SpyderBot Documentation
Explorer — Entities
The Entities view helps you understand which organizations, products, or other resolved entities appear in observed responses.
Depending on applicability, entity intelligence may include:
- Recommendation Rate — how often the entity is recommended within the eligible measurement scope.
- Mention behavior — how and how often the entity appears in eligible responses.
- Top-2 Gap — the difference between the leading entity and the second-ranked entity for the selected outcome.
- AI-System Support — how broadly the observed outcome appears across eligible AI systems.
- Outcome Consistency — how consistently the outcome appears across repeated eligible observations.
- Evidence Strength — how strongly the available evidence supports the finding.
Always interpret a metric together with its Measurement Scope and applicability.
Do not treat an unresolved entity label as automatically equivalent to a canonical Brand.
Measurement Scope and Applicability
Measurement Scope describes what a result represents. Depending on the workflow, it may include Context, prompts, AI systems, exposed models/versions, market, language, observation depth, observation dates, and filters.
Applicability answers: Does this metric make sense for this measurement scope? A metric can be Not Applicable without indicating poor performance.
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.