it_support · travel · workflow
Booking.com scales AI to 14,000 employees and redefines work with Glean
Booking.com juggled numerous workplace applications with inefficient information access, resulting in stale data, inefficient collaboration, and reduced productivity—while needing to comply with strict security and GDPR requirements.
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 · Employee natural language query
Employees and IT technicians query their needs in natural language.
Tools used
Glean
Outcome
Glean reduced video script creation time from 8 to 2 weeks and increased output from 2 to 5 videos per month; IT ticket resolution dropped from up to 10 minutes to little to no time; Glean became the first AI platform adopted company-wide at Booking.com across 14,000 employees.
What failed first
Booking.com tried several other search solutions before Glean, but none met their needs.
Results
Time saved8 to 2 weeks
Volume2 to 5 videos per month
Grounding & classification
Source type: vendor customer story
29 fields verified against source quotes.
agentic workflowai agentcontent generationenterprise searchknowledge searchknowledge basesupport ticketfailure mode describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedtravelcycle time reductionemployee productivityresolution time reductionthroughput increasevendor customer storyback office opsit supportmarketing opsautonomous resolutionrag answering