From Retrieval to Customer Context: Evaluating Frontier-Model Systems for Voice-of-Customer Analysis

Key points

• Organizations increasingly use frontier language models to analyze customer feedback, but answer quality also depends on how that feedback is organized and made available.1
• 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).1
• 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.1
• 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).1

Sources (1)

• [1]From Retrieval to Customer Context: Evaluating Frontier-Model Systems for Voice-of-Customer Analysis
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 7, 03:30 AM

  We define a customer context graph as a unified model of customer and business context.

  Organizations increasingly use frontier language models to analyze customer feedback, but answer quality also depends on how that feedback is organized and made available.

Extractive summary: sentences quoted from the sources.