SpyderBot Documentation

Observatory — Evidence

Evidence is the source of truth for validating Observatory findings.

Use it to inspect:

  • exact responses;
  • citations;
  • entity observations;
  • sentiment/portrayal classifications;
  • observation dates;
  • AI systems;
  • exposed models/versions;
  • prompt/context;
  • measurement/protocol scope.

Evidence should allow every major finding to be traced back to exact observations.


Evidence Strength

Evidence Strength indicates how strongly the available eligible observations support a finding.

It is not the same as Prompt Priority, outcome consistency, AI-System Support, Comparability, or Monitoring Health. Keep these meanings separate.

Severity describes how important or material a detected change is. Evidence Strength describes how strongly the available evidence supports the finding. A high-severity event can still require careful interpretation if evidence is limited.


Getting help from the Evidence

When a finding matters to a business decision:

  1. Confirm the Measurement Scope.
  2. Check Applicability.
  3. Check Evidence Strength.
  4. Check AI-system coverage.
  5. Check Comparability for temporal claims.
  6. Open Evidence.
  7. Review exact responses/citations/observations.
  8. Then decide whether action is justified.

This sequence is especially important for competitor recommendation changes, sentiment/portrayal changes, source ecosystem changes, Benchmark gap movement, and cross-system disagreement.

Common interpretation rules

Use these rules across Prompt Intelligence:

0% can be a valid observed value.
Missing is not 0%.
Unknown is not Neutral.
Not Applicable is not poor performance.
Not Observed is not Brand absence.
No AI Answer is not Brand absence.
Not Comparable is not No Change.
A citation is not proof of causality.
A higher Prompt Priority does not increase an observed outcome.
More raw executions do not automatically mean stronger evidence.

Prompt Observatory does not claim access to hidden model reasoning. Change Drivers answer which evidence-supported factors moved with the observed change; they do not automatically answer which factor caused the external AI system to change.

Next step

Review AI Brand Portrayal or return to Changes.