Skip to main content

System status

Coverage is stale.

Collection is paused. Latest public event: Aug 21, 2026 (11 days ago).

← Intel index

This coverage is stale.

Last updated May 20, 2026 (about 3 months ago).

distribution · May 20, 2026

Weaviate Podcast Episode 138 Features Booking.com Platform Engineer Başak Eskili on Production-Scale Vector Search

Share the canonical public link.

Share as image

Connor Shorten from Weaviate hosted Weaviate Podcast Episode 138 with Başak Eskili from Booking.com on May 18, 2026. The episode details Booking.com's evaluation of Weaviate using 100 million embeddings along with filtered vector search, multi-threaded concurrency, and simultaneous read-write tests. Booking.com shifted from keyword matching to semantic retrieval and now runs a partner-to-guest messaging agent handling tens of thousands of daily exchanges with Weaviate retrieving response templates. Başak Eskili described the tool-calling architecture and human-in-the-loop design at Booking.com.

Below validation threshold — auto-passed without scoring

Supporting evidence