Reported impact
Business outcome
System Research reduced the time needed to get information by making enterprise search natural-language driven, faster, and easier for employees to use on their own.
- Productivity Improvement
IBMCommercial and Professional ServicesEnterprise Knowledge SearchAI and Machine LearningGenerative AI / LLMProductivity Improvement2024 IBMIBM#0f62feCommercial and Professional ServicesJapanSystem Research needed employees to find information buried in internal documents and rulebooks without depending on supervisors or colleagues for search keywords and document-location hints.3 weeks duration of pilot for UI developmentApr 18, 20246Enterprise Knowledge SearchIBM Watson Discovery · IBM watsonx.ai0 2024-04-18 6
System Research
Enterprise Knowledge Search
System Research needed employees to find information buried in internal documents and rulebooks without depending on supervisors or colleagues for search keywords and document-location hints.
3 weeks duration of pilot for UI development
50% time reduction in getting needed information
Solution
System Research built an internal knowledge-search assistant around IBM Watson Discovery and IBM watsonx.ai to help employees find material buried in internal documents and rulebooks. Watson Discovery indexes the company's internal content and returns relevant results inside a chat-style interface, while watsonx.ai generates answers that match the intent of the user's question. During a three-week UI pilot, the team displayed Discovery results at the bottom of the chat field and tuned the experience to improve answer quality and make search more natural. The design keeps source retrieval connected to generated responses so staff can move from question to document evidence without asking supervisors for keywords or hints, turning a fragmented, non-cross-searchable repository into a more usable internal search workflow.
Data flow
Employees ask questions in natural language; Watson Discovery searches internal documents and rulebooks, the chat UI shows retrieved results beneath the conversation, and watsonx.ai turns that retrieved context into answers aligned with the user's intent.
Solution architecture
- Compute
- IBM watsonx.ai Generates answers that match the intent of employee questions using the retrieved enterprise content.
- Serving
- IBM Watson Discovery Searches internal documents and rulebooks and surfaces supporting results inside the chat experience.
Architecture clues
- Discovery search results were displayed at the bottom of the chat field during the pilot.
- The knowledge-search workflow surfaces specific details and internal rulebooks that were difficult to find manually.
- The team tuned the solution to improve answer accuracy during a three-week UI pilot.
Evidence from the source
"50% reduction in the time required to get the information it needed."
"By using IBM Watson Discovery's knowledge search capabilities, System Research was able to uncover specific information detail as well as rulebooks that could not otherwise be released to the public."
"System Research used IBM watsonx.ai ... to provide answers that match the intent of the questions."
"The company ran a pilot version for three weeks for UI development"
"This was a difficult and time-consuming process, as the data was not cross-searchable and the results were not what was expected."
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 confidence92%
- Source authority20/25The main evidence is an official vendor-published customer story.
- Claim traceability23/2511 of 12 key fields link to a named source.
- Direct evidence20/205 direct source quotes retained.
- Date provenance10/10The publication date comes from the source page or publisher.
- Source transparency9/102 source references 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/systemresearchIBMFirst-party
System Research 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
- https://www.sr-net.co.jp/company/history/System Research Co., Ltd.First-party
企業概要・沿革｜株式会社システムリサーチ
従業員（2026.3.31現在） 単体 1,548名 連結 1,569名
Supports- Company size
Date evidence
- Published on source page Apr 18, 2024 · IBM · First-partyOpen date source
Not separately sourced Industry, Region. 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