AI-Adjacent Issue
Low-Level Configuration Overrides Workflow Policy
A low-level configuration, product setting, connector rule, runtime option, or environment flag overrides the workflow policy the user expects to govern the task.
What This Looks Like
The workflow policy says one thing, but a lower-level configuration or product setting causes different behavior. A connector rule, environment flag, runtime option, tool setting, workspace configuration, model mode, or deployment setting may override the policy the user expects to control the task.
Why Users Blame AI
The user sees the AI behaving against the visible workflow policy. The actual cause may be buried in configuration below the policy layer. The AI looks inconsistent or disobedient because the governing rule is not the one the user can see.
What to Check First
- Whether product, workspace, connector, or runtime settings conflict with workflow policy
- Whether a hidden or lower-level rule has higher practical authority
- Whether the workflow policy is documented but not enforced in runtime configuration
- Whether tool permissions override prompt or policy intent
- Whether configuration differs between environments
- Whether the user can inspect which rule actually governed behavior
When This Is AI-Adjacent
Use this AI-Adjacent Issue when low-level configuration overrides the workflow policy expected by the user. If a hidden rule overrides a visible instruction, use the related Workbench Issue. If tool and prompt rules conflict, use that related Issue.
Related Workbench Issues
Hidden Rule Overrides Visible Instruction
A hidden, upstream, system, policy, tool, or product rule changes or overrides the visible instruction the user expects the AI to follow.
Actual Policy Differs From Declared Policy
The policy the AI or workflow actually follows differs from the policy that is documented, declared, displayed, or expected.
Tool Rules and Prompt Rules Conflict
Tool, connector, function, or MCP rules conflict with prompt instructions, causing the AI or agent to face incompatible requirements.
Behavior Does Not Match Declared Role
The AI or agent behaves outside, below, or differently from the role, authority, responsibility, or permission posture declared for it.
Permissions Conflict After Being Combined
Permissions, approvals, roles, policies, or authority rules that seem valid separately conflict when combined in the same workflow or AI action.
Common Ways People Describe This
- low level configuration overrides workflow policy
- configuration overrides AI policy
- product setting overrides workflow rule
- connector setting overrides prompt
- runtime config changes AI behavior
- hidden configuration overrides visible policy