# Evaluating a Coworker

Evaluations let you grade a Coworker’s answers against expected results using a labelled dataset. Because a Coworker runs as an agentic flow, you evaluate it with an **In-House DeepEval** evaluation whose inference source is the agent itself.

1. In the sidebar, open **Evaluations**, then the **In-House** tab. (If you do not see it, ask your administrator.)
2. Click **+** and choose **DeepEval**.
3. **Basic Information** — enter a Name (lowercase letters, numbers, and hyphens; up to 50 characters) and optional Tags.
4. **Metrics** — tick one or more; at least one is required.
5. **Inference Source** — choose **Agentic Flow Agent**.
6. **Select Agent** — pick your Coworker. Items marked *(Draft only)* have no published version; toggle **Use Draft Version** to test the unpublished draft.
7. **Evaluation Model** — choose the judge model (Model Category, then Model Type) that grades the answers.
8. **Dataset** — select a dataset with an `input` column and an `expected_output` column (the ground truth). If you have none, create one first.
9. Click **Save**, open the evaluation, go to the **Runs** tab, and click **Run Evaluation**. Use **Refresh** to update the status.
10. Open the completed run to review the **Overall Metrics** card and the per-row table — Input, Expected Output, and each metric’s result with an explanation. Use **Download** to export the results.

> **Note**
>
> Evaluations, the full metric catalogue, and datasets are documented under [Foundry → Evaluations](../12_foundry/evaluations/index.html) and [Foundry → Datasets](../12_foundry/datasets/index.html). This page covers only the Coworker-specific path — an In-House DeepEval evaluation with the **Agentic Flow Agent** inference source pointed at your Coworker. To grade a model directly rather than an agent, use the Bedrock evaluation family instead.

> **Tip**
>
> To build an evaluation dataset from real traffic, open a trace on the [Traces tab](observability.html) and use **Add to Dataset**.