---
title: "Refine run with feedback"
method: POST
path: "/runs/{runId}/feedback"
tags: ["Runs"]
---

# Refine run with feedback

`POST /runs/{runId}/feedback`

## Request

- Base URL: `https://app.uselamina.ai/v1`
- URL: `https://app.uselamina.ai/v1/runs/{runId}/feedback`
- Auth: one of:
  - API key in header `x-api-key`
  - HTTP bearer

Iterative refinement: provide natural-language feedback on a completed run. An LLM identifies which workflow nodes need prompt changes, re-executes them, and returns updated outputs. Only works on completed runs.

## Path parameters

- `runId` string, uuid, required

## Request body

- object
  - `feedback` string, required: Natural-language feedback describing what to change.

## Response `200`

Refinement result with updated outputs

- object
  - `data` object
    - `runId` string, uuid
    - `status` 'completed' | 'failed'
    - `summary` string: LLM-generated description of changes
    - `refinedNodes` object[]
      - `nodeId` string
      - `reason` string
    - `outputs` Output[] (unresolved $ref)
    - `errorMessage` string, nullable

## Other responses

- `400`: Run is not in completed state
- `404`: Run not found

---

[API](https://skmtc.dev/uselamina/apis/lamina-v1-api.md) · [All operations](https://skmtc.dev/uselamina/apis/lamina-v1-api/llms.txt) · [OpenAPI document](https://skmtc.dev/uselamina/apis/lamina-v1-api/revisions/73b598526531?raw)