Use Case Intelligence RSS Search use cases Search
IBM Public Sector Ireland

SOLAS

Customer Service Automation

SOLAS needed a better way to answer repetitive fetchcourses.ie support questions so adult learners could get immediate help without tying up scarce IT staff on simple issues.

Read the original story Explore all use cases
50% reduction
around 30 of the most common questions
hundreds of hours annually
one-year pilot project

Reported impact

Business outcome

The assistant cut incoming support-query volume by 50%, saves potentially hundreds of staff hours annually and frees SOLAS specialists to focus on higher-value work while learners get quicker answers.

  • Customer Experience
  • Productivity Improvement

Solution

SOLAS worked with SureSkills, Education and Training Boards Ireland and Ludex to build "Dave," a virtual assistant on fetchcourses.ie using IBM watsonx Assistant. The team cataloged about 30 of the most common support and course-related questions, then prepared ten variants of each so the assistant could recognize different phrasings. Answers were written in plain English, tested iteratively and adjusted with attention to GDPR implications and handoff needs. In production, the assistant handles common problems such as forgotten passwords, duplicate accounts and other navigation questions directly on the site, while more complex cases are routed to the relevant human support path. The implementation acts as a front-door service layer for lifelong-learning support: website users ask for help, watsonx Assistant matches intent against the curated Q&A set, and SOLAS staff only intervene on exceptions that genuinely need specialist attention.

Data flow

Learners ask for help on fetchcourses.ie, watsonx Assistant matches the request against the curated question-and-answer variants, returns plain-English answers for common problems, and leaves more complex cases for SOLAS or ETB human support teams.

Solution architecture

1 components · 1 layer
  1. Serving
    • IBM watsonx Assistant Powers the virtual assistant that answers common learner questions and routes harder cases to human support.

Architecture clues

  • Answers were prepared in plain English to maximize accessibility for learners.
  • The team explicitly considered GDPR implications when training the assistant.
  • Usage data is gathered after go-live to identify unanswered questions and future improvements.

Evidence from the source

"Our team member responsible for incoming support queries has seen a 50 percent drop in volume."
"SOLAS and ETBI collated a list of around 30 of the most common questions, preparing ten variants of each one"
"The requests reaching us now are related to more complex issues that really require specialist support."
"To build Dave, our fetchcourses.ie virtual assistant, we added the Q&As to Watson and then worked with Ludex to iteratively train, test, adjust, and retrain the system"
"saving potentially hundreds of hours annually"
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

    SOLAS customer story

    First-party
    https://www.ibm.com/case-studies/solas
    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.

Related

Similar use cases

See all like this
IBM Nov 14, 2024 Arizona Department of Child Safety Public Sector North America Arizona DCS needed to reduce manual casework, document handling, policy navigation, and development overhead so staff could make child-safety decisions faster and spend less time on administrative work. 40% productivity gain Customer Service AutomationDocument Processing IBM Consulting Advantage for Cloud Transformation · Microsoft Azure · Microsoft Azure OpenAI IBM Nov 12, 2024 INAIL Public Sector Italy INAIL needed to absorb a surge in grant-funding inquiries and application volume for its Bandi ISI program without overwhelming the contact center or delaying applicant guidance during the submission and admission… 2 months Customer Service AutomationEnterprise Knowledge Search IBM Watson Discovery · IBM watsonx Assistant · IBM watsonx.ai IBM May 14, 2024 City of Helsinki Public Sector Finland The City of Helsinki needed to improve citizen service speed and flexibility, reduce pressure on overworked customer-service teams, and connect siloed service organizations without compromising privacy for sensitive… 10 virtual assistants currently running Customer Service Automation IBM Cloud · IBM Consulting · IBM Garage