Enterprise Knowledge Search
AdriaCamps needed to help support agents answer complex accommodation questions faster because product information was fragmented across databases and PDF brochures spanning hundreds of campsites and amenities.
Reported impact
AdriaCamps proved it could consolidate booking knowledge into a multilingual assistant that improves response speed today and can support expansion into new markets without adding headcount proportionally.
AdriaCamps and IBM Business Partner Deegloo built a minimum viable customer-service assistant on IBM watsonx.ai to unify fragmented booking knowledge. The company manages accommodation data for more than 250 campsites and had support agents switching between multiple databases and large collections of PDF brochures to answer customer questions. The MVP assistant converses in English and German, brings together information from five sources and uses retrieval-augmented generation to supplement model knowledge with authoritative external content. Deegloo also added a confidence score so agents can judge how reliable a response is before using it. In the resulting flow, customer or agent questions are interpreted in natural language, supporting content is retrieved from structured and unstructured sources, and the assistant returns an answer that can either help an agent respond faster or eventually power customer-facing self-service.
Questions are submitted to the watsonx.ai-based assistant, relevant content is retrieved from five structured and unstructured information sources through the RAG workflow, and grounded responses with confidence scores are returned to agents or future self-service channels.
AdriaCamps chose to build a minimum viable product (MVP) using IBM® watsonx.ai™ studio.
Deegloo implemented a retrieval-augmented generation (RAG) technique to bring in additional information from authoritative sources outside of the training data.
This assistant brings together information from five sources and presents it intelligently in response to natural language queries.
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 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 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 