SpyderBot Documentation
Prompt Explorer Overview
Prompt Explorer is SpyderBot's on-demand investigation workspace for understanding what AI systems say now and what evidence supports the result.
What is Prompt Explorer?
Prompt Explorer is SpyderBot's on-demand investigation workspace for understanding what AI systems say now, how broadly an observed pattern appears across AI systems and observation contexts, how strong the evidence is, and what action is justified by that evidence.
It can investigate one or more prompts.
Prompt Explorer is not limited to one prompt at a time.
When to use Prompt Explorer
Use Prompt Explorer when you need to:
- investigate a recommendation gap;
- compare multiple AI systems;
- understand entity outcomes;
- inspect citations and source patterns;
- investigate a selected set from Prompt Universe;
- validate a hypothesis before continuous observation;
- inspect exact response evidence.
Prompt Explorer vs Prompt Observatory
| Prompt Explorer | Prompt Observatory |
|---|---|
| On-demand investigation | Continuous observation |
| Point-in-time analytical snapshot | Longitudinal history |
| Understand current observed patterns | Detect and investigate change |
| Can investigate 1..N prompts | Can observe 1..N measurement units |
| Best for current-state investigation | Best for monitoring |
Explorer is not a required prerequisite for Observatory.
Prompt Explorer views
A completed investigation uses:
Overview Prompts Entities Sources Models Evidence
If at least one AI Search Surface was configured, the investigation may also show:
AI Search
Product boundary
| Capability | In Prompt Explorer | Elsewhere |
|---|---|---|
| Strategic question discovery | No — use Prompt Universe | Prompt Universe |
| Point-in-time investigation | Yes | — |
| Continuous change monitoring | No — hand off to Observatory | Prompt Observatory |
| Export of investigation evidence | Yes (Evidence package / export) | Prompt Intelligence Exports |
Next step
Create an investigation from Create an Investigation.
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.