Custom JSON
Custom JSON is the generic Evidence Bridge entry point for systems with their own schema: define a deterministic mapping profile, then satisfy the eligibility rules of a supported evidence family.
Custom JSON is the generic Evidence Bridge entry point for systems without a predefined integration template. Users provide a sample source payload and define a deterministic mapping profile.
Custom JSON does not mean that any JSON can automatically become certified evidence. The mapped payload must still satisfy the semantic eligibility rules of a supported evidence family.
Flow
Custom JSON -> Mapping Profile -> Evidence Eligibility -> AI Execution V2AI execution example
{
"execution_id": "run-easy-001",
"occurred_at": "2026-09-10T10:15:00.000Z",
"provider": "openai",
"requested_model": "gpt-4.1",
"execution_role": "advisory",
"parameters": { "temperature": 0.2, "max_tokens": 250 },
"input": { "prompt": "Summarize this customer complaint." },
"output": { "summary": "The customer is requesting a refund." }
}| Source JSON pointer | Evidence semantic |
|---|---|
/execution_id | Execution ID |
/occurred_at | Occurrence time |
/provider | Requested provider |
/requested_model | Requested model |
/execution_role | Execution role |
/input | Actual captured input |
/output | Actual captured output |
Consequential execution example
{
"execution_id": "refund-42",
"occurred_at": "2026-09-10T10:15:00.000Z",
"component": "refund-worker",
"action_type": "REFUND",
"target_resource": { "type": "order", "id": "order-42" },
"pre_state": { "status": "paid" },
"action_applied": { "refund": 42 },
"outcome": "APPLIED",
"post_state": { "status": "refunded" }
}Producer / executing component: component is one possible source field. A stable producer field can have another name or appear elsewhere in the payload.
Custom JSON -> Mapping Profile -> Evidence Eligibility -> Consequential Execution V1When required semantics are missing
targetEligible = falseNo CER is created. The NexArt Node is not called.
Review the required semantics for AI Execution V2 and Consequential Execution before building a custom profile, and see Mapping profiles for the available transforms.