Enterprise Knowledge Search
IBM employees needed a faster way to find proposal content across many internal sources because searching sales documents, templates, product guides, and offerings manually slowed proposal creation and made it harder to respond with accurate details quickly.
Reported impact
AskTECHNO reduced proposal-content search effort, improved access to multilingual product knowledge, and created a reusable internal generative-search pattern IBM teams can apply elsewhere.
IBM Consulting, IBM Software, and the IBM CIO organization built AskTECHNO as a generative-search assistant for proposal management. The platform combines IBM watsonx.ai, IBM Granite-class language models, IBM Watson Discovery, and IBM Cloud Code Engine with curated internal IBM content such as sales documents and proposal artifacts. Watsonx.ai generates answer text from relevant material, Granite supports bilingual search and translation between Japanese and English, Watson Discovery indexes IBM web and content sources, and Cloud Code Engine captures user activity logs for continuous improvement. Using retrieval-augmented generation, AskTECHNO answers employee questions with grounded responses that include source references and publication dates. The result is a multilingual internal search layer that makes proposal knowledge accessible through natural-language questions instead of time-consuming content hunting across disconnected repositories.
Internal sales and product content is indexed through Watson Discovery, employees ask questions in Japanese or English, Granite helps interpret and translate those queries, watsonx.ai generates source-backed answers using RAG, and Cloud Code Engine records usage data for tuning and expansion.
The Retrieval-Augmented Generation (RAG) technique enables the digital assistant to use the ingested contents to create responses
The digital assistant was built with IBM watsonx.ai, IBM Granite-class large language models (LLMs), IBM Watson Discovery and IBM Cloud Code Engine
The intention is for all IBM employees to use the application
The responses offered by AskTECHNO include the information sources and when was the information published or last updated.
watsonx.ai helped generate answers to users’ questions while IBM Granite translated users’ queries and searched contents between English and Japanese.
Review how this reference was scored and trace each normalized claim back to its documented source.
Scoring methodology
Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.
Traceability
Field coverage shows which facts each source supports. Dates are shown only when documented by the source.
Related
IBM Sample Jul 31, 2026 Crazylog 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 IBM Cloud · IBM watsonx.ai · IBM watsonx.data IBM Sample Mar 28, 2026 Shorthills AI 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 IBM watsonx.data · Langflow IBM Sample Mar 24, 2026 IBM Human Resources 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 IBM Cognos · IBM watsonx BI 