Leveraging Large Language Models for Sales & Customer Success Automation

Mash helps revenue teams at technical B2B companies streamline pre- and post-sales activities by automating knowledge-intensive tasks such as answering product questions, managing bug reports and feature requests, and prepping for meetings. Its AI platform leverages data buried in messaging platforms, wikis, CRMs, and other internal tools to deliver timely, context-aware assistance to individuals in sales and customer success roles. Significant time is spent by individuals in these roles seeking out product knowledge and technical expertise in the context of customers’ needs. An internal point-person responsible for a given customer is often juggling multiple accounts at once and may not have all the necessary knowledge to effectively serve them. This often means scouring outdated documentation, incomplete notes, and past conversations for information, and pulling in other team members for help.
Through this project, Mash aims to work with the intern to incorporate cutting-edge LLM-related technologies into its platform to further improve its customers’ ability to access internally available information. By leveraging AI to reduce the manual work and multi-party overhead associated with traditional knowledge-sharing processes, Mash’s customers will be able to serve their own customers more effectively, preventing lost leads and churn, resulting in additional revenue.

Faculty Supervisor:

Scott Sanner

Student:

Partner:

Mash

Discipline:

Computer science

Sector:

Information and cultural industries

University:

University of Toronto

Program: