SpyderBot Documentation
Choose Your Workflow
Use this guide when you know what you want to learn but are not sure which part of Prompt Intelligence to use.
Choose the tool that matches your question
| If you want to... | Start with |
|---|---|
| Discover the important AI questions around your Brand | Prompt Universe |
| Understand which customer intents exist | Prompt Universe → Intent Landscape |
| Find the highest-priority questions | Prompt Universe → Prompt Priority |
| Decide which prompts to investigate now | Recommended Analysis Set / Recommended list |
| Investigate what AI says now | Prompt Explorer |
| Compare AI systems or models | Prompt Explorer → Models |
| Inspect entities and recommendations | Prompt Explorer → Entities |
| Inspect cited sources | Prompt Explorer → Sources |
| See exact supporting responses | Evidence |
| Monitor questions continuously | Prompt Observatory |
| Understand what changed | Prompt Observatory → Changes |
| Monitor source movement over time | Prompt Observatory → Sources |
| Monitor Brand portrayal and sentiment over time | Prompt Observatory → AI Brand Portrayal |
| Build a stable longitudinal AI Visibility benchmark | Prompt Universe → AI Visibility Benchmark |
| Measure a specific product separately | Create/select a Context → Prompt Universe |
| Analyze a supported AI Search Surface | AI Search Surfaces |
| Understand whether a result is usable | Evidence Strength + Applicability + Comparability |
Common workflows
I do not know which prompts matter
Prompt Universe → Intent Landscape → Prompt Priority → Recommended list / Recommended Analysis Set
I know the prompt and want to understand current AI behavior
Prompt Explorer → Overview → Entities / Sources / Models → Evidence
I want to know whether behavior changed
Prompt Observatory → Overview → Changes → Evidence
I want a stable strategic benchmark
Prompt Universe → Build AI Visibility Benchmark → Review Benchmark → Start Observing → Benchmark Observatory
I want to analyze one product separately
Brand → + New Context → select Product → confirm Context → build Prompt Universe
Next step
Start with Prompt Universe when you need to decide what matters, or Prompt Explorer when you already know the questions to investigate.
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.