How I AI
“A Full Software Engineering Teammate”: OpenAI Product Lead on Getting the Most Out of Codex | Alexander Embiricos
How I AI
•January 12, 2026•53 min
0
How I AI•Jan 12, 2026
Key Takeaways
- •Codex integrates into IDEs as a full engineering teammate.
- •Use same chat for plan edits to retain context.
- •Parallel tasks via Git work trees prevent code conflicts.
- •Planning with plans.md yields thorough, reliable implementations.
- •Codex built Sora Android app in 28 days, hit #1.
Pulse Analysis
In this episode, OpenAI’s product lead Alexander Embiricos demonstrates how Codex functions as a true software‑engineering teammate. Integrated directly into VS Code and other IDEs via extensions, Codex answers questions, generates code snippets, and maintains context when users iterate on prompts. By keeping the conversation in a single chat, developers can refine plans without losing the model’s mental model, making the tool especially valuable for both seasoned engineers and newcomers exploring AI‑assisted coding.
Embiricos highlights workflow efficiencies that come from treating Codex like a collaborative partner. He shows how parallel tasks can be safely executed using Git work trees, allowing separate feature branches—such as language‑specific UI strings—to be modified simultaneously without conflict. This approach, combined with the practice of editing plans in‑chat, dramatically reduces context‑switching and accelerates iteration cycles. The discussion also covers the “plans.md” methodology, a structured markdown template that guides Codex to produce thorough, milestone‑driven implementations, ensuring reliability even on complex codebases.
The conversation culminates with a real‑world case study: the Sora Android app, built by a four‑engineer team in just 28 days using Codex. By first crafting a detailed architecture plan and then letting Codex execute the tasks, the team delivered a #1 app in the store, illustrating how AI‑driven planning and execution can boost development velocity without sacrificing design rigor. This success story underscores Codex’s potential to reshape software delivery, positioning it as a critical productivity tool for modern engineering teams.
Episode Description
Alexander Embiricos, the product lead for Codex at OpenAI, shares practical workflows for getting the most out of this AI coding agent. In this episode, he demonstrates how both non-technical users and experienced engineers can leverage Codex to accelerate development, from making simple code changes to building production-ready applications. Alex walks through real examples of using Codex in VS Code and terminal environments, implementing parallel workflows with Git worktrees, and creating detailed implementation plans for complex projects. He also reveals how OpenAI uses Codex internally, including how they built the Sora Android app in just 28 days, and offers insights on automated code review and the future of AI-assisted development.
What you’ll learn:
How to set up and use Codex in VS Code and terminal environments for both simple and complex coding tasks
A practical workflow for running multiple Codex instances in parallel using Git worktrees to avoid conflicts
How to create detailed implementation plans using the Plans.md technique for complex engineering projects
Why context is critical when prompting Codex—and how to provide the right information for better results
How OpenAI uses automated code review to accelerate development while maintaining high quality standards
The key differences between vibe coding for prototypes versus building production-ready applications with AI
How the new GPT-5.2 model improves Codex’s capabilities with faster reasoning and better problem-solving
—
Brought to you by:
Brex—The intelligent finance platform built for founders
Graphite—Your AI code review platform
—
Detailed workflow walkthrough from this episode:
https://chatprd.ai/how-i-ai/advanced-codex-workflows-with-openai-alex-embiricos
—
In this episode, we cover:
(00:00) Introduction to Alex and Codex
(02:06) Getting started with Codex
(04:54) Using Codex for parallel tasks
(07:34) Understanding Git worktrees
(09:51) Terminal shortcuts and command-line efficiency
(12:16) How OpenAI built the Sora Android app with Codex
(15:37) Using PLANS.md for problem solving
(17:57) The importance of high agency
(22:22) Deciding between what needs a plan and what doesn’t
(26:42) How to multiply the impact of Codex
(28:08) Implementing automated code review with GitHub
(31:58) Delivering the benefits of AGI to all humanity
(34:35) Accelerating developer productivity
(36:38) Recap and final thoughts
—
Tools referenced:
• Codex: https://openai.com/blog/openai-codex
• VS Code: https://code.visualstudio.com/
• Cursor: https://cursor.com/
• Git: https://git-scm.com/
• GitHub: https://github.com/
• Atlas: https://openai.com/atlas
• ChatGPT: https://chat.openai.com/
• Slack: https://slack.com/
• Linear: https://linear.app/
—
Other references:
• Sora Android app: https://openai.com/blog/sora
• GPT-5.2 model: https://openai.com/index/introducing-gpt-5-2/
• SWE-bench: https://openai.com/index/introducing-swe-bench-verified/
—
Where to find Alexander Embiricos:
LinkedIn: https://www.linkedin.com/in/embirico
X: https://x.com/embirico
—
Where to find Claire Vo:
ChatPRD: https://www.chatprd.ai/
Website: https://clairevo.com/
LinkedIn: https://www.linkedin.com/in/clairevo/
X: https://x.com/clairevo
—
Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email jordan@penname.co.
Show Notes
0
Comments
Want to join the conversation?
Loading comments...