SecurityInsight settings · Settings > AI
AI for privilege tier catalog
| Key | SI_PrivilegeTierClassifier_RunAI |
|---|---|
| Where | Settings > AI > Where AI is used |
| Type | On / off |
| Default | On. |
| Edition | Community |
What it does
An override for ONE engine: whether the privilege tier classifier asks Azure OpenAI to tier new roles and permissions. It follows its own switch, not AI integration: it calls AI whenever the Azure OpenAI settings are set, unless this is off.
When enabled
On is the default: it works as described under "What it does".
When disabled
Turning it off sends nothing to Azure OpenAI: roles and permissions already in the catalog keep their tier, and new ones are left unresolved for manual review. Removes AI cost for this engine.
Risk and how to reverse it
With the Azure OpenAI settings set, new role and permission names are sent to YOUR Azure OpenAI deployment, and each call costs; off leaves new ones untiered for manual review. Reversible at once.
Requires
Read by: privilege-tier-classifier.
Recommended
Keep the default; turn it off only to keep AI out of this engine.
Documented for SecurityInsight 3.0.79. Written by the SecurityInsight team; Invardia publishes it. · All settings · Security review pack