Perry Ellis · Yotpo
1.4% — conversion rate
Independently reportedRetail & e-commerce · Customer support · NLP · Scaled
Customer support
TourRadar · boost.ai
Vendor-reportedTravel & hospitalityIn productionEnterpriseLLMLive 2024
Vendor-reported. The customer is named and the numbers are quoted from the source page, but the account comes from the vendor. No independent confirmation.
Reported by boost.ai (vendor self-report). Checked against the source page on 2026-09-05. 8 of 8 figures below appear on that page word for word.
The problem
Managing a high volume of diverse customer inquiries daily, handling over 5,000 chat interactions per month while serving a global base of 2 million+ travelers, requiring timely, relevant support across multiple time zones.
What was deployed
- Vendor
- boost.ai
- Products
- boost.ai platform, Generative Action
- Technique
- LLM
- Build or buy
- Bought off the shelf
- Deployment
- SaaS
- Data used
- approved knowledge sources, content directly from over 50,000 operator and supplier-provided tour pages, database of over 50,000 organized adventures
- Scale
- handles over 5,000 chat interactions per month, serves a global base of 2 million+ travelers, reads content from over 50,000 tour pages
What changed
Each row is quoted from the source. Figures we could not find on the page in those words are marked — they are kept, not deleted, so you can judge them.
82%customer inquiries handled automatically by AI Agent
“The AI Agent now handles 82% of all customer inquiries”
Quoted word for word from the source
80%Live chat deflectionfrom 50%
“Live chat deflection improved from 50% to 80%, a 30-point gain in automation efficiency.”
Quoted word for word from the source
98%accuracy rate of responses
“Responses boast a 98% accuracy rate, ensuring customers receive reliable information.”
Quoted word for word from the source
780+hours saved across chat and messaging supportper month
“780+ hours saved per month across chat and messaging support”
Quoted word for word from the source
200hours saved on human-written repliesper month
“This feature alone saves the team approximately 200 hours per month on written replies.”
Quoted word for word from the source
580hours saved on human assistance on Live Chatper month
“approximately 580 hours saved per month on human assistance on Live Chat”
Quoted word for word from the source
60%CSAT score for AI-handled chat messages
“Furthermore, the chat messages handled by the AI Agent have achieved a 60% CSAT score, demonstrating positive customer reception.”
Quoted word for word from the source
20%escalation rate to human agent
“The AI Agent successfully resolves a majority of conversations directly, with only 20% requiring escalation to a human agent, freeing up the human team to focus on more complex and high-value customer interactions.”
Quoted word for word from the source
“Since switching to boost.ai, we’ve gone from a rigid, keyword-based chatbot to a 24/7 AI Agent that now handles 80% of live chat inquiries with 98% accuracy. That level of automation lets us support customers around the globe without adding headcount.”
Difficulties and limits
- managing a high volume of diverse inquiries daily
- providing timely, relevant support across multiple time zones
- avoiding limitations of traditional rules-based chatbots
Sources
- boost.ai — vendor self-report
Similar deployments
Innovative Dining Group · Revmo AI
1200+ — Reservations booked by AI
Vendor-reportedTravel & hospitality · Customer support · NLP · In production · 2025
Houston Methodist · ActiumHealth
18000000 — staffing capacity created
Vendor-reportedHealthcare · Customer support · LLM · In production
Luxury Bath NJPA · Hatch AI
52% — Overall set rate
Vendor-reportedConstruction & real estate · Customer support · AI agents · Scaled
Radiant Credit Union · interface.ai
60% — Asset growth absorbed without contact center team expansion
Vendor-reportedBanking & finance · Customer support · LLM · Scaled · 2022
Talkmobile · LivePerson
92% — Customer Satisfaction Score (CSAT)
Vendor-reportedTelecom · Customer support · NLP · Scaled · 2014