SpyderBot Documentation
Core Prompts & Variations
Core Prompt is the preferred user-facing term for the canonical strategic question; Prompt Variations represent equivalent wording without artificial duplication.
Core Prompt
Core Prompt is the preferred user-facing term for the canonical strategic question.
Core Prompts are designed to represent distinct decision environments rather than every wording a user might type.
Prompt Variation
Prompt Variations help represent natural differences in wording without creating artificial duplication.
Example:
Core Prompt:
What are the best AI visibility platforms?
Possible variations:
- Which AI visibility platforms should I consider?
- Best platforms for tracking visibility in AI answers.
A variation should not cross a meaningful change in user intent or decision context.
For example:
What is AI visibility?
is a learning question and should not be treated as a variation of:
Which AI visibility platform should I buy?
Prompt Variations and external demand
External search queries or demand signals are not automatically Prompt Variations.
Prompt Universe may use external signals to help understand demand, but raw search volume is not the primary measure of strategic importance.
Next step
Use Prompt Priority to decide which Core Prompts to investigate or observe first.
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.