customer_support · travel · workflow
Forethought AI enables 72% self-serve rate and 96% sentiment accuracy for Kickfin customer support
Kickfin needed to provide 24/7 customer support for restaurant and hospitality workers accessing the platform at 2–4 AM, but relied on overnight human staffing that was hard to fill and impossible to cover on short notice. Training new reps was also a significant burden on support leadership.
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 · Customer submits inquiry via widget
Customers interact with Kickfin's chat widget on its public website or password-protected customer support portal.
Tools used
ForethoughtSolveAssistTriageLarge Language ModelsSalesforce · partner
Outcome
Kickfin achieved a 72% self-serve rate and over 2,000 chat deflections with Forethought Solve, eliminating the need for overnight staffing. Triage predicts customer sentiment with 96% accuracy.
What failed first
Before Forethought, Kickfin had no automation tools for customer self-service, forcing the team to staff overnight human shifts that were chronically difficult to fill and cover.
Results
Time saved96%
Volume72%
Grounding & classification
Source type: vendor customer story
33 fields verified against source quotes.
conversational aiknowledge searchsentiment analysissupport agentchat transcriptknowledge basesupport tickethuman review describedmetric backednamed customerproduction runtime claimedtools describedworkflow describedhospitalityaccuracy improvementautomation ratedeflection ratetime savedvendor customer storycustomer supportticket triageautonomous resolutionintake to triage