Aident Loadout を通じて Metatextai Tools の Metatextai Evaluate を使用します。実行前に入力、出力、設定、料金、リスクを確認できます。
Tool to evaluate LLM messages against policies/guardrails. Use after generating model output to get violation details or corrections.
messages必須arrayConversation messages to evaluate. Must include 'user' and 'assistant' messages; 'system' optional.
policiesarrayInline policies to evaluate; overrides console defaults when provided.
fail_fastbooleanIf true, stops evaluation on first violation.
policy_idsarrayList of policy IDs to override default console policies.
applicationstringApplication identifier; defaults to your configured application ID.
override_responsestringTop-level override response message on violation. Overrides correction.
correction_enabledbooleanIf true, returns corrected output when violations occur (unless override_response is set).
data必須Data from the action execution
errorstringError if any occurred during the execution of the action
successful必須booleanWhether or not the action execution was successful or not
API キー接続。リスクレベル 2/5。
無料 Action
この Action を明示的に参照する公開 Skills はまだありません。