Fetch a judgment with its copies
const url = 'https://example.com/v1/judgments/example';const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};
try { const response = await fetch(url, options); const data = await response.json(); console.log(data);} catch (error) { console.error(error);}curl --request GET \ --url https://example.com/v1/judgments/example \ --header 'Authorization: Bearer <token>'Returns the judgment (live or not) with the stored copy of the run’s input and output and, when the judgment pointed at an item, its value.
Authorizations
Section titled “Authorizations”Parameters
Section titled “Parameters”Path Parameters
Section titled “Path Parameters”Judgment id.
Responses
Section titled “Responses”Judgment with copies.
A judgment with the stored copies of what was judged.
object
What a judged run ran: an agent at a version, or a flow at a version.
object
The judged item of a run’s output.
object
The caller’s stable id for the item. kindgi:correction is reserved: a judgment on it is accepted only when it carries a correction at pointer "".
Where the item is in the run’s output, as a JSON Pointer (RFC 6901), e.g. /matches/2. "" is the whole output.
The item’s position in a ranked list (0 = first).
The expert’s correction of the run’s decisions, when they gave one.
object
The calls the agent should have made.
object
The partial set of top-level argument fields to compare, by value. Fields left out are not compared; an empty object asks only that the tool was called. At most 4000 characters in canonical JSON.
object
Tools that should not have been called at all.
The judge class the judgment is recorded under. Absent when unclassified (counts with weight 1).
Present (true) when the judge class was restricted (assertableBy) when the judgment was recorded, so the judge was checked against it. A restriction added or lifted later doesn’t change it.
Who asserted a judgment: the authenticated caller, never a typed name.
object
A user id, or for a service token its token or session id.
The app’s opaque id for its end user who judged, when an app judged on their behalf.
Set when the judgment was removed or superseded.
The judgment that replaced this one.
The stored copy of a judged run’s input and output, taken when it was first judged.
object
What a judged run ran: an agent at a version, or a flow at a version.
object
What a judged run needs besides its input to be replayed, captured when it was first judged. For an agent turn: the conversation before it, what its retrievals returned, and the decision at its session approval gate. For a flow run: its tool calls with their results. For both: the env values its tools were sent.
object
The conversation’s messages before the turn, oldest first (at most the last 200).
Whether older messages were left out of history.
What the turn’s retrievals returned.
Messages of earlier conversations the turn recalled (intents over conversations), as quoted to the model.
The reviewer’s decision at the turn’s session approval gate, when the turn waited on one. A replay of the turn follows it.
object
The reviewer’s reason for a rejection.
For a flow run: what it did, kept at its first judgment so it can be replayed. Every tool call it made with its result (at its tool nodes, in its agent steps’ turns and in its sub-flows), at most 500, and its agent steps.
object
object
The run that made it: the flow run, a sub-flow’s, or an agent step’s turn.
The tool node that made it, or the agent step whose turn did.
The loop iteration, in a loop body.
An agent step’s turn kept the result as outside data: another system’s answer to a paused call, or a result its tool says is outside data. A replay hands it to the model as data, as the turn did. Absent for a tool node’s call, and for a run judged before the mark was kept.
object
What the step’s turn retrieved.
Messages of earlier conversations the step’s turn recalled.
More calls were made than were kept.
The env values each tool’s calls were sent (needsSpec.env), by tool id: its first call’s, as the run recorded them. A replay sends them to a read-only tool it runs live, so the tool reads the config the run saw, not today’s. Absent for a run from before env was recorded.
object
object
When the judged run is a comparison’s replay: the run it re-ran, stamped at its first judgment. A test set built from judgments leaves replays out.
The segment path the run was started with (empty: none). Absent for runs judged before it was recorded.
object
Lowercase, like an identifier: company, contact-role.
The judged item’s value, when the judgment pointed at it.
Example
{ "subject": { "kind": "agent" }, "verdict": "yes", "restricted": true, "assertedBy": { "kind": "user" }, "run": { "subject": { "kind": "agent" }, "context": { "flow": { "calls": [ { "fromEvent": true } ] } } }}Missing / malformed / expired / revoked bearer token.
object
object
Stable machine-readable discriminant. Values match domain error codes (see docs/API-ROUTE-CONVENTIONS.md §4.3).
Optional, kind-specific.
object
Server-assigned request id; also echoed via X-Request-Id header.
Examplegenerated
{ "error": { "code": "example", "message": "example", "details": {}, "requestId": "example" }}No judgment with that id under this tenant.
object
object
Stable machine-readable discriminant. Values match domain error codes (see docs/API-ROUTE-CONVENTIONS.md §4.3).
Optional, kind-specific.
object
Server-assigned request id; also echoed via X-Request-Id header.
Examplegenerated
{ "error": { "code": "example", "message": "example", "details": {}, "requestId": "example" }}The database was too busy to answer in time (database-busy); Retry-After (whole seconds) says when to try again.
object
object
Stable machine-readable discriminant. Values match domain error codes (see docs/API-ROUTE-CONVENTIONS.md §4.3).
Optional, kind-specific.
object
Server-assigned request id; also echoed via X-Request-Id header.
Examplegenerated
{ "error": { "code": "example", "message": "example", "details": {}, "requestId": "example" }}