SpyderBot Documentation

Explorer — Models

The Models view helps answer where eligible AI systems or exposed models produce materially different outcomes.

What the Models view answers

The Models view helps answer:

Where do eligible AI systems or exposed models produce materially different outcomes?

SpyderBot distinguishes:

AI System / Surface
Model
Model Version
Model Exposure Status

Exact model/version is shown only when the provider exposes it.

Do not infer a specific hidden model from a provider or product name.


Cross-system vs cross-model

Use cross-model only when actual models are known.

Use:

cross-system
AI-system comparison

when exact underlying models are not exposed.


AI Systems & Models

SpyderBot distinguishes between the AI product/surface being observed and the exact underlying model when that model identity is exposed.

Do not assume a provider name automatically identifies an exact model/version.

Comparing eligible AI systems helps you understand whether an observed pattern is broadly shared or system-specific. A pattern that appears on only one system is not automatically a brand-wide outcome.

An AI Search Surface is an AI-generated answer experience within a search product. It is not the same thing as an AI model. When the AI Search view is configured, interpret NO_AI_ANSWER as the absence of an eligible AI answer for that search observation, not as Brand absence from an AI answer.

See AI Systems & Models and AI Search Surfaces.


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.

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.

Next step

Validate findings in Evidence.