2025-11-05 –, Eng
In this practical talk, we share how Booking.com built its AI Trip Planner—an LLM-powered experience that personalizes travel planning at scale. We’ll walk through real-world design decisions, technical challenges, and infrastructure optimizations involved in delivering real-time hotel and destination recommendations using large language models (LLMs).
We’ll cover key challenges like moderating user input, classifying intent, structuring dialogues, and generating grounded responses. Through prompt engineering and custom model development, we tailored LLM interactions to our product needs while ensuring speed and relevance.
To address inference latency, we implemented speculative decoding and integrated Medusa-1, a novel architecture that predicts multiple tokens in parallel, achieving a 1.8x speedup with no loss in quality. We’ll detail its design and training trade-offs.
Beyond acceleration, we’ll highlight our move toward agentic AI systems—modular components that orchestrate LLMs, retrieval services, and Booking.com APIs to solve complex travel queries. For example:
A Question-Answering Agent that fuses LLMs, real-time data, and APIs for context-aware answers.
An Itinerary-Building Agent that generates dynamic, multi-step travel plans by integrating user preferences and live availability.
Finally, we’ll show how we evaluate quality in production using LLM-based evaluations, including Judge LLMs for automatic assessment, dialog quality and more.
Attendees will leave with practical insights into building and scaling LLM systems—from architecture and inference to evaluation and agentic design—based on real deployment at Booking.com.
No previous knowledge expected
Moran is a Senior Machine Learning Manager at booking.com, researching and developing GenAI, NLP and CV models for the tourism domain.
Moran is a Ph.D candidate in information systems engineering at Ben Gurion University, researching NLP aspects in temporal graphs.
Previously worked as a Data Science Team Leader at Diagnostic Robotics, building ML solutions for the medical domain and NLP algorithms to extract clinical entities from medical visit summaries.
Machine Learning Manager with advanced skills in GenAI, Agentic flows, Recommendations, Reinforcement learning algorithms and simulations. In addition, experienced in Operations Research with a demonstrated history of working in the Defense & Space industry, Autonomous vehicles and E-commerce recommenders. Skilled in Conceptual System Design, Machine Learning, Numerical Simulation, Statistical Data Analysis, Discrete Event Simulation, and Python (Langgraph, Pyspark, Pytorch, Scipy, Pandas etc.). Strong research professional with a Master's degree in Applied Mathematics from Technion - Israel Institute of Technology. Thesis focuses on Combinatorial Optimization problems with multi agents and reinforcement learning algorithms. Recenetly Focused on GenAI for the travel industry including free text search, ai trip planner and other travel products utilizing GenAI to under user queries.