Prompt Does Not Say What to Exclude

The prompt declares what to include but does not declare what should be excluded, allowing unwanted scope, sources, content, or actions into the result.

What This Looks Like

The prompt tells the AI what to include, but does not say what to exclude. The output may bring in extra topics, sources, assumptions, sections, examples, actions, or surrounding context that the user did not want but also did not explicitly rule out.

Why It Matters

Inclusion rules do not automatically create exclusion boundaries. If the prompt does not declare what should stay out, the AI may expand into adjacent material that feels helpful but changes the task. This creates review burden and can make output appear noncompliant even when the prompt did not define the boundary.

Structural Signal

The task has positive guidance but lacks negative constraints. The issue is not simply that the AI overreached; it is that the prompt does not provide enough exclusion structure to prevent unwanted scope from entering the output.

Common Triggers

The prompt says what to cover but not what to avoid
Source boundaries are implied rather than explicit
The AI fills gaps with adjacent examples or background
The task asks for a focused answer without defining out-of-scope areas
The model treats related material as relevant
The output format has no section or content exclusion rules

When to Use This Issue

Use this Issue when unwanted material enters the output because the prompt declares inclusion but does not clearly declare exclusions.

When Not to Use This Issue

Do not use this Issue when exclusions are clearly stated and the AI ignores them. Do not use it when broad coverage was requested.

Primary Pattern

PAT-0170 — Constraints Underspecified

Declared Patterns

PAT-0170 — Constraints Underspecified
A structural condition where declared constraints are insufficient to eliminate ambiguity or multiple admissible states.
PAT-0140 — Boundary Leakage
A structural condition where effects, permissions, state, data, or authority cross a declared boundary without an authorized exception.
PAT-0400 — Unbounded Scope
A structural condition where an operation, authority, rule, or expansion has no declared upper bound, boundary, or termination condition.

Derived Primary Lenses

LEN-0160 — Constraint Sufficiency Lens
Evaluates whether declared constraints are sufficient to eliminate structural degrees of freedom.
LEN-0220 — Isolation Boundary Lens
Evaluates whether structural constraints, effects, and regions remain contained within declared boundaries.
LEN-0250 — Propagation Lens
Traces how structural declarations, effects, or state changes propagate across boundaries or stages.

Derived Secondary Lenses

LEN-0120 — Boundary Compliance Lens
Evaluates observed structure against declared boundary posture, including allow, block, and exception rules.
LEN-0180 — Determinism Lens
Evaluates whether identical structural inputs produce equivalent structural outputs across repeated executions.
LEN-0190 — Escalation Gradient Lens
Measures structural growth or intensification across sequential executions, states, or transitions.
LEN-0290 — Variance / Entropy Lens
Measures structural variability across repeated or comparable evaluations and identifies divergence beyond expected bounds.

Search Intents

prompt does not say what to exclude
AI included things I did not want
missing exclusion rule
prompt only says what to include
AI used unwanted content
need to tell AI what not to include

Ontology Metadata

Code: ISS-0076
Version: ISS-0076@0.1.0
Ontology release: 0.1.0
Updated: 2026-05-10T00:00:00Z

History

No public history entries recorded.

View full ontology changelog