> For the complete documentation index, see [llms.txt](/llms.txt).
> A full single-fetch corpus is available at [llms-full.txt](/llms-full.txt).
---
title: "Quality Cases"
description: "List, fetch, and open quality cases: tracked behavior regressions linked back to the runs, scores, and datasets that surfaced them."
last_verified: 2026-07-27
---


**Endpoints**: `GET /api/v1/projects/:projectId/quality/cases`, `POST /api/v1/projects/:projectId/quality/cases`, `GET /api/v1/projects/:projectId/quality/cases/:caseId`
**Auth**: `X-API-KEY` or `Authorization: Bearer <token>` (required)
**Error envelope**: 4xx/5xx return `{"error": string, "message": string, "code": int, "hint"?: string}`


A **quality case** tracks a single behavior regression — a failing [experiment](/docs/api-reference/experiments.md) run, a guardrail violation, or a manually reported issue — through triage to resolution.

## Next steps

* [Experiments](/docs/api-reference/experiments.md): the runs that most often surface a new quality case
* [Datasets](/docs/api-reference/datasets.md): turn a quality case into a regression test by adding its failing item to a dataset
* [Scorers](/docs/api-reference/scorers.md): the scoring logic that flagged the underlying failure