odei_guardrail_check
Validate agent actions against safety guardrails before execution. Checks financial transactions, communications, and scheduling against 7 layers of constraints including financial limits, time restrictions, and value alignment.
Instructions
Validate an agent action against ODEI's constitutional guardrails. Returns APPROVED, DENIED, or NEEDS_REVIEW with reasoning. Use this before executing any action that could affect finances, reputation, health, or relationships. The guardrail system checks against 7 layers of safety constraints including financial limits, time-of-day restrictions, and value alignment.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| action | Yes | The action to validate (e.g., "Transfer 5 ETH to external wallet", "Post tweet about token price", "Schedule meeting at 11pm") | |
| context | No | Additional context about the action — who initiated it, why, what system it affects | |
| domain | No | Which domain layer this action operates in | |
| severity | No | Self-assessed severity of the action (helps calibrate the check) |