exactly what’s going on here but I’m going to show you a backup. Um so here you can see I asked this earlier and we’re doing the same um API calls in this request. There we go. We’re doing the same API

09:32 calls here. So Codex is able to access those same resources that are just available in our Tailscale network. All right, let’s take a look at how our setup task went here. Um so, as I mentioned earlier, it figured out that it cannot actually test the iOS changes, but that it can still do mobile source editing. And then it suggested to us here uh both an install script that we can run as well as a startup skill. From here, I can go and modify this by hand, or I can continue to ask Codex any questions or give it instructions about

10:07 how I want to continue to configure this environment. You can do that at at while you’re creating it the first time, or continue to come back and iterate on it further. And similarly, we have a startup skill that describes all of the necessary details here for this project. And I can go and accept these. And now I can do any other changes, like controlling what network access it has, set up the network secrets, and even configure environment variables that are either specific to the cloud environment that I have, or use personal environment variables

10:38 that are stored in my vault so that they are not shared with my team. Cuz the other thing that I can do is choose between sharing this environment with just myself, or with my entire team. And because these tasks run in the cloud, I can actually turn uh like close my laptop and continue to have access to all of those tasks on my phone or in the browser. The other thing that you get out of running these tasks in the cloud is that we can bring them into the environments

11:09 where our teams are already working. So, in our case, that’s Slack, where we were able to have a conversation between me and my colleague about this bug that he found in the app where it looked like the web app didn’t actually have the right visuals implemented. I asked Codex or I asked ChatGPT to go and figure this out. It actually pulled up the pull request. It also accessed the Figma files to figure out what was wrong and noticed

11:42 that there was already a PR that was solving this problem. I asked it to dive deeper into it and even test these changes and it used that same cloud environment that I had already created and shared with my organization um to test all of the changes. We were able to collaborate on this between both of us and ultimately get to a point where the PR is ready to be reviewed. Talking about reviewing code, I don’t know about you all, but as agents write more code, I find myself spending more time actually reviewing code.

12:13 And because of that, we ended up overhauling the code review tab inside the desktop app. So, you can now see all of the PRs that are assigned to both yourself or were created by you um directly in the app. And from here, you can do all of the things that you would do with a regular code review. You can see the code, you can leave comments, you can see the comments of others, submit your review feedback, or even run a review with Codex. The thing that I personally find incredibly

12:43 helpful, though, is to be able to ask questions directly inside the app. Come on. Directly within the app. There we go. Um to get details about what this PR is about and help myself better understand the the side effects that might be happening inside um this particular pull request. And when I’m happy, I can submit the feedback. As agents take on bigger work, the other big part is planning and collaborating

13:15 with our teams. Um Space is a great way for you to actually collaborate both with your agent and with your team at the same time without having to copy-paste different pieces of information back and forth. So, in this case, I was working on a redesign of our API uh reference implement reference and how I wanted to deploy it. And so, in this case, Codex wrote up a plan, I put it into space, I can share it to with my team, get feedback from them,

13:48 but I’m I can also continue to iterate with Codex on it. So, in this case, I asked it to add a system diagram to better understand how these different pieces fit together. And then, um have a task tracker as well. And as Codex works on these tasks, I can have it update those, or if I’m working with the entire team on this project, we can have all of our all of our dots and our Codex contribute to this document so that we’re all in sync on what is happening. The other thing that I can do is once I’m happy with this plan,

14:20 I can go and ask Codex to implement the plan and it will pick it up and continuously push information back if I wanted to. The last part of all of this is productivity. Uh how many of you have been using like loops or threads of threads to manage their work? All right, a decent amount of you. So, you will actually love the productivity of dots uh because it gives you a way for you to manage both your existing Codex tasks and hand off more tasks to Codex while gaining some productivity of dots continuously watching out on what

14:55 is happening. That means you can track product and engineering discussions, it can notice code changes for you, and then it can also spin up tasks for you when necessary. In this case, for example, my colleague Carolus had tagged me in a PR that I had missed. And I got a notification that in Slack from my dot to check out this PR. I didn’t really have time in this moment to take a look at it. It was uh 10 20 past 10 on a Sunday. So, I asked it what the PR was about um and my dot actually uh

15:28 started reviewing that PR trying to figure out if it was what it was about. And then I asked it to do a more thorough review. As part of this, it went ahead and actually spun up a full-on cloud task uh directly from my Slack environment so that it could uh dive into the PR, figure out what the issues are, and then report back to me. But, because this is an actual task, I can also go in here and continue to ask follow-up questions myself later on, or even use this to bring the PR over the

16:01 finish line. Now, I showed you two Slack examples, and one of the questions I’m certain you’re answering asking yourself right now is, “Great, there is @ChatGPT and there is my dot. Why when when do I use which and what’s the difference?” And the way to think about it is the dots are an extension of yourself. We intentionally named these with your name and then the name of your dot, so that

16:33 people inside Slack understand that they’re tied to your personality, they have context about um what you’re working on, your memory. And so, they’re great for any ongoing work that is related to what you do. That means my dot regularly watches channels that I care about, weighs in on topics if I give it the permission to, but it also just means that I can forward constantly forward tasks to it in Slack or in other channels to go and have my dot tackle tasks for me. @ChatGPT, on the other hand, is meant

17:05 for collaboration. It’s a great way for you and your colleague to work in a thread at the same time, interact on it, work together on a PR, for example, and because of that, your dot has access to all of your cloud environments and your local code acts while at chat GPT only has access to your shared cloud environments. But, it makes it so much easier for you to collaborate on things. Now, earlier I mentioned that I want you to be able to use code acts anywhere you

17:37 want to, and whatever way you want. And so far, the only thing that I showed you is desktop and we talked about mobile. But, I know a lot of you also love using the CLI, and because of that, we started giving the CLI a big overhaul. Um Among other things, you now have an agent view, which means you can see all of the different tasks that are running inside your code acts, so you can keep an eye on on um which ones need your attention, start up new ones, and run multiple ones in

18:08 parallel very easily. We’ve also overhauled We also overhauled things like being able to at mention both all of your plugins that you’re using, as well as making it significantly faster to do things like selecting image selecting text. You can render um diagrams and LaTeX directly inside the terminal. Uh and we even added things like voice mode, so that you can now talk to your agent directly within the terminal using

18:40 the same um the microphone is not enabled on this one. Um but, using the same uh GPT life model that you know and love from the desktop app. The other thing that you can do now is use more of your experience directly in the web. So, this is Chrome. Um it is not the desktop app, but you’re going to see a very familiar experience. You can access all of your cloud tasks that you’ve been running using code acts cloud directly in the browser. You can

19:15 see here actually it shows the same app shot that I sent over. We can review that video that wasn’t playing earlier. So you can see it here engaging with it. And you can even interact with the sites that were deployed directly within your web interface. You can also access your dot and soon hopefully very soon in the next coming days you’ll be able to access your code review tab inside the web app as well.

19:46 So you don’t have to install or use the desktop app just to get more things done. Now the way we develop has drastically changed over the last year. We moved from individual tasks to giving increasingly bigger and bigger problems to our agents. And um and it made it easier for you to take on the things that you’ve dreamed up and actually build high quality solutions rather than just some prototypes.

20:19 And you don’t need to adopt all of these things that I’ve showed you today all at once. We want you to be able to use codex wherever you want and however it fits into your workflow. But there are three things I would encourage you to try. One, if you’re still leaving your laptop cracked or managing a pile of dev boxes in whatever shape it is. Try out codex cloud for your work. It means you can move off your laptop and reuse prepared environments and spend less time maintaining that infrastructure.

20:53 And if you’re tired of jumping across docs for your team and then go and copy the plan back into a doc for codex to be used. Instead, try out space. It gives you our It you the ability to take the features and plans and keep them in one place for both your agents and for your team. And it lets your Codex continuously update the progress directly within the doc so that your team knows what is happening at the same time.

21:23 And if you’re tired of manually forwarding work to Codex and prompting each every time uh uh prompting it every time, give your dot an ongoing responsibility that you’re handling and let it keep that uh keep track of that work and let it uh handle keeping it moving. With then, go ahead and build the things that you’ve been dreaming up with Codex anywhere. Thank you. >> [applause]