How to
Build a lead score from your own converted leads rather than from a template. Split fit from behavior, weight them separately, then test the weights against what actually converted before anybody routes anything.
Fit is whether this account should buy: size, industry, technology, region. It is knowable before anybody does anything.
Behavior is whether they are acting like somebody who will. Combining them into one number hides which is missing, and the response to each is completely different.
Take everything that converted in the last year and everything that did not. Find what was true of the first group and not the second.
That list, sorted by how cleanly it separates the two, is your model. It will not look like the template.
Testing. Run the weights against past leads and check whether the high scores actually converted. If a score of 80 converts at the same rate as a 40, the model does nothing and should not be shipped.
A lead score answers whether to work it. A deal score answers whether this one will close. They use different signals and a single model for both usually serves neither.
Questions
Start from your own converted and unconverted leads, find what separated them, split fit from behavior, then test the weights against past outcomes before routing anything on them.
They were built from intuition rather than outcomes, and nobody re-tests them when the business changes. A model that is never checked drifts quietly.
It arrives in Slack
Every morning, each rep gets one message naming the deals on their own book that moved overnight, biggest mover first, with the reason beside each number and the deals that have gone quiet underneath.
$99 a month, cancel any time.. Everyone on the team. No per seat charge. Connect a CRM and it runs. No implementation fee. 14 day trial. No card.
Related reading
One decides whether to work something. The other decides whether it will close. Using one model for both is why both get ignored.
Most deal scores cannot be opened or adjusted. Why that matters the first time one is wrong about your business, and what an editable model gives you instead.
The three ways to score deals in a CRM, what each costs in time and money, and why most home built scoring models stop being maintained within a quarter.
Most dashboards answer questions nobody asked. What to include, what to remove, and the test for each panel.
Reviewed September 20, 2026 against the product as it behaves today.