Sales Research Agent and Sales Research Bench

TL;DR

This paper introduces the Sales Research Agent, an AI system integrated with CRM data for sales insights, and the Sales Research Bench, a benchmark to evaluate AI quality across multiple dimensions, demonstrating superior performance over existing models.

Contribution

The paper presents a novel AI agent for CRM data analysis and a comprehensive benchmark for evaluating AI quality in sales contexts, enabling transparent comparison.

Findings

Sales Research Agent outperforms Claude Sonnet 4.5 by 13 points.

Sales Research Agent outperforms ChatGPT-5 by 24.1 points.

The benchmark scores AI systems on eight customer-weighted dimensions.

Abstract

Enterprises increasingly need AI systems that can answer sales-leader questions over live, customized CRM data, but most available models do not expose transparent, repeatable evidence of quality. This paper describes the Sales Research Agent in Microsoft Dynamics 365 Sales, an AI-first application that connects to live CRM and related data, reasons over complex schemas, and produces decision-ready insights through text and chart outputs. To make quality observable, we introduce the Sales Research Bench, a purpose-built benchmark that scores systems on eight customer-weighted dimensions, including text and chart groundedness, relevance, explainability, schema accuracy, and chart quality. In a 200-question run on a customized enterprise schema on October 19, 2025, the Sales Research Agent outperformed Claude Sonnet 4.5 by 13 points and ChatGPT-5 by 24.1 points on the 100-point composite score, giving customers a repeatable way to compare AI solutions.