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

Crazylog

Enterprise Knowledge Search · Predictive Maintenance

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 troubleshooting harder.

Read the original story Explore all use cases
10 frontline naval vessels
3 customers adopted the solution within six months of production release
3× faster access to maintenance support information
~25% reduction in downtime generating ~€240K annual savings per plant

Reported impact

Business outcome

Crazylog reduced the time technicians spend searching for information, lowered downtime for customers, improved repair quality and safety, and used the new AI features to differentiate its CMMS offering in industrial markets.

  • Productivity Improvement
  • Revenue Growth
  • Risk Reduction

Solution

Crazylog embedded governed AI into its QuickBrain CMMS platform by combining IBM watsonx.ai, IBM watsonx.data, and IBM Cloud. After an experimentation phase with IBM Client Engineering and PEDAB, the production architecture introduced two AI modules: QuickSearch, which uses retrieval-augmented generation to answer natural-language maintenance questions with referenced answers grounded in documentation, and QuickAssist, which generates structured troubleshooting guidance from a failure scenario. IBM watsonx.data stores and retrieves technical documentation, asset registers, and maintenance histories as the vector-backed RAG layer, while IBM Cloud hosts the SaaS platform and watsonx.ai provides the language-model layer for both text and image tasks such as machine-nameplate recognition. The result is a field-ready knowledge workflow where technicians can query complex maintenance history and procedures directly inside the CMMS instead of searching scattered documents under pressure.

Data flow

Technical documentation, asset registers, and maintenance histories are indexed into watsonx.data, technicians query QuickBrain in natural language, watsonx.ai generates grounded answers or troubleshooting steps, and the resulting guidance is returned inside the maintenance workflow with traceable dialog history.

Solution architecture

3 components · 3 layers
  1. Compute
    • IBM watsonx.ai Provides the language-model and experimentation environment for QuickSearch and QuickAssist.
  2. Storage
    • IBM watsonx.data Stores and retrieves technical documentation and maintenance records as the vector-backed RAG layer.
  3. Orchestration
    • IBM Cloud Hosts the QuickBrain SaaS platform that delivers AI support into maintenance workflows.

Architecture clues

  • Dialogue history is retained to improve documentation and repair procedures over time.
  • QuickAssist generates structured troubleshooting guidance from specific failure scenarios.
  • QuickSearch returns referenced answers grounded in authoritative documentation.

Evidence from the source

3x reduction in the average search time for maintenance support information
Crazylog uses IBM watsonx.data as a vector database to store and retrieve relevant technical documentation
QuickAssist goes a step further by generating structured troubleshooting guidance
QuickSearch enables technicians to ask technical questions in natural language and receive referenced answers grounded in authoritative documentation using retrieval augmented generation (RAG)
customers see a ~25% reduction in equipment downtime
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
    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

    Crazylog customer story

    First-party
    https://www.ibm.com/case-studies/crazylog-pedab
    Source type
    Vendor-published customer story
    Published
    Jul 31, 2026
    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 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 IBM Jan 15, 2026 IBM Software / SaaS Global IBM needed to reduce the time employees spent on repetitive work across HR, procurement, IT, supply chain, tax, and sales while creating a repeatable enterprise blueprint for scaling AI, automation, and hybrid-cloud… 15K AI agents proposed by employees during the 2025 IBM watsonx Challenge Enterprise Knowledge SearchIT Operations Automation IBM Apptio · IBM Turbonomic · IBM Watson Discovery