Project / 03 / Mayur Patil
SIGNAL: Sales Intelligence Layer
Turn B2B sales-call transcripts into themes, sentiment patterns, and prioritized recommendations through a sequential five-agent workflow.
The problem
Qualitative insights are scattered across long conversations. SIGNAL explores how a sequence of focused agents can structure and synthesize those observations.
How it works
Give each of five agents a distinct responsibility, from ingestion to strategic advice. Surface findings in a dashboard with report export.
Evidence and evaluation
Five specialized agents and six sample transcripts documented in the repository. A human-reviewed quality benchmark has not been published.
Limitations
Work in progress. The repository documents six sample transcripts; quantitative performance claims need a defined evaluation dataset and human-review methodology.
About the author
Mayur Patil is a data scientist and ML engineer pursuing an M.S. in Data Science at The George Washington University, based in Falls Church, Virginia. His work spans data engineering, applied ML, language models, and sports forecasting.
More about Mayur Patil ↗