Skip to main content
POST
Analytics V2 Judge (source-grounding)

What it does

The judge takes an answer you already generated and returns a structured verdict on how well each claim is backed by the sources that answer cited. For every cited source it reads the verbatim quoted text plus its metadata (document, type, tickers, dates, publisher, and FactSet fields), then checks each claim against that source. A figure that contradicts its source, or that appears in no cited source, is flagged. The check is deterministic (temperature 0); your prompt is the entire judging instruction and your response_schema defines the verdict shape, so we add no criteria of our own.

Getting the chat_message_id

As you consume the Analytics V2 SSE stream (POST /v2/analytics/sse), the id arrives as its own event:
Capture the event whose event_name == "chat_message_id" and keep data.chat_message_id.

Example

You can only judge answers generated by your own organization; judging another org’s answer returns 404. The call is a single long-running LLM request, so allow a generous client timeout (~160s).

Authorizations

X-API-KEY
string
header
required

Path Parameters

chat_message_id
string<uuid>
required

The assistant answer's ChatMessage UUID. Emitted as the chat_message_id event on the Analytics SSE V2 stream.

Body

application/json
prompt
string
required

Your judging instruction, used verbatim as the judge's system prompt.

Maximum string length: 50000
response_schema
object

Optional JSON Schema for the verdict shape (must serialize to at most 100000 bytes). Omit to use the default verdict schema.

Response

Grounding verdict, shaped by your response_schema.

error
object | null
payload
object