Start with a visual direction

GPT Image 2 is great at generating high quality UI mockups. Instead of starting from scratch when exploring new ideas, you can leverage image generation to get a visual direction.

You can do this in two ways:

• Iterate on the visual direction using the ImageGen skill, and once you are satisfied with the proposed UI, you can ask Codex to build a prototype matching the visuals. In that case, make sure to copy the final image you want to implement in a new turn rather than continuing the conversation directly – Codex will do better when it can reference a user attachment.
• Use a plugin and simply describe your idea: the plugin will generate the visual direction for you and handle next steps.

Leverage a plugin

If you do not need to iterate on the visual direction before starting the implementation, you can use a plugin and describe your idea.

Use the Build Web Apps plugin for web apps, dashboards, creative websites, and frontend-heavy tools. Its workflow pushes Codex to generate a design first, match it in code, and use the browser to compare the result back to the concept.

Use the Game Studio plugin when the proof of concept is a browser game. That path should define the player verbs, first playable loop, engine, asset workflow, HUD, controls, and browser test before expanding the game.

Iteration workflow

A good proof of concept is scoped to an MVP that can be implemented quickly and validated with the team. If you want to make sure the MVP is working as expected, you can use Playwright interactive to let Codex verify its work.

Once you have a first version working, you can iterate on it by asking for scoped changes in the same conversation: