OpenAI Launches Codex: An Autonomous Programming Agent
AI and I16 Touko 2025

OpenAI Launches Codex: An Autonomous Programming Agent

OpenAI just launched Codex, a brand-new coding agent that can build features and fix bugs autonomously. We’ve been testing it at Every for a few days, and I’m impressed.


I invited Alexander Embiricos, a member of the OpenAI product staff responsible for Codex, to demo the agent live on a special edition of AI & I. We talk through:


  • What Codex is and how it works. Codex’s UI allows developers to see the list of tasks the agent is working on, how many lines were changed for each, and the status of the PR. It’s built for the senior software engineer who wants to delegate and review tasks efficiently.

  • How OpenAI is thinking about agents. Codex is one piece of a unified super-assistant OpenAI wants to eventually build—an agent that helps users easily get things done by selecting the right tools for them behind the scenes.

  • Why an “abundance mindset” is best for interacting with agents. Codex is designed to allow users to delegate many tasks at once without getting caught up in the details. This lets you point an abundance of agents at a specific task, like a difficult bug—it’s worth it even if only one of them succeeds.

  • OpenAI’s vision for the future of programming. In the future developers will probably spend less time writing routine code and more time guiding agents, reviewing their work, and making strategy decisions. Programming will become more social, letting teams easily delegate multiple tasks at once, allowing people to focus on ideas and collaboration instead of routine coding.


Timestamps:

  • Introduction: 00:00:52

  • The product decisions behind Codex’s interface: 00:01:40

  • How Codex works under the hood: 00:06:20

  • Why you need an abundance mindset to work well with agents: 00:14:06

  • Setting Codex to work on a real task in “Ask” mode: 00:16:28

  • How OpenAI is thinking about designing agents: 00:18:54

  • The future of programming is social: 00:31:16

  • Reviewing Codex’s work live: 00:37:21

  • How the landscape of agents will evolve: 00:39:41

    • Jaksot(99)

    The Secret to Building Sticky AI Products - Ep. 42 with Chris Pedregal

    The Secret to Building Sticky AI Products - Ep. 42 with Chris Pedregal

    Chris Pedregal knows how to build AI products that people love. Chris is the cofounder and CEO of Granola, an AI notepad for meetings. We use it all the time at Every—Granola listens in on a meeting a...

    12 Joulu 20241h

    Do 60-Minute Coding Tasks in 60 Seconds—With AI - Ep. 41 with Steve Krouse

    Do 60-Minute Coding Tasks in 60 Seconds—With AI - Ep. 41 with Steve Krouse

    Here’s the most compelling benchmark of AI progress:  A task that took 60 minutes a year ago now takes 60 seconds. In January 2024, Geoffrey Litt and I spent an hour coaxing ChatGPT and Replit to buil...

    4 Joulu 20241h 1min

    How We Incubate and Launch New Products With AI - Ep. 40 with Danny Aziz, Brandon Gell

    How We Incubate and Launch New Products With AI - Ep. 40 with Danny Aziz, Brandon Gell

    Over the last few months at Every, we’ve: Launched two AI products Acquired tens of thousands of users Released a new incubation in private alpha The weird thing is: We’re a media company w...

    27 Marras 20241h

    His GPT Wrapper Has Half a Million Users—And Keeps Growing - Ep. 39 with Vicente Silveira

    His GPT Wrapper Has Half a Million Users—And Keeps Growing - Ep. 39 with Vicente Silveira

    Everyone told Vicente Silveira that his startup—a GPT wrapper—would fail.  Instead, one year later, it’s thriving—with about 500,000 registered users, nearly 3,000 paying subscribers, and over 2 milli...

    20 Marras 20241h 3min

    How to Win With Prompt Engineering - Ep. 38 with Jared Zoneraich

    How to Win With Prompt Engineering - Ep. 38 with Jared Zoneraich

    Prompt engineering matters more than ever. But it’s evolving into something totally new:  A way for non-technical domain experts to solve complex problems with AI. I spent an hour talking to prompt wi...

    13 Marras 20241h 2min

    How Notion Cofounder Simon Last Builds AI for Millions of Users - Ep. 37 with Simon Last

    How Notion Cofounder Simon Last Builds AI for Millions of Users - Ep. 37 with Simon Last

    This episode is sponsored by Notion. I’ve been using Notion to manage my professional and personal life for almost 10 years. As a company, they pay attention to the craft and ideas underlying the soft...

    8 Marras 202455min

    How Union Square Ventures Built an AI Brain for Venture Capital - Ep. 36 with Matt Cynamon

    How Union Square Ventures Built an AI Brain for Venture Capital - Ep. 36 with Matt Cynamon

    Union Square Ventures is building an AI operating system to support their investment team.  But it’s not what you think: It’s a constellation of AI tools that captures and synthesizes the firm's colle...

    30 Loka 20241h 9min

    Building AI That Builds Itself - Ep. 35 with Yohei Nakajima

    Building AI That Builds Itself - Ep. 35 with Yohei Nakajima

    Yohei Nakajima leads a double life.  By day, he’s a general partner of a small venture firm, Untapped Capital.  By night, he’s one of the most prolific internet tinkerers in AI. (He also sometimes wor...

    23 Loka 202458min