My defaultOpenAISecond AI agent

OpenAI Codex

For computer control, images, and as an end-to-end test orchestrator.

Claude Code writes the code; Codex clicks through the app like a user would.

Use it when

Computer control, image generation and image understanding, where it does better.
Driving Playwright through complex UI scenarios as an e2e test orchestrator.

Instead, consider

Claude Code Everything else.

Where it fits

Building with AI agents: Pick 02.
Clicks through the app and drives Playwright.

Last reviewed 18 October 2026 by Nicolas Dao

Also in Build and test

Default Claude Code: AI coding agent
Default GitHub: Code hosting
Default Node.js (plain JavaScript): Language
Default Playwright, Vitest, pytest: Testing
Default Stryker mutation testing: Test quality
Skip TypeScript
Never GitLab, Bitbucket and Atlassian

Back to the map →

Want this stack in your AWS account?

Cloudless Labs is a Sydney consultancy. We migrate on-premises systems to AWS, build serverless apps on this stack, and coach teams to ship with Claude Code and Codex.