On August 26, 2026, loveholidays said it is using Codex to enable non-engineering teams to create and deploy software directly on its platform. The online travel company operates across eight European markets and says its systems evaluate about 60 trillion package combinations each day.
From idea to product with Search Playground
The company built Search Playground with its design system, frontend technologies and Codex to let product managers, designers and commercial teams prototype customer experiences without entering an engineering queue. More than ten new search experiences have been developed through the Playground, the company reported; most were built by non-engineers and at least three are now live on the loveholidays website.
Examples cited include Inspire Me, which helps travellers explore trip types, and a marketing microsite for a “Crisps from Abroad” activation. Dmitri Lerko, Head of Engineering at loveholidays, said: “Everybody is a builder. Making changes to our applications, infrastructure, and deploying code is no longer an engineering-only activity.”
Operational results and platform changes
loveholidays also described how Codex is being applied to internal data and infrastructure workflows. Engineering teams encoded best practices, validations and release checks into workflows that Codex can guide other users through, allowing employees to focus on goals rather than specialist tools.
The company reported that successful AI-assisted changes to its Data Platform rose from 58% to 93% over the last year, and that it is seeing four times as many Data Platform changes for every support request. Across broader self-service infrastructure workflows, success reportedly increased from 63% to 90%.
loveholidays said AI-assisted code changes grew from about 7% to 79% in a year, and deployment frequency increased 73% while engineering headcount remained broadly flat. The Data Engineering team reported reductions in cloud storage costs of around £36,000 a year and additional annual savings of about £100,000 from reduced data-processing waste.
Mike Jones, CTO, described the ambition as building a “general intelligence for travel” by combining the company’s technology and staff expertise and making both more accessible via AI and Codex.
Reported metrics include the jump in AI-assisted changes from 7% to 79%, a 73% increase in deployments, Data Platform success moving from 58% to 93%, and the cited annual cost savings of approximately £136,000.
Original source: OpenAI News