customer_support · travel · workflow
Booking.com builds a GenAI agent to assist accommodation partners with guest message responses
Partners at Booking.com manually replied to each guest inquiry, and even when response templates existed they still had to search for and select the right one. During busy periods this extra effort delayed replies, leaving travelers without reassurance and sometimes leading to cancellations and lost bookings.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Guest inquiry arrives
Guests reach out with questions via Booking.com's messaging platform.
Tools used
LangGraphPythonFastAPIGPT-4 MiniMiniLMWeaviateKafkaGraphQLSuperAnnotateArizeE5-SmallMCP serverKubernetes
Outcome
The agent handles tens of thousands of partner-guest messages daily, and in live pilots the human-in-the-loop approach boosted user satisfaction by 70%, reduced follow-up messages, and sped up response times, with partners reporting less time spent on repetitive questions.
Results
Time savedsped up response times
Volume70%
Grounding & classification
Source type: technical build writeup
38 fields verified against source quotes.
agent assistagentic workflowcontent generationragchat transcriptknowledge basehuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedhospitalitytravelcustomer satisfactionemployee productivityresponse time reductiontechnical build writeupback office opscustomer supportagentic task executionai draft human approval