Application Refactoring · IT Operations Automation
loveholidays needed to let product, design, and commercial teams test and ship ideas without waiting for scarce engineering and platform specialists, while also making infrastructure and data changes easier to self-serve safely.
Reported impact
loveholidays raised AI-assisted code changes from 7% to 79%, increased deployment frequency by 73% without more engineers, improved Data Platform change success from 58% to 93%, and lowered cloud-storage and processing costs while letting non-engineers ship new experiences.
loveholidays embedded Codex into both customer-experience prototyping and internal platform operations so more of the business could build software directly. Search Playground, built with the company's design system, frontend technologies, and Codex, lets non-engineers turn ideas into working travel experiences, gather feedback, and even launch them on the production site. Behind the scenes, the company encodes data-platform and infrastructure best practices, validations, and release checks into Codex-guided workflows so employees can propose changes, run validations, and move work through deployment without mastering every specialist tool. Codex has become a control plane across engineers and business users, so specialists spend less time handling routine requests and more time improving the platform. The result is an operating model where more experiments become products, deployments rise without more headcount, and data-platform efficiency improves along with cloud-cost discipline.
Business ideas enter Search Playground through Codex, which uses loveholidays' design system and frontend stack to produce working experiences for feedback or launch. For infrastructure and data changes, users submit the intended change to Codex, which applies encoded best practices, runs checks, and guides work through release workflows.
"A year ago, around 7% of its code changes were AI-assisted. Today, that figure is 79%."
"Its engineers created Search Playground using the company's design system, frontend technologies, and Codex."
"Successful AI-assisted changes to loveholidays' Data Platform have risen from 58% to 93%"
"The expertise of our data and infrastructure engineers is available through Codex"
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
OpenAI Sample May 22, 2026 Virgin Atlantic Virgin Atlantic needed to ship a customer-facing mobile app under a fixed holiday deadline, improve software quality, and refactor legacy systems faster without increasing launch risk for operational airline services. 30 minutes to refactor legacy codebases, down from 2 weeks Codex OpenAI Sample Oct 9, 2026 Asana Asana needed to cut the cost and latency of its StackAI browser agent so it could offer customers more capable models for browser-driven workflows without unsustainable operating expense. $0.47 average estimated model cost with the optimized GPT-6.1 Sol workflow Codex · Command · GPT-6 Astra OpenAI Sample Oct 8, 2026 Braintrust Braintrust wanted to respond to customer feature requests faster and run more engineering experiments, but slower coding tools and backlog-driven workflows made it costly to turn feedback into working prototypes in real… 50% of the Braintrust team moved to Codex in one month Codex · GPT-5.5 