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

Shorthills AI

Enterprise Knowledge Search

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.

Read the original story Explore all use cases
4X increase in comprehensiveness
9X increase in diversity of legal arguments
over 60% improvement in recall and precision

Reported impact

Business outcome

Shorthills AI delivered broader, more reliable legal research results with better recall and reasoning diversity while preserving the security posture required by regulated clients.

  • Productivity Improvement
  • Risk Reduction
  • Scalability

Solution

Shorthills AI collaborated with IBM to build a production-grade legal search platform on IBM watsonx.data. The architecture combines hybrid retrieval methods—keyword, vector and graph-based search—behind a routing layer that sends each query to the most appropriate strategy. Documents are ingested into a secure data lake, chunked intelligently and enriched with entities such as judge names, case types and citations. Embeddings are stored in watsonx.data so the system can perform semantic retrieval at scale, while Langflow helps compose the modular search workflow. The platform then reranks results and returns citation-backed answers rather than partial or opaque outputs. By treating search as a governed, multi-method retrieval problem rather than a simple chatbot prompt, Shorthills built a secure, on-premises-capable legal-research engine that improves recall, comprehensiveness and the diversity of legal reasoning for enterprise clients.

Data flow

Legal documents are ingested into a secure data lake, chunked and entity-enriched, embedded in watsonx.data and then searched through a routing layer that selects keyword, vector or graph retrieval before results are reranked and returned with citations.

Solution architecture

2 components · 2 layers
  1. Storage
    • IBM watsonx.data Stores embeddings and underpins the hybrid search platform with scalable retrieval and governance.
  2. Orchestration
    • Langflow Helps compose the modular routing and retrieval workflow used by the legal search platform.

Architecture clues

  • Entity extraction enriches documents with judge names, case types and citations
  • Suitable for on-premises deployment in regulated environments
  • Uses a modular hybrid search architecture

Evidence from the source

Shorthills AI collaborated with IBM to build a production-ready hybrid search platform using IBM® watsonx.data® and Langflow.
The team designed a modular architecture combining keyword, vector and graph-based search.
With IBM watsonx.data, Shorthills AI delivered measurable improvements: a 4X increase in comprehensiveness, a 9X increase in diversity of legal arguments and over 60% improvement in recall and precision.
Transparency Evidence & methodology 96/100 reference value · 84% 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 value96/100
  • 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 specificity16/20
    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 confidence84%
  • 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 evidence15/20
    3 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

    Shorthills AI customer story

    First-party
    https://www.ibm.com/case-studies/shorthills
    Source type
    Vendor-published customer story
    Published
    Mar 28, 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 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 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