SpyderBot Documentation

AI Search Surfaces

An AI Search Surface is an AI-generated answer experience within a search product, not an AI model.

What is an AI Search Surface?

An AI Search Surface is an AI-generated answer experience within a search product.

Examples may include supported surfaces such as:

Google Search → AI Overview
Google Search → AI Mode
Bing → Copilot Search

Availability depends on the supported product configuration for your investigation or Observatory.

An AI Search Surface is not the same thing as an AI model.


When the AI Search view appears

The AI Search view appears only when at least one supported AI Search Surface was configured for the investigation or Observatory.


Key interpretation rule

A search can occur without an AI-generated answer being present.

Therefore:

NO_AI_ANSWER

does not mean:

Brand absent from an AI answer

because no eligible AI answer existed for that search observation.


Common AI Search questions

AI Search can help answer:

  • How often was an AI answer available?
  • When an AI answer appeared, how often was the Brand included?
  • How often did the Brand appear across all eligible searches?
  • Which citations appeared in the AI-generated answer region?
  • How do supported Search Surfaces differ?

Search-level and AI-answer-level denominators are different and should not be mixed.


Next step

Return to Prompt Explorer Overview or validate outcomes in Evidence.


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.

SpyderBot observes AI outputs and supporting evidence. It does not have access to the private internal reasoning of third-party AI systems. Prompt Intelligence distinguishes observed outcome, observed association, measured contributor, evidence-supported driver, and causal explanation. A citation appearing alongside a recommendation does not by itself prove that the citation caused the recommendation.

Measurement Scope describes what a result represents. Applicability answers whether a metric makes sense for this measurement scope. Comparability answers whether observation periods can be compared normally. Evidence Strength indicates how strongly eligible observations support a finding. Keep these meanings separate from Prompt Priority and Monitoring Health.