SpyderBot Documentation
Observatory — Sources
The Sources view helps you understand how source evidence appears and changes over time.
The three primary source questions are:
Source Ecosystem Distribution
Where does current source evidence come from?
AI × Source Matrix
How do source patterns differ across AI systems?
Source Presence Over Time
How is source behavior changing?
Do not treat source movement as automatic causality for AI outcome movement.
Source Ecosystem dimensions
SpyderBot distinguishes source dimensions such as Ownership, Channel, Platform, Content Type, Publisher / Creator / Community, and Content Item.
Prefer wording such as sources cited in observed responses. Avoid claiming that a cited source caused an AI recommendation or portrayal change.
Comparability for source history
Comparability answers: Can these observation periods be compared normally?
Comparability can be affected by membership, AI-system scope, market/language, measurement protocol, Benchmark version, and Context version. If a comparison is not valid, do not interpret a missing delta as “no change.”
Missing source enrichment is not negative evidence. Charts and tables should use actual eligible observation dates rather than carrying missing values forward as zero.
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.