Artificial Intelligence

One engineer, many agents, still no proof

Revolut engineer Dmitry Pitik used Codex agents to build a review service, but his own line-by-line checks show why solo AI builds still need proof.

StartupHub.ai Staff

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

2 min read

Dmitry Pitik built an internal code review service at Revolut with Codex as the main tool, OpenAI reports. The goal was to automate reviews and make them faster for engineers, Pitik said. That matters at Revolut scale, with more than 80 million customers worldwide as of November 2026, per La Stampa.

The obvious read is that one engineer replaced a team.

How one engineer built a code review service with Codex | Revolut’s Dmitry Pitik
How one engineer built a code review service with Codex | Revolut’s Dmitry Pitik

Pitik said he planned the features, then launched parallel agents with one task each and waited for implementation. He spent more time on design and planning than on writing code, which is a fair win for a senior platform engineer whose job is tooling. I see delegation here, not proof the output holds up in production.

Pitik said Revolut engineers own their code and he reviews every line Codex produces, challenging anything suspicious until he is confident. That honesty undercuts the solo-builder myth. For the obvious reading to hold, we would need review time, defect rates and merge times, and none appear in his account. The strongest fact for his side is that Codex sped up his research and let him run tasks in parallel, which he said boosted productivity a lot.

Pitik said small teams can now ship impressive things with this method. If you are copying it, hire for judgment first and treat agent output as a draft that still needs an owner.

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.

TopicsRevolutOpenAICodexDmitry Pitik

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.