Open an unfamiliar repository in Codex, ask how to run it, launch the app with the returned command, and make a small behavior change in plain language while Codex traces the relevant code.
Source episode · 03:00
How I AI: 3 Advanced Codex Workflows for Faster, Smarter Development with OpenAI's Alex Embiricoswith Claire Vo
Alex installs the Codex extension, asks how to play an unfamiliar game, runs the command Codex finds, and lowers an oversized jump with a plain language request.
A locally running project plus one small, verified behavior change made through Codex.
OpenAI conversational AI
OpenAI's cloud-based AI software engineering agent that can execute code, run tests, and handle complex multi-file tasks autonomously.
Step by step
Follow the sequence once, then adapt the prompts, checks, and handoffs to your own setup.
3 steps
Install the Codex extension in VS Code, sign in, and open the repository folder. Keep the Codex panel beside the editor so you can ask questions while inspecting the files and terminal output.
For easier access, drag the Codex icon from the primary sidebar to the secondary sidebar on the right.
Ask Codex how to run the project instead of guessing from the file tree. Have it identify the package manager, setup command, and development command from the repository, then run those commands in the terminal.
Inspect this repository and tell me how to run it locally. Identify the package manager, required setup, environment files, and exact development command from the files in this repo. Then explain how I use the app once it starts.
Use the running app to choose one visible behavior, then describe the desired change in plain language. Let Codex locate the implementation, make the narrow edit, and run the relevant check. Return to the app and repeat the same interaction to confirm the result.
The character jumps much too high. Trace the code that controls jump height, lower it to a reasonable value without changing other movement behavior, and run the relevant checks. Summarize the file and value you changed.
Turn an idea into a PRD, user stories, and a plan.
After the steps
How to recover when the loop fails and where human judgment helps.
Recover
Keep building
Design a weekly meta-workflow that analyzes your interactions with your AI assistant to make it smarter. This system learns your writing style from edits, suggests new automations for repetitive tasks, and helps you filter valuable AI techniques from hype.
Create a daily AI workflow that summarizes yesterday's meetings, identifies urgent tasks, and proactively learns internal company terms it doesn't understand. This keeps your AI assistant's knowledge current and highly relevant to your work.
Build a recurring AI task that automatically gathers updates from your calendar, Slack, and notes to suggest weekly priorities and prepare you for upcoming meetings. Start every Monday with a clear, comprehensive plan without the manual effort.
Join 100,000+ product managers who use ChatPRD to write better docs, align teams faster, and build products users love.