Track record

How we measure accuracy.

Most vendors publish a number and ask you to trust it. This page shows our number, how it is made, and where we fall short. Every figure here comes from claims our customers and design partners graded against what actually happened.

One claim, end to end Immutable

Day 0

The run finishes. Every finding is written down as one specific claim, with a date.

Sealed hereThe file cannot be edited. Nothing can be added later.

Day 1–30

The campaign runs. The outcome happens, and we have no say in it.

Grading

Your team marks the claim against your own data. We have no vote.

Hit Miss

After

It stays on the ledger. Hit or miss, we do not remove it.

Next run

The grade feeds back into your model. Hits confirm a pattern. Misses correct one.

+1 learning signal

The numbers

Where we stand today

These are from live accounts. Nothing is a pilot study or lab test.

Accuracy

84%

Across all live accounts - customers & design partners. One blended number, not a best case.

Graded by you

100%

Every call is marked HIT or MISS by the customer’s own team, against their own platform data. We never score ourselves.

Claims graded

473

Every claim that has been graded is in the number above. None removed.

The numbers are not fixed. Every graded claim feeds back into the model for that account. Hits confirm a pattern, misses correct one, and the committee that reads your page in three months has learned from every call your team graded in between.

The method

Four rules

A number is only as good as the rules behind it. Here are ours. They do not change after the fact.

The claim is sealed before launch

When a run finishes, every finding is written down as a specific claim with a date. The file is immutable. We cannot edit the wording later, and we cannot add a claim after the outcome is known. The claim exists before the result does. This is the same idea as pre-registering a trial before you run it. A tool that answers differently every time cannot do this, because there is no single claim to lock.

Your team grades it, not us

You mark each claim HIT or MISS against your own analytics, your own CRM, and what your sales team heard. We have no vote. If we scored our own homework, the number would be worth nothing, and you would be right to ignore it.

The bar is set before grading starts

Each claim type has a target we publish in advance. Objections and blockers are held to 80 percent. Fixes to 70. Root cause to 75. The bar is ours, not an industry standard.

Nothing is removed

A miss stays on the ledger forever. We do not delete bad runs, drop weak accounts, or pick a flattering window. The 473 above is every graded claim we have. If our number drops next quarter, we publish the drop.

Definitions

What each grade means

Four outcomes. Only two of them count toward the hit rate.

Hit · counts

What we said would happen, happened. The role we named did block. The objection we predicted did come up.

Miss · counts

We were wrong. It stays on the record with the original claim text and date, so you can read what we got wrong and when.

Can’t grade · excluded

The evidence to settle it never arrived. The campaign was pulled, or the data was never captured. Excluded from the rate because there is no verdict, not because it went badly. 21 of the 473 fall here.

No call · on the record

The evidence was too thin, so the system declined to make a claim at all. We log these too. A tool that always has an answer is a tool that is guessing.

The breakdown

Every call, against its bar

One overall number hides more than it shows. We are much better at some calls than others. Here is the split, including the row where we are below our own bar.

By claim type	Accuracy	Our bar
Does this role block? Does this objection land?	96.6%	80%
What is already working on the page	95%+	88%
Which fix to apply	71.4%	70%
Why it broke, the root cause	67.5%	75%

Root cause sits below our bar. We would rather show you that than hide it inside an average.

By engine	Accuracy	Our bar
Content pages	94%	78%
Landing pages	83%	78%
Email campaigns	76%	80%
Ad campaigns	78%	75%

Email sits below our bar. We would rather show you than calling both “across accounts.”

The boundary

What we do not claim

WhyUser predicts direction and rank order. Which role disengages, where on the page, and which of two variants wins. It does not do these things, and any vendor who says otherwise is guessing.

We do not predict your conversion rate or bounce rate as a number.

We do not replace a live A/B test. We tell you which variant deserves the traffic.

We cannot see your paid targeting, so we diagnose the message, not the audience.

The agents are simulated. We will never imply they are real people.

Check us

Do not take our word for it

The fastest way to settle accuracy is to grade us yourself.

Request access

Pick a campaign whose ending you already know. A page that underperformed. An email that flopped. An ad set you killed.

We run it without seeing the result. The claims seal the moment the run finishes, with a timestamp you can check. Then you grade them against what actually happened.

You will get some hits and some misses. Both go on the ledger. That is the whole point: a track record you can audit beats a number you have to trust. More on how the product works in the FAQ.