List quality evaluations for an experiment

curl --request GET \
  --url https://api.verlon.ai/v1/ab-tests/:id/quality \
  --header 'Authorization: Bearer <token>'

{
  "error": "<string>",
  "message": "<string>",
  "details": "<unknown>"
}

Experiments

List quality evaluations for an experiment

Use when: caller wants per-response quality evaluations (Layer’s Tracer/Einstein scoring) for an experiment, used for qualitative comparison alongside the quantitative metrics

Paginated list of JudgeMan rubric evaluations attached to the experiment’s requests. Each row carries the per-dimension scores, the pairwise verdict (which variant won), and rationale text. Filter by variant to inspect one side. Drives the per-evaluation drilldown view.

GET

ab-tests

:id

quality

List quality evaluations for an experiment

curl --request GET \
  --url https://api.verlon.ai/v1/ab-tests/:id/quality \
  --header 'Authorization: Bearer <token>'

{
  "error": "<string>",
  "message": "<string>",
  "details": "<unknown>"
}

Authorizations

Authorization

string

header

required

Layer API key (prefixed sk-). Generated from the dashboard under Settings → API Keys, or via layer key create in the CLI.

Query Parameters

variant

string

limit

integer

default:50

Required range: 1 <= x <= 500

offset

integer | null

default:0

Required range: x >= 0

Response

Quality evaluations payload.

Get full experiment analysis (sequential testing + multi-metric + SRM)Get time-series metrics for charting an experiment

Documentation Index

Authorizations

Query Parameters

Response