Question
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 short answer
You can change how a deal score is calculated only if the vendor exposes the model, and most do not. A score you cannot open cannot be adjusted or audited. An editable score shows every weight, lets you change it, and can be proven against your own closed deals. In Kaypo the weights are yours and refit nightly.
How Kaypo answers this on your pipeline
30 minutes with the founder
Thirty minutes on your pipeline or the example one. Pick a time and it is booked.
A proprietary model is trained somewhere else, arrives as a number, and cannot be questioned. Vendors describe this as an advantage: it adapts, it learns, you do not have to maintain anything.
An editable model shows its inputs and their weights, and lets you change them. You can see why a deal scored 31 and you can disagree with it.
Every scoring model will eventually be wrong about a deal your team understands better than it does. When that happens with a proprietary model, there is nothing to do. You cannot see what it weighed, you cannot tell it that procurement takes six weeks in your business, and the only recourse is a support ticket.
When it happens with an editable model, you open it, see that security review was worth 18 points, decide that is wrong for your market, and change it.
This is the whole reason scores go unused. A rep who cannot see why a number moved argues with it. A rep who can see the inputs acts on it.
The strongest version of an editable model is one you can test. Take your weights, run them against every deal you have already closed, and see whether they actually separate your wins from your losses.
That is a checkable claim. It either separates them or it does not, and you find out before you ask anybody to trust a number.
A proprietary engine cannot offer this. It can tell you it was trained on a great deal of data, which is a reason to trust it, not evidence that it works on your pipeline.
Every score lists its inputs and exactly what each one contributed. The weights are yours to set. A back test runs them against your own closed deals and reports how cleanly they separate wins from losses.
Then the result goes to each rep in Slack every morning with the reason beside the number, which is the only form in which a score gets used.
Recorded in the sandbox, the same example pipeline you can open yourself. Pick any part.
Deals. Every open deal, scored on what the buyer did.
Not for the predictive score. It cannot be inspected or edited. You can build a separate manual score with a calculated property, which you then maintain yourself.
Because they cannot see why a number moved. A score with no visible reason gets argued with, and a score that gets argued with stops being used within a quarter.
Running your scoring weights against deals you have already closed to check whether they separate wins from losses. It turns a score from something you trust into something you have checked.
The product page for this: How Kaypo works.
Reviewed November 8, 2026 against the product as it behaves today.
30 minutes with the founder
Bring this question and your own deals. Pick a time and it is booked.
Next step
The real product on invented B2B software companies. Nothing to connect and no signup.
Open Deals in the sandboxThe whole product on an example pipeline: scores, next steps, plays and agents. No signup and no call.
$1,500 a month, or $15,000 a year, for one admin and up to 15 users. Free for 14 days, no card.
Or get the free report on your own closed dealsOr talk it through with a person, 30 minutes