IBM Education Italy

Trinity ViaggiStudio

Customer Service Automation · Sales Automation

Trinity ViaggiStudio needed to answer growing volumes of real-time questions from students, parents, companions, universities, and partner colleges, but manual service across messaging channels could not keep pace or support higher website conversion.

3 offices in Europe
6,000 students per year
70 destinations on 5 continents
about 85% of the overall questions asked by website visitors

Reported impact

Business outcome

Trinity created always-on self-service, reduced customer-service workload, captured qualified leads from conversations, and improved the speed and quality of responses for prospective travelers and their families.

  • Customer Experience
  • Productivity Improvement
  • Revenue Growth

Solution

Trinity ViaggiStudio worked with IBM Business Partner Ubico to build Trinny, a 24x7 website assistant based on IBM watsonx Assistant. The implementation centered on a live-chat widget for site visitors and a knowledge layer built from Trinity's FAQs and service responses, including content that initially came from an Excel-based source and was then expanded through gradual uploads. Watsonx Assistant provides the natural-language understanding and response engine, while the operating process around it continuously monitors conversations to identify new intents or gaps in the knowledge base. The assistant now handles more than 120 trained question types, answers most routine website inquiries autonomously, and directs prospects to relevant catalog downloads, contact forms, and appointment-booking pages. The design gives Trinity one conversational front end for support and lead generation, while its roadmap extends that experience toward CRM integration and guided study-program selection.

Data flow

Questions from website visitors enter the Trinny chat widget, watsonx Assistant matches them against the uploaded FAQ and customer-service content, answers routine queries, and routes interested prospects to catalog, contact, or appointment pages while conversation feedback is used to improve future responses.

Solution architecture

1 components · 1 layer
  1. Compute
    • IBM watsonx Assistant Powers Trinny's natural-language understanding and automated response flow for website visitors.

Architecture clues

  • The initial knowledge base could be bootstrapped from an Excel file and then expanded with additional FAQ uploads.
  • The team continuously monitors conversations to identify missing intents and improve bot training.
  • Trinity plans to connect the assistant with company software and CRM for guided experience selection.

Evidence from the source

"Now customers can get all the information they need in the blink of an eye, even when the offices are closed."
"The virtual assistant was able to collect over 150 contacts from potential customers"
"a live chat widget capable of interacting with site visitors in real-time"
"responding to over 120 questions from users"
"the system ... has so far been able to manage almost all of the questions for which it was trained to respond and about 85% of the overall questions asked by website visitors"
Transparency Evidence & methodology 90/100 reference value · 89% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value90/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity20/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact15/25
    1 metric describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence89%
  • Source authority20/25
    The main evidence is an official vendor-published customer story.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    5 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity10/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. IBM

    Trinity ViaggiStudio customer story

    First-party
    https://www.ibm.com/case-studies/trinityviaggistudio
    Source type
    Vendor-published customer story
    Published
    May 14, 2024
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date

Date evidence

Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.