# How Booking.com Boosted Agent Accuracy 2x with Mini LLMs with Pranav Pathak

Page: https://stenobird.com/podcast/beyond-the-pilot-enterprise-ai-in-action-7531113/how-booking-com-boosted-agent-accuracy-2x-with-mini-llms-with-pranav-pathak
Text version: https://stenobird.com/podcast/beyond-the-pilot-enterprise-ai-in-action-7531113/how-booking-com-boosted-agent-accuracy-2x-with-mini-llms-with-pranav-pathak.md
Podcast: [Beyond The Pilot: Enterprise AI in Action](https://stenobird.com/podcast/beyond-the-pilot-enterprise-ai-in-action-7531113)
Published: 2025-12-03T11:30:00+00:00
Episode link: https://traffic.megaphone.fm/UTEAU2545255799.mp3?updated=1764696558
Audio file: https://traffic.megaphone.fm/UTEAU2545255799.mp3?updated=1764696558
Processing state: not_requested
JSON: https://stenobird.com/v1/public/podcasts/beyond-the-pilot-enterprise-ai-in-action-7531113/episodes/how-booking-com-boosted-agent-accuracy-2x-with-mini-llms-with-pranav-pathak
Duration seconds: 2747

## Resource

We built AI agents by accident... and it worked. 🤯 In this episode of VentureBeat’s Beyond the Pilot, we go inside the engineering brain of Booking.com with Pranav Pathak (Director of Product Machine Learning). Pranav reveals how they "stumbled" into agentic architectures before the term even existed, how a simple text box revealed a massive missed revenue opportunity (the "Hot Tub" story), and exactly how they stack LLMs, RAG, and Orchestrators to handle millions of travelers without breaking the bank. If you are building Enterprise AI, this is the blueprint for moving from "cool demo" to production scale. 🚀 In this episode, we cover: The "Hot Tub" Revelation: How free-text AI search exposed features customers desperately wanted but couldn't find. Real ROI Metrics: How LLMs drove a 2x increase in topic detection accuracy and freed up 1.5x of agent bandwidth. The Booking.com AI Stack: A full breakdown of their Orchestrator → Moderation → Agent → RAG architecture. Latency vs. Intelligence: Why they don't use GPT-5 for everything and how they decide between small models and big brains. The Memory Problem: How to build AI that remembers user preferences without being "creepy”. 00:00 Introduction to Agentic Architectures 00:30 Meet Pranav Pathak from Booking.com 01:24 Evolution of Travel Recommendations 03:41 Impact of Gen AI on Customer Service 07:29 Building an Effective AI Stack 10:32 Agentic Systems and Best Practices 13:45 Choosing Between Building and Buying AI Solutions 18:51 Evaluating AI Models for Business Use 24:10 Challenges in Human Evaluation 25:06 Recommendation System and Data Utilization 27:26 Innovations in Travel Search 29:04 Journey and Challenges in ML Integration 32:08 Managing Memory and User Data 38:07 Future of Travel Assistance 41:33 Advice for Ne…

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/beyond-the-pilot-enterprise-ai-in-action-7531113/episodes/how-booking-com-boosted-agent-accuracy-2x-with-mini-llms-with-pranav-pathak/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/beyond-the-pilot-enterprise-ai-in-action-7531113/how-booking-com-boosted-agent-accuracy-2x-with-mini-llms-with-pranav-pathak.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.