📈

Lead Scoring Model AutoResearch Agent

productapi-pushhours cycle

Autonomously optimize lead scoring criteria and weights by testing formula variants against historical conversion data overnight.

Primary Metric

Precision@K

↑ Higher is better

Experiment Settings

Variants per round: 5

Max rounds: 15

Min sample size: 200

Guard Rails

Experiments auto-pause if these thresholds are breached

Minimum 20% precision (never worse than random)Floor: 20.0%