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

Formez PA

Enterprise Knowledge Search

Formez PA needed a way to standardize public-sector professional profiles, skills, and terminology so agencies could compare roles, exchange data, and collaborate without being blocked by incompatible dictionaries and manual profile entry.

Read the original story Explore all use cases
60% expected increase in user satisfaction
80% expected improvement in search accuracy
90% expected reduction in time spent on data entry and processing tasks

Reported impact

Business outcome

Formez PA expects to reduce manual profile management work, improve search accuracy, and make professional-role data more consistent and usable across public administrations.

  • Customer Experience
  • Productivity Improvement
  • Scalability

Solution

Formez PA and IBM Client Engineering embedded AI into the RiVa portal to turn public-sector professional profiling into a semantic search and classification workflow. User descriptions are converted into embeddings with IBM watsonx.ai using the Llama model, while IBM watsonx.data—backed by Milvus as a vector database—executes semantic searches to find professional profiles that are conceptually similar even when keywords do not match. A custom microservice exposes APIs between the RiVa portal and the IBM services, and optional filters for contractual areas, professional dimensions, and professional families help narrow the result set. The solution can suggest profile names, organizational purposes, and primary activities from user descriptions and is designed to expand into skills and role recommendations over time. In practice, RiVa becomes a governed semantic layer for public-sector HR data rather than a static profile-entry form.

Data flow

Public-sector role descriptions entered into the RiVa portal are converted to embeddings with watsonx.ai, searched semantically in watsonx.data and Milvus, filtered by public-administration criteria, and returned through RiVa as suggested profiles, activities, and future skill recommendations.

Solution architecture

6 components · 3 layers
  1. Compute
    • IBM watsonx.ai Converts natural-language descriptions into embeddings and interprets public-sector HR requests.
  2. Storage
    • IBM watsonx.data Runs semantic searches across vectorized professional profiles and skills data.
    • Milvus Provides the vector database used to search for semantically similar professional profiles.
    • IBM Cloudant Supports cloud-native data persistence in the solution's API and feedback workflows.
  3. Orchestration
    • IBM Code Engine Supports the microservice layer that exposes APIs between RiVa and the IBM AI services.
    • IBM Cloud Hosts the cloud components that integrate the semantic search and API services.

Architecture clues

  • A microservice intermediary converts requests into embeddings and invokes vector search APIs.
  • The solution uses semantic similarity rather than exact keyword matching.
  • User feedback is built into the product to refine results over time.

Evidence from the source

IBM watsonx.data, which leverages Milvus as its vector database to execute semantic searches within vector spaces.
The solution leverages the IBM watsonx portfolio of products to translate user queries into embeddings.
approximately 80% increase in search precision
approximately 90% reduction in manual data entry and data processing
the IBM–Formez team devised a microservice to expose APIs.
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
    3 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
    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

    Formez PA customer story

    First-party
    https://www.ibm.com/case-studies/formez-pa
    Source type
    Vendor-published customer story
    Published
    May 19, 2025
    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 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 2, 2024 Austrian Armed Forces Public Sector Austria The Austrian Armed Forces needed a trustworthy way to query large volumes of open-source and internal documentation because users required fact-based answers with traceable sources, low hallucination risk, and human… Enterprise Knowledge SearchSecurity and Compliance ChatZentDoc · IBM Client Engineering · IBM Watson Explorer