SpyderBot Documentation
Citations & Sources
The Citations view helps you understand which sources are cited or referenced in observed AI responses and how the source ecosystem is structured.
What the Citations view answers
The Citations view helps you understand:
- which sources are cited or referenced in observed AI responses;
- who publishes or controls those sources;
- which channels and platforms appear;
- which content types appear;
- how source presence varies across AI systems;
- which source gaps are associated with high-priority prompts.
Source Ecosystem
SpyderBot distinguishes source dimensions such as:
Ownership Channel Platform Content Type Publisher / Creator / Community Content Item
A YouTube citation, for example, should not be understood only as:
youtube.com
The meaningful source may be a specific channel/creator and a specific video.
Citation Presence vs Citation Share
These answer different questions.
Citation Presence Rate
How often a source/dimension is present across eligible prompt-level observations.
Citation Share
How much of total citation occurrence belongs to a source/dimension.
Do not assume both metrics use the same denominator.
AI Brand Portrayal vs Source Brand Portrayal
Keep these separate.
AI Brand Portrayal = how the AI response portrays the Brand Source Brand Portrayal = how the cited source content portrays the Brand
A cited source does not automatically cause the AI response to adopt the same portrayal.
Causality
Use wording such as:
Sources cited in observed responses.
Avoid:
Sources that caused the AI answer.
Source association does not prove causal influence.
Next step
For longitudinal measurement of strategic questions, continue to AI Visibility Benchmark.
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:
- Confirm the Measurement Scope.
- Check Applicability.
- Check Evidence Strength.
- Check AI-system coverage.
- Check Comparability for temporal claims.
- Open Evidence.
- Review exact responses/citations/observations.
- 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.