NEC and Quollio Technologies Complete Technical Verification of Context Layer for Managing Features Extracted by dotData and Business Context in a Catalog; Pilot Program Begins at NEC

NEC has collaborated with Quollio Technologies, Inc. (hereinafter Quollio), a provider of next-generation data intelligence solutions for Japanese enterprises, to complete technical verification of integrating the "Quollio Data Intelligence Cloud." This platform enables the management and utilization of business context as business metadata for features automatically extracted by the AI data analysis platform "dotData." Following these results, both companies began a pilot program in NEC's internal business environment in March 2026.

Background of Joint Verification: Challenges in AI-Ready Data Preparation

With the spread of generative AI and AI agents, the importance of converting data accumulated within companies into "knowledge (AI-Ready data)" that AI can understand and utilize is increasing. "dotData" can streamline and accelerate the preparation of AI-Ready data by automatically extracting features (insights), which are statistical facts hidden in the data. On the other hand, "semantic information"—such as how to interpret extracted features within a business context and connect them to decision-making—often relies on human knowledge and operational experience, creating a barrier for AI to understand context and generate responses.

Content of Technical Verification: Establishing a "Knowledge Circulation Cycle" on Data Infrastructure

From October to December 2025, the companies utilized "Cortex Agents," a generative AI agent provided by Snowflake Inc., and "Streamlit," an application development tool for visualizing and sharing data. In this environment, through dialogue (brainstorming) via the AI agent's chat UI, it was confirmed that by adding business context to the features extracted by dotData, the AI agent could generate meaningful responses that go beyond mere numerical presentation by considering the context. Furthermore, the technical feasibility of an architecture that autonomously integrates and utilizes these elements was confirmed.

1. Verification Architecture: Features extracted by dotData were stored in Snowflake, and an AI agent environment was built to call Cortex Agents from Streamlit and interact with users.

2. Fusion of Statistical Facts and Business Context (Specific Example): Supermarket purchase data was used as a model case. Through dialogue (brainstorming) in the AI agent's chat UI, "business context" was derived for the features extracted by dotData. By utilizing both the features and the business context together, it was confirmed that the AI agent could provide responses beyond simple numbers.

   ・Fact extracted by dotData (Feature): "Purchase time is in the 22:00 hour."
   ・Business context derived through chat UI brainstorming: "Customer visiting just before closing (last-minute demand)."
   ・AI Agent behavior: When a user asks, "What are the characteristics of customers who buy Product A?", the AI references the "22:00 hour (fact)" data and generates a response that facilitates user understanding by incorporating the "last-minute customer (business context)."

3. Context Management at Quollio: Features and business context stored as Snowflake tables...