OptionalactualActual output data
OptionalallMulti-turn specific: All AgentRun IDs
OptionaldurationDuration in milliseconds
OptionalerrorError message if status is Error
OptionalexpectedExpected output data
Number of checks that failed
OptionalinputInput data used
Oracle results
OptionaloutputsStructured outputs emitted by the driver (screenshots, logs, data, etc.). The engine persists each item as a TestRunOutput entity record.
Number of checks that passed
Overall score
Execution status
OptionaltargetEntity ID identifying the type of target being tested. References Entity.ID (e.g., Entity ID for "MJ: AI Agent Runs"). This is the proper FK reference for entity linkage.
Target entity ID (final AgentRun ID for single/multi-turn)
Optional sub-category or variant label for the test target. Use for ad-hoc labeling or to distinguish test scenarios within the same entity type. Examples: "Summarization", "Classification", "Code Review", "Multi-turn Chat"
Total number of checks
OptionaltotalCost in USD
OptionaltotalMulti-turn specific: Total number of turns
OptionalturnMulti-turn specific: Results for each turn
Result from driver execution