A case study of Generative AI in MSX Sales Copilot: Improving seller productivity with a real-time question-answering system for content recommendation
This is an incremental improvement for Microsoft sellers to enhance productivity by quickly accessing sales content during live interactions.
The paper tackled the problem of helping sellers find relevant sales materials during customer calls by designing a real-time question-answering system using LLM embeddings and a bi-encoder with cross-encoder re-ranker architecture, achieving content recommendations in just a few seconds for large datasets and deploying it in Microsoft's Dynamics CRM for daily use.
In this paper, we design a real-time question-answering system specifically targeted for helping sellers get relevant material/documentation they can share live with their customers or refer to during a call. Taking the Seismic content repository as a relatively large scale example of a diverse dataset of sales material, we demonstrate how LLM embeddings of sellers' queries can be matched with the relevant content. We achieve this by engineering prompts in an elaborate fashion that makes use of the rich set of meta-features available for documents and sellers. Using a bi-encoder with cross-encoder re-ranker architecture, we show how the solution returns the most relevant content recommendations in just a few seconds even for large datasets. Our recommender system is deployed as an AML endpoint for real-time inferencing and has been integrated into a Copilot interface that is now deployed in the production version of the Dynamics CRM, known as MSX, used daily by Microsoft sellers.