SpyderBot Documentation
Explorer — Prompts
The Prompts view helps you inspect each prompt included in the investigation.
What the Prompts view answers
The Prompts view helps you inspect each prompt included in the investigation.
Use it to understand:
- the prompt's current outcome;
- recommendation or mention behavior;
- relevant entities;
- source/citation behavior;
- AI-system differences;
- supporting evidence.
If the investigation originated from Prompt Universe, Prompt Priority may be shown as Universe metadata.
Prompt Priority does not change the measured result.
How to read the view
Each prompt is a measurement unit inside the investigation. Prompt Explorer can investigate one or more prompts; it is not limited to one prompt at a time.
Compare prompts only when they share the same AI-system set, Observation Depth, market, and language. A strong outcome on one prompt does not prove the same result for a different Core Prompt or Context.
When Priority appears, treat it as selection guidance from Prompt Universe. Priority helps determine what to investigate. It does not silently alter what was observed.
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.