Booking.com and Weaviate with Başak Eskili - Weaviate Podcast #138!

Weaviate vector database · Intermediate ·🤖 AI Agents & Automation ·5h ago
Başak Eskili joins the Weaviate Podcast to explore how one of the world’s largest travel platforms adopted vector search, retrieval-augmented generation, and agentic AI at production scale. The conversation begins with Booking.com’s shift from keyword matching to semantic retrieval as internal teams needed embeddings, similarity search, and eventually GenAI RAG workflows. Başak explains why OpenSearch was a practical first step on AWS, how adoption grew across teams, and why hundreds of millions of embeddings, strict latency requirements, complex filtering, and rising concurrency pushed the platform toward Weaviate. The discussion then moves into Booking.com’s partner-to-guest messaging agent, a production GenAI system that helps accommodation partners answer guest questions about check-in, parking, special requests, and reservation details. Başak breaks down the tool-calling architecture, where Weaviate retrieves relevant response templates while GraphQL APIs fetch property and booking context. The agent can suggest templates, craft grounded replies, or decline to answer and leave the conversation to a human, highlighting the practical role of human-in-the-loop design. Evaluation spans offline datasets, LLM-as-a-judge scoring, A/B testing, and live partner feedback. From there, Başak describes the platform engineering behind AI at Booking.com: a central MCP server for internal APIs and external tools, a GenAI gateway for model access, PII reduction, guardrails, prompt injection detection, logging, traceability, and cost tracking across large-scale LLM usage. She also details Booking.com’s evaluation process of Weaviate, including 100 million embeddings, filtered vector search, multi-threaded concurrency testing, reads during writes, and cost-efficient infrastructure provisioning. The episode closes with Başak’s path from computer science and NLP to MLOps and AI platforms, then looks ahead to practical AI, personalized travel agents, and memory systems that captu
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Related AI Lessons

Prescriptive actions for BFSI Banking: next-best workflow tasks, escalation, and value realization
Learn how to implement prescriptive actions in BFSI banking for next-best workflow tasks, escalation, and value realization using AI and ML
Dev.to · Ananthapathmanabhan A
I red-teamed Oracle APEX 26.1's new AI Agent feature in the 72 hours after it went GA. Claude refused 7 of my 10 attacks on its own.
Learn how to red-team test Oracle APEX 26.1's new AI Agent feature and understand its security vulnerabilities
Dev.to · Ranjith Kumar Kondoju
OpenClaw told me it failed its own trust test, and that’s the real story
Learn how OpenClaw's self-reported failure on its own trust test reveals more about agent reliability than polished benchmarks
Dev.to AI
OpenClaw outbound agents need deliverability checks before sending
Implement deliverability checks for OpenClaw outbound agents to ensure emails land in the inbox, reducing operational risk
Dev.to AI
Up next
Introducing Gemini Enterprise Agent Ready
Google Cloud
Watch →