Enterprise Knowledge Search
Honda needed a faster way to transfer skilled engineering knowledge into its Advanced Expert System because converting internal PowerPoint materials into reusable knowledge models for vehicle-development reviews was too manual and slow to scale across thousands of parts.
Reported impact
Honda expects to accelerate knowledge modeling, reduce development and planning effort, and make expert engineering knowledge easier to reuse across product-development workflows.
Honda worked with IBM to use generative AI for extracting engineering know-how from Microsoft PowerPoint materials and turning it into reusable knowledge for its Advanced Expert System. The source documents contained diagrams and graphs but relatively little text, which made them difficult to reuse with conventional AI techniques. IBM proposed a multimodal approach in IBM watsonx.ai that converts graphical and diagram-heavy content into text, stores the resulting know-how in a database, and then supports retrieval-augmented-generation-style knowledge access. A pilot run from November to December 2023 validated the approach. The resulting architecture lets Honda move from manually creating handbooks and knowledge models over multi-year timelines toward AI-assisted documentation modeling that can surface engineering guidance faster, reduce rework in collision-safety simulation reviews, and broaden reuse of expert knowledge across the development organization.
PowerPoint materials containing engineering diagrams and graphs are processed in watsonx.ai, converted into textual knowledge, stored in a database, and then reused through retrieval-augmented access to support Honda's Advanced Expert System and engineering review workflows.
30%-50% saving in development and planning work
67% reduction in documentation modeling time
IBM proposed using generative AI to extract and database knowledge from Microsoft PowerPoint materials containing dispersed know-how within the company.
IBM suggested applying a large, multi-modal model (LMM) to convert graph and diagram content into text
Storing textual know-how in a database allows for retrieval-augmented generation (RAG) search-like knowledge utilization.
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 Aug 14, 2026 Wikimedia Deutschland Wikimedia Deutschland needed to make Wikidata’s massive, multilingual knowledge graph usable for modern generative AI applications because the existing access pattern depended on specialized query languages and complex… 180 employees IBM DataStax Astra DB · IBM watsonx.data 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 Jun 24, 2026 trivago trivago needed a secure, EU-compliant way for employees to use generative AI across knowledge work without locking the company to one provider or exposing internal data to public tools, while also reducing the friction… 70% of the company attended the AI Learning Day IBM Digital Product Design and Engineering Consulting · trivago Copilot 