Give parallel Codex tasks separate Git worktrees so each agent has its own branch and directory. Alex creates French and German variants, runs both at once, and keeps their changes independently testable.
Source episode · 07:34
How I AI: 3 Advanced Codex Workflows for Faster, Smarter Development with OpenAI's Alex Embiricoswith Claire Vo
Alex asks Codex to create French and German worktrees from main, opens each in its own terminal tab, and runs the two translation tasks in parallel.
Two isolated worktree directories and branches where Codex can run concurrently without writing into the same checkout.
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
From the main checkout, ask Codex to create one worktree and branch for each independent experiment. Use names that describe the work so the directory, branch, and terminal tab are easy to match.
Create two Git worktrees from the current main branch. Name one branch and directory `french` and the other `german`. Show me the resulting paths and confirm the active branch in each worktree.
Open one terminal tab in each worktree and run a separate Codex task. Alex translated the same placeholder into French and German, which made the separation visible while both agents worked concurrently.
# In the french worktree Translate the input field placeholder strings to French. Keep the change limited to user facing placeholder copy and run the relevant tests. # In the german worktree Translate the input field placeholder strings to German. Keep the change limited to user facing placeholder copy and run the relevant tests.
Review each branch from its own directory, run the app or tests there, and keep or discard the experiments independently. Merge the chosen branch first, then update and retest the other branch if you still want both changes.
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.