Skip to main content
POST
Run the A/B benchmark suite for this skill's latest version

Authorizations

Authorization
string
header
required

Enter your API key (e.g. dai_sk_test_key_001)

Headers

Authorization
string

Path Parameters

skill_name
string
required

Query Parameters

triggered_by
string
default:api

Where this run was kicked off from

model
string | null

Override the agent-arm model (e.g. claude-haiku-4-5 for the model-relative lane). Must be in GET /api/v1/auth/models. Default: the platform's configured model. The executed model is recorded as runner_model on the run.

runs
integer
default:1

Re-run the WHOLE suite this many times, uniformly (1-10; default 1). Every (case, run) record enters the aggregate at equal weight, so the headline pass-rate is a MEAN over runs whose expected value does not depend on this count — more runs only narrow the error bars (ADR-0007). This is the run-level replacement for the retired per-case pass^k trials.

Required range: 1 <= x <= 10

Cookies

decimal_session
string | null

Response

Successful Response