Use Case Intelligence RSS Search use cases Search
IBM Nonprofit Italy

ASPHI Onlus

Document Processing · Enterprise Knowledge Search

ASPHI Onlus needed a better way to make reading materials accessible for people with hearing or cognitive impairments and non-native Italian speakers because conventional text experiences created barriers to learning and engagement.

Read the original story Explore all use cases
4 weeks
Expected increase in accessibility of ASPHI services up to 100,000 users
Students will be able to read at least 30 narrative documents a year

Reported impact

Business outcome

ASPHI expects to broaden access to reading, reduce drop-off from education programs, and scale personalized learning support for a much larger population of readers.

  • Customer Experience
  • Productivity Improvement
  • Scalability

Solution

ASPHI Onlus, IFAB, and IBM Client Engineering ran a four-week proof of concept to build a more accessible reading and learning environment on IBM watsonx. The resulting platform, Limpide Letture, uses IBM watsonx.ai to classify text, generate titles and summaries, simplify reading passages, produce quizzes, and recommend suitable learning paths. A companion assistant named LucIA uses watsonx Assistant to answer questions about the text in real time. IBM Cloud Code Engine provides the runtime layer for the application, while IBM Cloudant stores documents and session data so the experience can scale without heavy infrastructure maintenance. This architecture turned static written material into an interactive accessibility service that combines content transformation, knowledge assistance, and personalization for readers with different abilities and language proficiency levels.

Data flow

Reading content is classified and simplified by watsonx.ai, LucIA uses watsonx Assistant to answer questions about the material, and Cloudant plus Code Engine store and serve the documents and session interactions needed by the application.

Solution architecture

4 components · 3 layers
  1. Compute
    • IBM watsonx.ai Simplifies texts, generates summaries and titles, and powers the adaptive reading features in Limpide Letture.
  2. Storage
    • IBM Cloudant Stores large volumes of documents and session data used by the reading platform.
  3. Serving
    • IBM watsonx Assistant Drives the LucIA virtual assistant that answers questions about texts on demand.
    • IBM Cloud Code Engine Provides the scalable runtime environment for the accessibility application.

Architecture clues

  • Cloudant and Code Engine were chosen to avoid heavy maintenance while supporting large volumes of documents and sessions.
  • The proof of concept used both foundation-owned data and public data.
  • The solution includes both a content-transformation engine and a text-questioning assistant.

Evidence from the source

"The POC ran for 4 weeks."
"The virtual assistant is built on watsonx.ai and deploys watsonx Assistant"
"Using watsonx's robust analytical abilities, they developed a tool that simplifies reading"
"up to 100,000 users"
Transparency Evidence & methodology 100/100 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 value100/100
  • 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 impact25/25
    2 metrics 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
    4 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

    ASPHI Onlus customer story

    First-party
    https://www.ibm.com/case-studies/asphi-onlus
    Source type
    Vendor-published customer story
    Published
    Nov 6, 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 Feb 25, 2026 General State Attorney’s Office Public Sector Spain The General State Attorney’s Office needed to manage and access a very large volume of legal information more efficiently so legal professionals could find relevant precedents, compare lawsuits, and prepare responses… Document ProcessingEnterprise Knowledge Search IBM cloud · IBM watsonx · TEMIS IBM Dec 10, 2025 Tech Mahindra Commercial and Professional Services Global Tech Mahindra needed a way to extract value from long, complex, unstructured enterprise documents while also proving that generative-AI outputs could be governed, explained, and trusted in regulated customer… 30% productivity improvement Document ProcessingEnterprise Knowledge Search IBM Deep Search · IBM Granite 13b · IBM watsonx.ai IBM Dec 9, 2025 LDS Łazewski Depo & Partners Commercial and Professional Services Poland LDS needed to reduce the time, cost and risk involved in manual patent searches and drafting work so its attorneys could protect clients' intellectual property more efficiently without sacrificing accuracy or data… over 40 IP professionals Document ProcessingEnterprise Knowledge Search IBM watsonx.ai