customer_support · logistics · workflow
Ask Julie intelligent virtual assistant delivers 8x ROI and 32% containment increase for Amtrak
Amtrak wanted to provide instant self-service to its more than 375,000 daily web visitors, giving them answers and transaction assistance without requiring them to call or email a representative.
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 · Traveler states travel request
Travelers can book rail travel by simply stating where and when they'd like to travel.
Tools used
Ask JulieVerint IVA
Outcome
Ask Julie delivered an 8x return on chatbot investment, a 32% increase in containment, and 30% more revenue per booking, while answering over 5 million questions annually and reducing call volumes and handle times for live agents.
Results
Time savedlower call volumes and handle times
Volume8x
Cost replaced30%
Grounding & classification
Source type: vendor customer story
26 fields verified against source quotes.
chatbotconversational aisupport agentchat transcriptmetric backednamed customerproduction runtime claimedtools describedvendor confirmedworkflow describedtraveldeflection rateresolution time reductionrevenue increasevendor customer storycall center aicustomer supportorder processingautonomous resolutionescalation workflow