SpyderBot Documentation
Understanding Your Universe
Prompt Universe organizes Cluster × Intent into Intent Segments, Core Prompts, and Prompt Variations.
The hierarchy
A useful way to understand Prompt Universe is:
Cluster × Intent
↓
Intent Segment
↓
Core Prompt
↓
Prompt Variations
Cluster
A business/topic area.
Example:
AI Visibility Platforms
Intent Type
SpyderBot uses a fixed intent taxonomy:
LEARN DISCOVER SOLVE EVALUATE COMPARE SELECT VALIDATE BUY
Intent Segment
An Intent Segment is the actual business-specific decision space produced by:
Cluster × Intent
Example:
AI Visibility Platforms × SELECT
Core Prompt
A Core Prompt is the canonical strategic question representing one distinct decision space after semantic deduplication.
Example:
What are the best AI visibility platforms for enterprise teams?
Prompt Variation
A Prompt Variation is a materially equivalent alternative wording of a Core Prompt.
A variation should preserve the same:
- semantic intent;
- decision context;
- materially equivalent candidate set.
If the meaning changes materially, it should become another Core Prompt rather than a variation.
Next step
Review how intents are distributed in Intent Landscape.
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.