The Solution

To address these challenges, the project team developed a proof-of-concept (POC) that leveraged advanced graph technology combined with AI-augmented classification techniques. 

The solution was implemented across several workstreams:

Defining System Functionality
The initial phase involved clearly articulating the use case. By mapping out the decision landscape—from strategic objectives (improving modern contraceptive prevalence rates) to granular insights from user research—the team designed a tailored taxonomy and ontology for the women’s health domain. This semantic framework was engineered to capture cultural nuances, local linguistic variations, and the diverse attributes influencing contraceptive choices.

Processing Existing Data
With the functionality defined, the next phase involved transforming internal survey responses and investment documents into a unified, structured format. An AI-augmented classification workflow was deployed to extract tacit knowledge from survey responses. This process was supported by a stakeholder-validated taxonomy and ontology, allowing raw responses to be mapped into clearly defined data classes. This robust data processing pipeline ensured that quantitative measures (like frequency of citation) and qualitative insights were captured in a cohesive base graph.

Building the Analysis Model
The core of the solution was the creation of a Product Adoption Survey Base Graph. Processed data was converted into RDF triples using a rigorous ontology model, forming the base graph designed to answer competency questions via SPARQL queries. While this model laid the foundation for revealing correlations and decision factors, the full production of the advanced analysis graph—designed to incorporate deeper inference and reasoning—remained as a future enhancement.

Handoff of Analysis Graph Production and Frontend Implementation
Due to time constraints, the production of the comprehensive analysis graph and the implementation of the interactive front end were transitioned to the client. Our team delivered the base graph and all necessary supporting documentation, providing the client with a solid foundation and a detailed roadmap for further development. This handoff ensures that the client’s in-house teams can continue productionalizing the analysis graph and integrate it with their BI dashboard for end-user access.

Provide a Roadmap for Further Development
Beyond the initial POC, a clear roadmap was established. The next steps include refining the AI classification workflow, fully instantiating the analysis graph with enhanced reasoning capabilities, and developing the front end to expose these insights via a business intelligence (BI) dashboard. These tasks have been handed off to the client, along with guidance on leveraging enterprise graph database licenses and integrating the solution within existing knowledge management frameworks.

 

The EK Difference

A standout feature of this project is its novel, generalizable technical architecture:

AI-Augmented Classification Pipeline:
The solution leverages state-of-the-art language models to perform the initial classification of survey responses. Supported by a validated taxonomy, this pipeline automatically extracts and tags critical data points from large volumes of survey content, laying the groundwork for subsequent graph instantiation, inference, and analysis.

 

The Solution

To address these challenges, the project team developed a proof-of-concept (POC) that leveraged advanced graph technology and a semantic RAG (Retrieval Augmented Generation) agentic workflow. 

The solution was built around several core workstreams:

Defining System Functionality

The initial phase focused on establishing a clear use case: enabling the foundation to query its data ecosystem with natural language questions and receive accurate, explainable answers. This involved mapping out a comprehensive taxonomy and ontology that could encapsulate the knowledge domain of investments, thereby standardizing how investment documents and data were interpreted and interrelated.

Processing Existing Data

With functionality defined, the next step was to ingest and transform various data types. Structured data from internal systems and unstructured investment documents were processed and aligned with the newly defined ontology. Advanced techniques, including semantic extraction and graph mapping, were employed to ensure that all data—regardless of source—was accessible within a unified graph database.

Building the Chatbot Model

Central to the solution was the development of an investment chatbot that could leverage the graph’s interconnected data. This was approached as a cross-document question-answering challenge. The model was designed to predict answers by linking query nodes with relevant data nodes across the graph, thereby addressing competency questions that a naive retrieval model would miss. An explainable AI component was integrated to transparently show which data points drove each answer, instilling confidence in the results.

Deploying the Whole System in a Containerized Web Application Stack

To ensure immediate usability, the POC was deployed, along with all of its dependencies, in a user-friendly, portable web application stack. This involved creating a dedicated API layer to interface between the chatbot and the graph database containers, alongside a custom front end that allowed executive users to interact with the system and view detailed explanations of the generated answers and the source documents upon which they were based. Early feedback highlighted the system’s ability to connect structured and unstructured content seamlessly, paving the way for broader adoption.

Providing a Roadmap for Further Development

Beyond the initial POC, the project laid out clear next steps. Recommendations included refining the chatbot’s response logic, optimizing performance (notably in embedding and document chunking), and enhancing user experience through additional ontology-driven query refinements. These steps are critical for evolving the system from a demonstrative tool to a fully integrated component of the foundation’s data management and access stack.

 

 

The EK Difference

A key differentiator of this project was its adoption of standards-based semantic graph technology and its highly generalizable technical architecture. 

The architecture comprises:

Investment Ontology and Data Mapping:

A rigorously defined ontology underpins the entire system, ensuring that all investment-related data—from structured datasets to narrative reports—is harmonized under a common language. This semantic backbone supports both precise data integration and flexible query interpretation.

Graph Instantiation Pipeline:

Investment data is transformed into RDF triples and instantiated within a robust graph database. This pipeline supports current data volumes and is scalable for future expansion. It includes custom tools to convert CSV files and other structured datasets into RDF and mechanisms to continually map new data into the graph.

Semantic RAG Agentic Workflow and API:

The solution utilizes a semantic RAG approach to navigate the complexities of cross-document query answering. This agentic workflow is designed to minimize unhelpful hallucinations, ensuring that each answer is traceable back to the underlying data. The integrated API provides a seamless bridge between the front-end chatbot and the back-end graph, enabling real-time, explainable responses.

Investment Chatbot Deployment:

Built as a central interface, the chatbot exemplifies how graph technology can be operationalized to address executive-level investment queries. It is fine-tuned to reflect the foundation’s language and domain knowledge, ensuring that every answer is accurate and contextually relevant.