Interface RecordResult

Deep-trace link to an Action Execution Log, when the work was an Action.

Deep-trace link to an AI Agent Run, when the work was an Agent.

Deep-trace link to an AI Prompt Run, when the work was an Infer-and-Write-Back.

Number of attempts made for this record.

The outputs answered below their confidence floor and withheld.

Per-output confidence scores keyed by output Name: the driver's own, else the answer's at each ConfidenceRef.

True when a dry run computed the record (nothing written, no Outcome).

Processing duration in milliseconds (the engine fills this in if the processor does not).

Error detail when Status is Failed.

Set when the answer was rejected (see RecordFailureKind): the run counts it apart from other failures.

Reference to the FeatureValueCache entry when served from or saved to the cache.

Whether this record's values and write-back changed anything. Absent on a dry run.

The MJ: AI Prompts row behind AIPromptRunID and PromptVersionHash, when it is not the Record Process's own prompt (an escalated record is answered by its target prompt). Absent means the process's own prompt.

Content hash of the prompt version / instructions used to compute this record's result.

Structured output payload produced for the record (persisted as JSON on the detail row).

Whether the record succeeded, failed, or was skipped.

Non-fatal problems with this record's processing (e.g. its cache entry could not be stored).