Use Case Intelligence RSS Search use cases Search
IBM Software / SaaS Global

GigaSpaces

Enterprise Knowledge Search

GigaSpaces needed a faster way to let enterprise users query complex structured data with generative AI because conventional approaches to databases and metadata were too unintuitive and inaccurate for natural-language access.

Read the original story Explore all use cases
days instead of months to prototype an assistant based on eRAG
near 95% accuracy rate with eRAG approach is the mission
up to 55% accuracy rate

Reported impact

Business outcome

GigaSpaces accelerated prototyping, raised the expected accuracy of natural-language access to structured data, and created a reusable AI layer for mission-critical digital services.

  • Productivity Improvement
  • Scalability

Solution

GigaSpaces used IBM watsonx.ai and IBM watsonx Assistant to build an enterprise retrieval-augmented generation platform aimed at structured enterprise data. The architecture places watsonx Assistant at the front end as the conversational interface and uses watsonx.ai to power the query, reasoning, and summarization flow behind it. GigaSpaces layered semantic enrichment and vector caching on top of its Digital Integration Hub approach so metadata reasoning and retrieval could work across operational datasets such as sales records, inventory, order payments, and marketing analytics. This allowed the R&D team to prototype the experience in days rather than months and to focus on improving the core eRAG logic. The resulting design turns complicated structured datasets into a natural-language service layer that can surface business insight more accurately than generic AI-to-database methods, while leaving room for future governance controls as the platform matures.

Data flow

Structured enterprise data and metadata are enriched inside the eRAG platform, watsonx.ai reasons over the retrieved context using semantic enrichment and vector caching, and watsonx Assistant returns the answer through a conversational interface.

Solution architecture

2 components · 2 layers
  1. Compute
    • IBM watsonx.ai Provides the LLM-driven query, reasoning, and summarization capabilities behind the eRAG platform.
  2. Serving
    • IBM watsonx Assistant Serves as the conversational front end through which users query enterprise structured data in natural language.

Architecture clues

  • The solution combines semantic enrichment and vector caching to improve metadata reasoning and retrieval.
  • The target datasets include sales, inventory, order-payment, and marketing-analytics records.
  • watsonx Assistant is the front end while watsonx.ai powers query and summarization.

Evidence from the source

"By using the advanced LLMs on IBM watsonx.ai and applying techniques like semantic enrichment and vector caching"
"The GigaSpaces team is building the new solution using IBM watsonx.ai and IBM watsonx Assistant"
"near 95% accuracy rate with eRAG approach is the mission"
"significantly reduced its time to prototype an assistant ... to within several days, instead of months"
Transparency Evidence & methodology 85/100 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 value85/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth20/25
    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 scale0/10
    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

    GigaSpaces customer story

    First-party
    https://www.ibm.com/case-studies/gigaspaces
    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 Jul 31, 2026 Crazylog Software / SaaS France Crazylog needed to help industrial maintenance technicians find trusted technical information quickly during equipment failures, even as documentation volumes, compliance needs, and workforce turnover made field… 10 frontline naval vessels Enterprise Knowledge SearchPredictive Maintenance IBM Cloud · IBM watsonx.ai · IBM watsonx.data IBM Mar 28, 2026 Shorthills AI Software / SaaS Global Shorthills AI needed to make legal research more comprehensive and trustworthy across very large corpora without forcing users to accept incomplete, hallucinated or weakly sourced answers. 4X increase in comprehensiveness Enterprise Knowledge Search IBM watsonx.data · Langflow IBM Mar 24, 2026 IBM Human Resources Software / SaaS Global IBM HR needed to make people analytics easier for business leaders and non-technical users because dashboard growth alone still left managers dependent on analysts to interpret metrics, filters, and workforce context. 20% each year initial self-serve Dashboards Adoption Growth Enterprise Knowledge SearchReal-time Analytics IBM Cognos · IBM watsonx BI