Reported impact
Business outcome
Nelen & Schuurmans improved product usability, expanded the number of supported user interactions and opened a strong ROI path for premium generative features on Rana.
- Productivity Improvement
- Revenue Growth
IBMCommercial and Professional ServicesEnterprise Knowledge SearchData AnalyticsGenerative AI / LLMProductivity ImprovementRevenue Growth2025 IBMIBM#0f62feCommercial and Professional ServicesNetherlandsNelen & Schuurmans wanted to make its Rana water-intelligence platform easier to use by turning complex documentation and workflows into guided assistance for hydrodynamics modeling users.2,132% ROI for paid code-generation prompt packsMar 25, 20256Enterprise Knowledge SearchIBM watsonx.ai · IBM watsonx.data0 2025-03-25 6
Nelen & Schuurmans
Enterprise Knowledge Search
Nelen & Schuurmans wanted to make its Rana water-intelligence platform easier to use by turning complex documentation and workflows into guided assistance for hydrodynamics modeling users.
2,132% ROI for paid code-generation prompt packs
265% increase in capacity to host free-user interactions
Solution
Nelen & Schuurmans worked with IBM Ecosystem Engineering to add a generative AI assistant to Rana, its hydrodynamics and water-intelligence platform. The solution uses IBM watsonx.ai together with IBM watsonx.data in a retrieval-augmented architecture that transforms documentation into indexed, semantically searchable knowledge and generates code snippets and guidance for users. IBM and Nelen & Schuurmans refined the source material with semantic chunking so the assistant could provide more grounded answers during modeling workflows. Users can ask questions through the application interface and receive relevant instructions, API-call guidance and contextual explanations without navigating manuals manually. The design improves accessibility for less experienced users while also creating a revenue path for premium prompt packs and advanced interactions, making the assistant both a usability feature and a commercial extension of the Rana platform.
Data flow
Rana documentation is semantically chunked and indexed in watsonx.data, retrieved based on user questions and then combined with watsonx.ai generation to return guidance, API snippets and workflow explanations inside the Rana interface.
Solution architecture
- Compute
- IBM watsonx.ai Generates guidance, answers and code snippets for Rana users during modeling workflows.
- Storage
- IBM watsonx.data Stores and indexes refined documentation to support semantic retrieval and grounded responses.
Architecture clues
- Built as a retrieval-augmented generation architecture
- Supports both interface guidance and API-call code generation
- Uses semantic chunking to refine source documentation
Evidence from the source
Capacity to host free-user interactions exceeded expectations by 265%.
The implementation process involved collaboration ... around a retrieval-augmented generation (RAG) solution architecture, using a semantic chunking methodology.
The solution uses both IBM watsonx.ai® and IBM watsonx.data® to transform and index documentation, provide semantic search capabilities and generate API call code snippets for users.
Transparency Evidence & methodology
Review how this reference was scored and trace each normalized claim back to its documented source.
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 clarity20/20Measures whether the customer's operational problem is specific enough to compare.
- Implementation depth25/25Rewards named components, data flow, integrations, and architecture detail.
- Outcome specificity20/20Measures whether the reported benefit is concrete rather than a generic claim.
- Quantified impact25/252 metrics describe measurable impact.
- Deployment scale10/10Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence84%
- Source authority20/25The main evidence is an official vendor-published customer story.
- Claim traceability21/2510 of 12 key fields link to a named source.
- Direct evidence15/203 direct source quotes retained.
- Date provenance10/10The publication date comes from the source page or publisher.
- Source transparency8/101 source reference document publisher, URL, authority, retrieval, and supported fields.
- Implementation specificity10/10Rewards source-backed components, data flow, quantified impact, and a specific outcome.
Traceability
Sources & provenance
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
- https://www.ibm.com/case-studies/nelen-schuurmansIBMFirst-party
Nelen & Schuurmans customer story
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
- Published on source page Mar 25, 2025 · IBM · First-partyOpen date source
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.
Related
Similar use cases
IBM Sample Dec 10, 2025 Tech Mahindra 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 IBM Deep Search · IBM Granite 13b · IBM watsonx.ai IBM Sample Dec 9, 2025 LDS Łazewski Depo & Partners 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 IBM watsonx.ai IBM Sample Sep 8, 2025 C-Metric C-Metric needed to help a healthcare-services client search fragmented document repositories, reduce data errors and make compliance-heavy workflows faster and more reliable. 40% reduction in operational costs Aivio · IBM Granite · IBM Watson Discovery