loveholidays turns everyone into a builder with OpenAI Codex: data platform change success hits 93%

OpenAI published a customer story on August 26 detailing how loveholidays, an online travel agent operating across eight European markets, is using Codex to open up software development across the business. The company's platform processes 60 trillion package combinations daily, and building on it was long the preserve of engineering.

Now, the case study says, product managers, designers, and commercial teams are increasingly contributing directly to codebases. They can prototype customer experiences, make data and infrastructure changes, and turn ideas into working software without every request entering an engineering queue. "Everybody is a builder," says Dmitri Lerko, Head of Engineering at loveholidays.

The flagship example is Search Playground, built by engineers using the company's design system, frontend technologies, and Codex. It lets people across the business turn an idea into a working customer experience, gather feedback, and test whether it delivers value. More than ten new search experiences have been developed through the Playground, most built by non-engineers, with at least three now live on the loveholidays website.

Marketing provides another example: for its recent "Crisps from Abroad" activation, the team built an interactive microsite in hours with Codex and Search Playground — work that previously would have gone to an external agency.

Behind the scenes, engineering teams encode best practices and validations into workflows Codex can guide other users through, so employees can propose changes, run checks, and navigate the release process without deep system knowledge. The results are measurable: successful AI-assisted changes to the Data Platform rose from 58% to 93% over the past year, with four times as many Data Platform changes per support request, and broader self-service infrastructure success climbed from 63% to 90%.

CTO Mike Jones frames it as building "the general intelligence for travel" — combining the company's technology with its people's expertise and democratizing both with AI and Codex. For OpenAI, the story positions Codex as moving from assisted coding to democratized development inside enterprises.

The question now is how far the pattern generalizes: whether success rates among non-engineers like these convince more companies to hand coding workflows to AI assistants, and how organizations reshape engineering processes around them.