Verification
Did the change really happen, and did it help?
Example finding
Re-run the affected prompts
Mention and citation rates before and after a change are shown for the prompts it affects, not for the whole brand.
Quick answer: Verification
Verification re-asks only the prompts behind one action's opportunity, then compares the rate before and after with the same statistical method an audit-over-audit change uses, reported as improved, not improved, or unverified when the sample is too thin.
What you see
Mark an action done and press Verify now: it re-asks only the prompts behind that opportunity, then compares the rate before and after with the same statistical method used for audit to audit change.
A status, not a guess
Verified: improved, No improvement, or Unverified: not enough signal, never a bare yes or no.
Affected prompt re-run
Only the prompts tied to the action are re-run, not a full audit.
Before and after, same rate card
The same interval and sample size display used everywhere else in the dashboard.
Every verification, kept
Each run is listed, queued through completed, so nothing is asked and lost.
How it works
- 1
Mark done
Set an action to Done on Actions or Opportunities.
- 2
Verify now
Re-run only the prompts behind that opportunity.
- 3
Compare
Report the difference with the same interval and sample size shown elsewhere, with unverified shown honestly when the sample is too thin.
How it is measured
Definitions come first, so numbers stay comparable from one audit to the next.
- Verification outcome
- Verified: improved, No improvement, or Unverified: not enough signal.
- Affected scope
- The topics and prompts re-run for this one action.
- Delta
- Change in mention, recommendation or citation rate with sample size and interval.
Good to know. No action is marked improved without observable verification against the same statistical bar used for every other rate in the platform. A thin sample is reported as unverified, never rounded up to a verdict.
Common questions
Does verification prove my change worked?
It shows what changed on a defined sample, with the same interval used everywhere else. It does not prove causation.
What if the result is unverified?
That means the sample was too thin to call either way, and it is reported as unverified rather than guessed at.
Does it prove causation?
No. It shows what changed on a defined sample, with the same interval used everywhere else.
A short checklist
- Mark the action Done
- Press Verify now
- Wait for the re-run to complete
- Read the status: improved, not improved, or unverified
- Open the before and after rate cards
Who uses it
- Analyst
- A defined before and after method, same interval as every other rate.
- Marketing lead
- Evidence that work landed, or an honest unverified when it did not have enough signal.
- Agency
- A credible client story, including when the honest answer is unverified.
Common mistakes
Verifying too soon
Allow time for sources to be re-read before pressing Verify now.
Crediting every change to the action
Other factors move answers; this is a before and after, not a causal proof.
Changing the prompts
Only the prompts tied to the action are re-run, by design.
See Verification on your own brand.
Start with a first audit. We show where you appear, who is named instead, and what to fix first.