Reads your deals tagged with a primary trust signal, referral, customer proof, review, expert content, prior familiarity, and compares win rate, cycle time, and deal size across them. Flags small samples instead of calling a lucky streak a pattern, and flags deals with no trust signal recorded at all.
A single lucky streak on a small sample can look exactly like a real pattern until someone checks the sample size.
14 synthetic deals tagged with a primary trust signal (Referral, Customer Proof, no signal recorded, and a deliberately tiny Expert Content sample), run twice: once at the default 5-deal reliability threshold, once at 3.
75%
Referral win rate
25%
Untagged deal win rate
4
Deals missing a signal
The tool's job is knowing when a number is too small to trust, not just computing the number.
Configurable. The default threshold in testing was 5 deals per signal before a result counts as reliable.
They're separated into their own list as a CRM hygiene gap, not folded into a misleading average.
Runs against your CRM using your own credentials, through your own AI instance. We don't copy, store, or retain your data.