---
title: "POST /human-loops"
method: POST
path: "/human-loops"
---

# POST /human-loops

`POST /human-loops`

Starts a human loop, provided that at least one activation condition is met.

## Request body

- object
  - `HumanLoopName` string, required — The name of the human loop.
  - `FlowDefinitionArn` string, required — The Amazon Resource Name (ARN) of the flow definition associated with this human loop.
  - `HumanLoopInput` object, required — An object containing the human loop input in JSON format.
    - `InputContent` string — Serialized input from the human loop. The input must be a string representation of a file in JSON format.
  - `DataAttributes` object — Attributes of the data specified by the customer. Use these to describe the data to be labeled.
    - `ContentClassifiers` ContentClassifier[] — <p>Declares that your content is free of personally identifiable information or adult content.</p> <p>Amazon SageMaker can restrict the Amazon Mechanical Turk workers who can view your task based on this information.</p>

## Response `200`

Success

- StartHumanLoopResponse
  - `HumanLoopArn` string — The Amazon Resource Name (ARN) of the human loop.

## Other responses

- `480` — ValidationException
- `481` — ThrottlingException
- `482` — ServiceQuotaExceededException
- `483` — InternalServerException
- `484` — ConflictException

---

[API](https://skmtc.net/aws/apis/sagemaker-a2i-runtime.md) · [All operations](https://skmtc.net/aws/apis/sagemaker-a2i-runtime/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/aws/sagemaker-a2i-runtime/versions/2c5b0408d20c/schema)