Artificial Intelligence

Revolut turned 7 years of docs AI-ready in a day

Revolut documented seven years of design system in one day for AI use, saving review time.

StartupHub.ai Staff

By StartupHub.ai Staff, reviewed by Daniel Singer, Editor

2 min read

Revolut turned almost seven years of design documentation into AI-readable docs in a day, and I think that is the practical Codex win. Dmytro Pavlov, senior design system designer at Revolut, told OpenAI he spent one day on the draft and the rest on review.

Pavlov said the design system works as a shared language for outside users and inside the company. He said that documentation will anchor a new AI tool for designers, which is why AI readability mattered more than polish.

Making seven years of design documentation AI-readable in a day | Revolut’s Dmytro Pavlov
Making seven years of design documentation AI-readable in a day | Revolut’s Dmytro Pavlov

Speed bought review time.

Because the draft took a day, Pavlov said the team had time to review the output and fix the source. The exercise exposed flaws in the documentation template and unclear wording in the visual docs.

DocsAlot takes the productized route, offering an AI-readable base with llms.txt, Markdown and MCP-ready endpoints. The TechYorker API guide pushes the same idea for agents: publish a machine-readable contract with concise, task-oriented explanations.

Fair point: a one-day draft without review would just ship template errors into the new tool.

That review step is why the claim holds. If you want AI to help designers, fix the docs first and let the model do the boring pass.

Mentioned in this story

Sources

Get the free daily brief every morning

Every morning the day's AI news, new AI startups and new funding rounds. Free and takes a few minutes to read, unsubscribe at any time.

Join 64,000 other subscribers.

TopicsRevolutDmytro PavlovCodexOpenAIDocsAlot

StartupHub.ai StaffDaniel SingerWritten by StartupHub.ai Staff, Editorial teamReviewed by Daniel Singer, EditorAbout

StartupHub.ai Staff, Editorial team

The staff writers of StartupHub.ai, ranging from investment analysts to avid AI tool users, early adopters and critical enthusiasts. Backgrounds span engineering, business and the arts. We hold every piece to rigorous standards of research and review.

Daniel Singer, Editor

Daniel Singer is an AI expert who has been writing about, covering and building AI technology since 2018.

More from Daniel Singer

Test your Agent Readiness now

Paste your website. How well ChatGPT, Claude and the other agents can read and use a site, in about a minute.

Watch

The videos behind the news, one flip at a time

The feed mixes the videos from our articles with startup demos and you flip through them like TV channels for free with no signup.