Issue
AI Touches Unrelated Scope
The AI affects, edits, analyzes, changes, or reasons over material outside the scope of the requested task.
What This Looks Like
The user asks the AI to work on a specific file, field, section, task, issue, or decision, but the AI also touches unrelated scope. It may edit nearby content, analyze irrelevant material, modify other files, introduce unrelated recommendations, or make changes outside the declared work area.
Why It Matters
Scope control protects work from unintended side effects. When the AI touches unrelated scope, the user has to audit areas that should not have been affected. In agentic or tool-based workflows, this can create real changes outside the user’s intended permission boundary.
Structural Signal
The requested work has a bounded scope, but the AI’s behavior crosses into adjacent or unrelated scope. The issue is not that the AI did extra thinking; it is that the work surface affected by the AI exceeds the declared task boundary.
Common Triggers
- The prompt names the target but does not explicitly forbid adjacent changes
- The AI treats nearby material as part of the task
- The agent has broad file or tool access
- A repair instruction is applied globally instead of locally
- The model optimizes the surrounding context rather than the requested element
- The workflow does not distinguish read scope from change scope
When to Use This Issue
Use this Issue when the AI affects or reasons over unrelated scope in a way that changes, expands, or complicates the task beyond what the user requested.
When Not to Use This Issue
Do not use this Issue when the AI only references related context to understand the task and does not change or rely on it improperly. Use this Issue when unrelated scope is actually touched, changed, or allowed to govern the output.
Category
Primary Pattern
Declared Patterns
Overreach
A structural condition where actions, effects, authority, or modifications extend beyond declared scope without authorization.
Boundary Leakage
A structural condition where effects, permissions, state, data, or authority cross a declared boundary without an authorized exception.
Unbounded Scope
A structural condition where an operation, authority, rule, or expansion has no declared upper bound, boundary, or termination condition.
Derived Primary Lenses
Boundary Compliance Lens
Evaluates observed structure against declared boundary posture, including allow, block, and exception rules.
Constraint Sufficiency Lens
Evaluates whether declared constraints are sufficient to eliminate structural degrees of freedom.
Isolation Boundary Lens
Evaluates whether structural constraints, effects, and regions remain contained within declared boundaries.
Overreach Lens
Detects structure that exceeds declared scope or authority reach.
Propagation Lens
Traces how structural declarations, effects, or state changes propagate across boundaries or stages.
Derived Secondary Lenses
Related AI-Adjacent Issues
One Workspace Affects Another
State, memory, files, permissions, settings, tools, or workflow effects from one workspace affect another workspace where they should not apply.
Tool Effect Crosses Target Boundary
A tool, connector, function, or integration affects an object, file, record, workspace, or state surface beyond the intended target.
Search Intents
- AI touches unrelated scope
- AI changed unrelated content
- agent edited files not requested
- AI affected something outside task
- AI included unrelated scope
- agent went outside requested area