Demo Area

Recomentor by Graphwise transforms sustainability reporting from a box-ticking exercise into a strategic advantage by turning complexity into clarity and bringing confidence to AI.

• Recomentor ingests reports at scale, structures and links concepts, and aligns insights to established or custom frameworks.
• Teams can add missing companies and upload reports in minutes, then select peer groups for instant comparisons.
• Every insight is traceable to the exact paragraph, enabling confident, audit-ready decisions.

Through Graphwise, CABI was able to streamline the process of users accessing critical, evidence-based information and to prepare its vast data landscape for truly explainable AI use cases.

• Provides users with personalised and tailored search experience that speeds up information retrieval.
• CABI enables its users to explore the vast, dense and scientific knowledge its thesaurus holds in a blink of an eye.
• The thesaurus is also employed to power explainable and replicable conversational AI through a (beta) GraphRAG application.

Graphwise helps millions of users to find reliable health advice across over 200 content silos in a precise way. With Graphwise, HDA was able to improve their help desks and self-service portals to search over scattered information about complex domains.

• Providing a one-stop shop for end users to search for knowledge in their own words.
• HDA uses most of the features of Graphwise, with a comprehensive drug graph powering their website to provide information on medicines.
• The Knowledge Graph supports various services, such as a dedicated health service finder and complex topic exploration navigator. 

Graphwise helps users to find answers and documents across multiple repositories in a precise way.
Example: Improve help desks and self-service portals to search over regulations or product documentation.

• Provide actionable insights for industries where the stakes are high.
• Benefit from precise GraphRAG and content recommendation services
• See how personalisation based on domain knowledge models works!

This Graph RAG demo is a great example to show when we want to illustrate self-service training and self-support use cases. It has a chatbot-like interface which keeps the context of the interaction and provides a quiz to self-test the acquired knowledge

• Graph RAG applied to the technical documentation domain - drink your own champagne scenario!
• The knowledge graph contextualises questions and answers and helps retrieving the relevant documents
• Reduce hallucinations and provide provenance to answers through the recommended documents

With Graphwise, Microsoft Learn was able to become a centralised, comprehensive, and interlinked knowledge hub that helps its user community in content discovery and retrieval with the help of a semantic layer and automatic tagging across data silos.

• The Knowledge Hub centralises search and access to million of distributed pieces of content maintained by thousands of contributors.
• Changes to taxonomies managed centrally drastically reducing the time to production, and allowing the creation of complex relations between products.
• Shift from manual tagging of million of pieces of content to an automated approach which enables the growth of the business unit.

The GBA thesaurus demonstrates how Graphwise’s core capabilities in managing and bringing together complex knowledge helps a federal agency become a pioneer using linked data in the geospatial sector in the EU.

• Provides users with a bilingual and connected knowledge representation of the geological survey.
• GeoSphere enables its users to explore and traverse their knowledge graph in a visual manner for quick information retrieval and discovery
• The Knowledge Graph is used in geoscientific text publications and geological maps

The perfect synergy between  Custom Taxonomies, Graph and LLM
OTKG transforms content into a strategic asset by structuring it with custom taxonomies and ontologies and thus enabling: seamless content reuse across platforms, LLM-powered search and interaction with content, easy discovery of content gaps through domain knowledge analytics, automated schema.org markup, personalized experiences  and content recommendations.

• Content discovery and efficient information sources retrieval. 
• Tailored navigation and relevant recommendations
• Question-answering and insights through a natural language interface to consume knowledge graph information  in a user-friendly way

Transform business processes such as hiring, talent management and human resources pooling into a dynamic Knowledge Graph, providing a 360-degree view of human resources and enable precise impact analysis and risk quantification of people, skills and projects.

• Deliver precise, data-driven answers to key HR and strategic workforce planning questions.
• Make informed decisions based on real-world skill requirements, compensation patterns, and market trends.
• Suggest relevant candidates based on skills and experience 

HR Recommender provides an attractive example of an application that takes advantage of connection between concepts i.e. skills and considers implicit relations within families of skills (e.g. programming languages) 

• HR Recommender showcases knowledge graph powered recommendations for the domain of HR
• Employees, positions and projects are semantically profiled for meaningful comparisons and better matching
• The knowledge graph relations enables the on-the-fly recalculation or rankings

With Transparency Energy Knowledge Graph (TEKG) you can explore the world of open electricity data. TEKG integrates part of ENTSO-E Transparency Platform data and showcases how applying Linked Data principles and semantic technology to electricity data can turn fragmented data into a semantically linked, queryable format for better integrated and validated electricity data.

• A Knowledge Graph with electricity data enables the integration between TSOs, DSOs, market participants, and regulators.
• Linked Data supports grid optimization, sustainability tracking, and policy compliance using a common data language.
• Electricity data in a knowledge graph supports the access to cross-border, cross-actor electricity data.