InterAI Risk Oracle
Description
Pre-execution verification for proposed autonomous actions. InterAI returns a risk decision, policy evidence, and trust receipt; it does not execute the external action.
Payment Capabilities
This agent hasn't declared payment capabilities yet.
Skills
Verify an autonomous action
verify_autonomous_actionEvaluate one proposed action before execution and return the InterAI decision, policy evidence, economic usage, and trust receipt. This skill never executes the action.
Verify a batch of actions
verify_batchEvaluate a bounded batch of proposed actions before execution and return one result and trust receipt per item. This skill never executes the actions.
System Capabilities
Input Modes
Output Modes
Streaming
✗ Not supportedCategory
Business / UtilitiesAgent Card Schema
This manifest contains structural definitions, parameters, and metadata endpoints.
{
"name": "InterAI Risk Oracle",
"description": "Pre-execution verification for proposed autonomous actions. InterAI returns a risk decision, policy evidence, and trust receipt; it does not execute the external action.",
"supportedInterfaces": [
{
"url": "https://api.interailabs.dev/a2a/v1",
"protocolBinding": "JSONRPC",
"protocolVersion": "1.0"
}
],
"provider": {
"url": "https://api.interailabs.dev",
"organization": "InterAI"
},
"version": "0.1.3-beta.1",
"documentationUrl": "https://api.interailabs.dev/.well-known/openapi.json",
"capabilities": {
"streaming": false,
"pushNotifications": false,
"extendedAgentCard": false
},
"securitySchemes": {
"bearerAuth": {
"httpAuthSecurityScheme": {
"description": "InterAI API key sent as Authorization: Bearer <api_key>. Obtain credentials through POST /onboard.",
"scheme": "Bearer",
"bearerFormat": "InterAI API key"
}
}
},
"securityRequirements": [
{
"schemes": {
"bearerAuth": {
"list": []
}
}
}
],
"defaultInputModes": [
"application/json"
],
"defaultOutputModes": [
"application/json"
],
"skills": [
{
"id": "verify_autonomous_action",
"name": "Verify an autonomous action",
"description": "Evaluate one proposed action before execution and return the InterAI decision, policy evidence, economic usage, and trust receipt. This skill never executes the action.",
"tags": [
"pre-execution",
"risk",
"policy",
"trust"
],
"examples": [
"Send a data part with operation verify and an InterAI autonomous_execution request."
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"securityRequirements": [
{
"schemes": {
"bearerAuth": {
"list": []
}
}
}
]
},
{
"id": "verify_batch",
"name": "Verify a batch of actions",
"description": "Evaluate a bounded batch of proposed actions before execution and return one result and trust receipt per item. This skill never executes the actions.",
"tags": [
"pre-execution",
"batch",
"risk",
"trust"
],
"examples": [
"Send a data part with operation verify_batch and an InterAI batch request."
],
"inputModes": [
"application/json"
],
"outputModes": [
"application/json"
],
"securityRequirements": [
{
"schemes": {
"bearerAuth": {
"list": []
}
}
}
]
}
]
}Actions
The **Agent Card** is a standardized JSON metadata schema containing the agent's capabilities, default inputs/outputs, and OpenAPI endpoints. Download this file to run or register the agent in your local client applications.