Virgin Atlantic used Codex to ship its revamped mobile app in time for the Christmas travel rush with near-complete unit test coverage and zero P1 defects at launch. OpenAI's customer story reports 78 to 80% codebase size reduction on legacy refactors, approximately 100% unit test coverage on the new app, and legacy refactoring that took 2 weeks now taking about 30 minutes. "The ability to utilize Codex to improve the quality of the application before it got into the hands of our customers was a game-changer for us," said Neil Letchford, Vice President, Digital Engineering.
The Christmas travel rush is one of the highest-risk periods of the year for potentially introducing software bugs. "We're an operational airline, so we have to be very careful about when we deliver applications to our customers live," Letchford explains. "People are flying with this application. They need to be able to check in, and they need to be able to get on their aircraft."
Virgin Atlantic launched the new mobile app in beta over Christmas and went live in production weeks later. "The quality levels there due to the test coverage were exceptional," Letchford says. The team shipped the app with zero P1 tickets at launch.
Codex is also used on legacy code the team has maintained for years. "We're seeing in some instances anywhere from 78 to 80% reduction in codebase size from utilizing Codex," Letchford says, and "We're seeing gains in the refactoring space where a two-week piece of work now maybe takes about 30 minutes to an hour." In a recent sprint, one of the team's lead front-end developers, a heavy Codex user, built a complete, working front-end application from a Figma prototype in a week, with the backend stubbed out.
On the data side, Richard Masters, VP of Data and AI, says: "Codex has really helped us unblock and de-risk various migrations of databases onto our core data warehouse." Analyst teams across network planning, customer experience, and engineering and maintenance now prototype internal applications directly against the data warehouse with Codex, rather than routing requests through the central Data and AI team.
Looking ahead, Letchford asks: "How do we start scaling this up, not just in pockets, but across that whole software development lifecycle?" Masters adds that "The trajectory of Codex is thinking beyond pure engineers. It's moving into a real tool for everyone."