QCon London 2026: Behind Booking.com's AI Evolution: The Unpolished Story

Editor's take

Booking.com's Senior Principal Engineer shared a candid account of the company's journey integrating generative AI, highlighting the practical challenges and iterative development behind their AI deployments.

This presentation offers a valuable counterpoint to the often-hyped narratives surrounding AI adoption, revealing the messy reality faced by large enterprises like Booking.com as they move from experimentation to production. It underscores the significant engineering effort required to make AI useful and reliable for millions of users, directly impacting customer experience and operational efficiency.

Future discussions should focus on how Booking.com is addressing the ongoing costs and complexity of maintaining these AI systems, particularly concerning model drift, bias mitigation in large-scale recommendation engines, and the integration of new open-source models like Llama 3 or Mistral Large into their existing infrastructure. Success will be measured by sustained performance improvements and cost-effectiveness.