Red Team Evaluations

Start Red Team Evaluation

Start a new red team client workflow. Auto-triggers planning phase. Client should then poll /next-action.

post/evaluations/v1-beta/red-team

Request body

namestring required

Name for this evaluation

target_modelstring required

Target model identifier

objective_idsstring[]

Objective IDs to evaluate

execution_strategy_typestring

Execution strategy type

n_random_techniquesinteger

Number of random techniques to use

max_parallel_techniquesinteger

Maximum parallel techniques

max_turnsinteger

Maximum conversation turns

attacker_max_generation_attemptsinteger

Maximum generation attempts for attacker

refusal_judge_modelstring

Model for refusal judging

objective_judge_modelstring

Model for objective judging

evaluation_report_modelstring

Model for evaluation report

attacker_modelstring

Model for attacker

hl_project_idstring

HiddenLayer project ID

prompt_set_idstring

Prompt set ID for static prompt evaluation

sessions_per_techniqueinteger

Number of sessions per technique

target_system_promptstring

System prompt for the target

Response

Workflow started successfully

workflow_idstring required

Workflow identifier

run_idstring required

Run identifier

Changes