Behavior Intelligence · Scoped answers

What approval or permission controls are documented?

Codex documents configuration-dependent approval escalation, Claude Code documents deny/ask/allow rules and permission modes, Gemini CLI documents confirmation and isolation boundaries, and Cursor CLI documents allow/deny operation controls. The selected Claude and ChatGPT evidence does not establish comparable approval models, so no permission behavior is inferred for those surfaces.

Six product answers

What the selected evidence establishes

Anticipate which actions may pause for consent or be constrained by client and workspace configuration.

Open-source agentic coding interface

OpenAI Codex

Documented

Direct factual answer

Codex's selected excerpt says terminal and patch calls may be escalated to the user for approval depending on configuration.

Surface: Codex CLI
Model context: GPT-5.2
Configuration / version scope: The specific run determines which calls require escalation.
Reviewed: 2026-08-11

Limits and uncertainty

The excerpt does not define every sandbox or approval mode.

Evidence

Web, desktop, and mobile AI assistant

Claude

Not established

Direct factual answer

The selected Claude prompt evidence does not establish an approval or permission-control model for product tools.

Surface: Not established
Model context: Not established
Configuration / version scope: Not established
Reviewed: 2026-08-11

Limits and uncertainty

This answer does not cover Claude Code permissions.

Evidence

No supporting evidence is linked because the selected sources do not establish this behavior.

Multi-surface agentic coding product

Claude Code

Documented

Direct factual answer

Claude Code documents deny, ask, and allow rules with precedence, plus permission modes that constrain tool execution.

Surface: Claude Code terminal CLI · Claude Code IDE integrations
Model context: Not established
Configuration / version scope: Rules can be managed at different settings scopes and by the client environment.
Reviewed: 2026-08-11

Limits and uncertainty

The selected evidence does not establish every deployment policy.

Evidence

Open-source agentic command-line interface

Gemini CLI

Documented

Direct factual answer

Gemini CLI documents confirmation for mutating file and shell tools, with sandboxing and trusted-folder boundaries.

Surface: Gemini CLI
Model context: Not established
Configuration / version scope: Security policy and isolation settings shape the actual boundary.
Reviewed: 2026-08-11

Limits and uncertainty

The selected evidence does not establish every enterprise policy.

Evidence

Multi-surface conversational AI product

ChatGPT

Not established

Direct factual answer

The selected ChatGPT sources document user-facing capabilities but do not establish a general tool approval or permission model.

Surface: Not established
Model context: Not established
Configuration / version scope: Not established
Reviewed: 2026-08-11

Limits and uncertainty

Product settings are not converted into a universal execution-control claim.

Evidence

No supporting evidence is linked because the selected sources do not establish this behavior.

AI code editor and agentic coding product

Cursor

Documented

Direct factual answer

Cursor CLI documents global and project allow or deny controls for shell, read, and write operations, with deny rules taking precedence.

Surface: Cursor CLI
Model context: Not established
Configuration / version scope: Editor and CLI control surfaces can differ.
Reviewed: 2026-08-11

Limits and uncertainty

The selected evidence does not establish every organizational policy layer.

Evidence