arXiv:2503.23303
Predicts sales conversion probability during live conversations
Deep Dive
Featuring Preston Rhodes
Watch original on InstagramWhat It Does
SalesRLAgent analyzes each message in a sales conversation and calculates the probability that the deal will close. As the conversation progresses, it updates predictions in real-time, helping sales reps understand exactly where they stand.
See It In Action
Customer
"I need to think about it..."
Agent
"What specific concerns do you have?"
Customer
"The price is a bit high"
Agent
"Let me show you the ROI..."
Customer
"That makes sense, let's proceed"
How It Works
Each message is converted to a 3072-dimension vector using Azure OpenAI embeddings, capturing semantic meaning.
A PPO (Proximal Policy Optimization) agent learns from conversation trajectories, treating prediction as a decision problem.
At each turn, the model outputs a conversion probability based on the full conversation context so far.
Results