Name: Getting started with Codex
Uploaded: 2026-02-06T10:33:23.000Z
Duration: 53 min 2 s
Description: Thousands of YouTube videos with English-Chinese subtitles! Now you can learn to understand native speakers, expand your vocabulary, and improve your pronunciation...

Hi, welcome to today's Getting Started with Codex session.

And I'm Charlie and we work with customers to help them get onboarded to Codex.

It's a really exciting time in the AI coding space and it's quickly changing how developers work.

So Codex is OpenAI's coding agent that developers can use across different surfaces.

And we've seen firsthand how developers are delegating routine and time consuming tasks to codecs and spending more time on complex and novel challenges like design and architecture.

And we've seen a lot of excitement from the developer community about codecs.

And our goal this session today is to give you a high level introduction to codecs.

So we're going to cover a few different topics here.

First we're going to walk through just the introduction to codecs, what it is, kind of what the extent of the product is.

Then we'll talk about installation and setup, how to get started with codecs.

We'll then dive into AgentsMD, a readme format for Codex and how to configure codecs with config toml.

We'll also talk about prompting with Codex and some of the best practices around that.

We'll give you some CLI and IDE tips and tricks, talk about MCP configuration and then dive into advanced use cases and give you some follow up additional resources.

So you can use Codex in multiple clients today.

So the CLI allows for lightweight interaction in the terminal.

It also offers a headless SDK mode for more advanced programmat ability.

So Codex's IDE extension works with any VS code based IDE and really allows developers to write code in more of a rich graphical user interface.

And you can also kick off remote tasks in a cloud environment as needed.

And with Codex's cloud environments it really allows you to run multiple parallel tasks in the background even with your laptop closed.

So it's really ideal for kicking off async tasks like code review or working while on the go with your mobile phone.

So for today's session we'll focus more on the CLI and the IDE extension.

So here are a few of the ways that customers are using codecs today and how it can integrate with your team's workflows.

As Derek mentioned, you can kick off code reviews in Codex Cloud whenever PR gets opened and codecs can provide comments and find critical bugs and issues before they get merged into production.

You can also use it with Slack mentions so you can integrate codecs into Slack.

Mention it and then it picks up the whole conversation thread that you've maybe been chatting with your team about and then implements it and gives you a pr.

And you can also build your own integrations with the Codecs SDK.

This allows you to run codecs programmatically in your own containers and so you can get structured output out of codecs.

And we'll cover this kind of in the back half of the presentation here.

So OpenAI at its core is a research company and Codex is backed by our state of the art models, most recently GPT 5.1 codecs max, which is our best model for agentic coding.

So it's specifically trained in the Codex CLI harness and our continuous focus will be to have each model generation be more efficient, be able to run faster and longer, and

to generate even better production ready code.

So our models are natively trained in Linux, macOS, Windows environments, so it'll be very reliable in Bash and PowerShell and will adhere to the sandboxing rules.

We also train the model to be able to accurately auto compact long conversations so you can have codecs work for you on longer running tasks.

So for example, really large scale refactor tasks.

Yeah, Windows support and those long ring tasks are like maybe the two of the biggest feature requests we've been getting with codecs.

And we also recently published a guide that tells your team how to build an AI native engineering team.

It goes through how we can use coding agents to accelerate different parts of the software development life cycle.

We broke it down into seven phases that span planning and design, all the way to documentation and maintenance.

And as we go through today's session, I would just encourage you to think about how Codex can help your team in these different areas.

Even though we're starting with just the basics here, all of this is applicable throughout the software development lifecycle.

As a quick reminder again, the focus of today's session is the CLI and IDE surfaces.

We'll be using an open source repository, so if you're new to Codex, we definitely encourage you to follow along using the same repository or just a repository of your choice.

Let's start with installing Codec CLI on your local machine so you can install in a couple ways.

You can install using Brew or NPM which is the suggested method since it's going to be the most up to date.

Our team ships very, very quickly, sometimes multiple times per week.

So this way you're always going to be on top of the latest release when you run Codex sessions as well, there's going to be a banner on the top that reminds you if you if there's a newer version to update to.

If you want, you can look at the latest binary releases on GitHub.

Since codex is open source, codec CLI is open source, and

you can also look at the change log on our developer's website for more specific changes for each version.

So you can install the codec CLI extension in VS code as well.

And so to do that you can open VS code and click on the Extensions tab here and search OpenAI codecs.

And so you want to make sure you're looking at the official one made by OpenAI as seen here.

And when you download it you'll see the version that you have and you'll be able to switch between pre release version and the release candidate.

And you can also toggle on auto update or not.

I definitely recommend toggling on auto update since you want to make sure you're seeing the latest updates for the IDE extension.

So let's talk about actually signing in with your ChatGPT Enterprise account to use Codex.

So there's two different ways and if you use either way you'll be signed in on both sides.

So on the IDE extension when you first open it, you'll be able to see a splash screen that says sign in.

And so when you click on that, it'll bring you to a sign in page similar to how you you'll see on the codec cli, which I'll demonstrate now.

So in the codec cli, all you need to do is type Codex login which will take you to a page where you can sign in with your work email.

It will probably route you through your internal SSO to be able to log in.

And once you're you've done with that, you'll be able to start using Codex locally on your computer on the CLI and the IDE extension.

And so once you're in Codex cli, I'll show you how to start running it.

In a second you'll see that there's a couple slash commands that I will note throughout this session.

This just gives you a high level overview of the model that you're using, the directory, the sandbox mode, the approval policy, how much context window you have left.

So for example, just to go back to the CLI here, I'm on this specific version, I'm using this model and currently in the agents.md directory.

And so what you can do is go to slash status.

And you'll see here that I'm using this specific set of configurations with my account and my session ID as well.

And so let's get started by cloning the repository that we'll be using here today.

So we're using the Agents MD web website, which you'll see here.

So Charlie will Talk more about AgentsMD and why it's very important.

But for today, we'll be cloning this repository that's open source.

So once you clone that repository through this link below, just CD into that file, install NPM and then NPM run dev so you'll be able to run it locally.

We're using the AgentsMD microsite while also talking about AgentsMD.

But you know, we want to hammer in AgentsMD today.

So we've set up AgentsMD and I'm running it locally now.

So I'll hand it over to Charlie to dig a little deeper on AgentsMD.

All right, so we have a project set up and we want to work on it.

We can use AgentsMD to help get codecs clued in to how this project is going to work.

Well, when you think about it, coding agents don't really retain any context between sessions.

Every time you start it up, it's coming in with a fresh context window.

AgentsMD ensures that the instructions that you want to give the agent to just give it the background, the TLDR on your project are always loaded automatically.

If it's in the directory where you're starting codecs, you can use it basically as a lightweight readme that allows your agent to quickly understand and get up to speed on your project and just get that context it needs to actually be able to do its work.

Subtitles ListPlay Video

Getting started with Codex

specific

context

awesome

figure