> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://humanloop.com/docs/v4/guides/evaluation/evaluating-with-human-feedback/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://humanloop.com/_mcp/server.

> Learn how to set up a human evaluator to collect feedback on the output of your model.

### Prerequisites

* You need to have access to evaluations.
* You also need to have a Prompt – if not, please follow our [Prompt creation](/docs/v4/guides/create-prompt) guide.
* Finally, you need at least a few logs in your project. Use the **Editor** to generate some logs if you don't have any yet.

### Set up an evaluator to collect human feedback

### Create a 'Human' Evaluator

From the Evaluations page, click **New Evaluator** and select **Human**.

![](/docs/_fern-img/e9dc9654e29f4d618690694da2df73760e816095b769f81b3f3834ee54c8f812.webp)

### Give the evaluator a name and description and click **Create** in the top-right.

### Return to the **Evaluations** page and select **Run Evaluation**.

### Choose the model config you are evaluating, a dataset you would like to evaluate against and then select the new Human evaluator.

![](/docs/_fern-img/545e97ced5e334cf8612e02f687ad386d32cddf0ee09c815668eef38f66294a7.webp)

### Click **Batch generate** and follow the link in the bottom-right corner to see the evaluation run.

![](/docs/_fern-img/b345eb0b35573e3ba5e5949ec672427a9972f4821abceea7674285c72c4df199.webp)

### View the details

As the rows populate with the generated output from the model, you can review those outputs and apply feedback in the rating column. Click a row to see the full details of the Log in a drawer.

### Apply your feedback either directly in the table, or from the drawer.

![](/docs/_fern-img/ee4ec8d3a8c5efccf9fe17b55a2b91b757cfc7342b73e1043ba002e02e181a6a.webp)

### Once you've finished providing feedback for all the Logs in the run, click **Mark as complete** in the top right of the page.

### You can review the aggregated feedback results in the **Stats** section on this page.

## Configuring the feedback schema

If you need a more complex feedback schema, visit the **Settings** page in your project and follow the link to **Feedbacks**. Here, you can add more categories to the default feedback types. If you need more control over feedback types, you can [create new ones via the API](/docs/v4/api/projects/create-feedback-type).

> This guide demonstrates how to run a batch generation and collect manual human feedback.