Customer context graph improves voice of customer analysis with frontier ai
From Retrieval to Customer Context: Evaluating Frontier-Model Systems for Voice-of-Customer Analysis
Machine Learning
Summary
Organizations want to understand customer feedback better using advanced language AI, but how feedback is organized also matters. The authors created a system called a customer context graph that links customer feedback to business details, actions, and results in one model. They tested three AI systems on thousands of real feedback messages, finding that the system using this graph gave much better, more detailed answers that showed clear evidence. This helps provide not just what customers say, but why and what was done about it.
What this means in practice
- •For customer support teams: Analyze customer feedback more deeply with linked business context to identify issues, responsible teams, and resolution status effectively.
- •For product management teams: Use integrated customer context graphs to uncover detailed insights and quantify customer themes for better product decisions.
Authors
Raviraja G, Viraj Bagal, Prabhath Chellingi
Abstract
Organizations increasingly use frontier language models to analyze customer feedback, but answer quality also depends on how that feedback is organized and made available. We define a \emph{customer context graph} as a unified model of customer and business context. Typed relationships connect customer objects (feedback, conversations, users, and accounts), operational objects (tickets, support agents, opportunities, and competitors), and analytical or action objects (taxonomy concepts, evidence, insights, work items, and outcomes). This lets an agent investigate not only what customers say, but why, who is affected, what action followed, who owns it, and whether it was resolved. For this experiment, the graph is populated from public Cursor feedback; the same architecture can support any type of feedback source. We compare Agentic RAG, a Deep Research Agent, and a Customer Context Graph-backed Agent on the same 9,432 public Cursor feedback records using 30 realistic product, incident, comparison, and metadata questions. Without exhaustive ground truth, we jointly score responses on answer quality (coverage and organization), analytical depth (specificity and decomposition), and evidence quality (citation support and traceability), using a comparative rubric calibrated on 28 of the 30 questions. We sample cited records against their claims and weight the three dimensions equally. Under this aligned rubric, the Customer Context Graph-backed Agent scores 0.961 overall, versus 0.710 for the Deep Research Agent and 0.651 for Agentic RAG, and leads the Deep Research Agent on 27 of 30 paired questions (sign-test p < 10^(-5); strictly best on 26 of 30). Its largest advantage is analytical depth (0.967 versus 0.642), reflecting more specific, hierarchically developed findings with quantified themes and traceable evidence...