SpyderBot Documentation

Observatory — Prompts

The Prompts view lists the measurement units being observed.

Use it to inspect:

  • prompt/context;
  • source/origin;
  • intent;
  • cluster;
  • Priority where applicable;
  • latest outcome;
  • material changes;
  • Evidence Strength;
  • health;
  • last observed time.

Benchmark memberships may be read-only here. Benchmark composition is managed in Prompt Universe. Do not edit Benchmark Core membership from the Observatory Prompts view.


Prompt detail

A prompt/context detail can include:

Current Snapshot
History
Changes
Evidence

History should use actual observation dates. Missing cycles are not silently replaced with zeros.


Zero, missing, and Context boundaries

Zero is an observed value only when eligible observations exist and the outcome was absent. Example: Brand Mention Rate = 0% is valid only when eligible observations exist and the Brand was not mentioned.

A blank or unavailable value may mean no eligible evidence, not observed, not applicable, unavailable, insufficient evidence, or not comparable. These are not the same as poor performance.

Contexts share Brand and Website identity, but context-dependent intelligence is recalculated. Do not assume historical measurements from one Context automatically become measurements for another Context.


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:

  1. Confirm the Measurement Scope.
  2. Check Applicability.
  3. Check Evidence Strength.
  4. Check AI-system coverage.
  5. Check Comparability for temporal claims.
  6. Open Evidence.
  7. Review exact responses/citations/observations.
  8. 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.

Next step

Investigate material movement in Changes.