---
title: Managed Evaluators
description: Learn how to configure managed evaluators for your LLM applications.
breadcrumbs: Docs > Agent Observability > Investigate > Evaluations > Managed Evaluators
---

> For the complete documentation index, see [llms.txt](https://docs.datadoghq.com/llms.txt).

# Managed Evaluators

{% callout %}
# Important note for users on the following Datadog sites: app.ddog-gov.com, us2.ddog-gov.com

{% alert level="danger" %}
This product is not supported for your selected [Datadog site](https://docs.datadoghq.com/getting_started/site.md). ({% placeholder "user-datadog-site-name" /%}).
{% /alert %}

{% /callout %}

## Overview{% #overview %}

Managed evaluators are built-in tools to assess your LLM application. Agent Observability associates evaluations with individual spans so you can view the inputs and outputs that led to a specific evaluation.

Learn more about the [compatibility requirements](https://docs.datadoghq.com/llm_observability/investigate/evaluations/compatibility.md).

## Create new evaluators{% #create-new-evaluations %}

1. Navigate to [AI Observability > Evaluators](https://app.datadoghq.com/llm/evaluations).
1. Click on the Create Evaluator button on the top right corner.
1. Select a specific managed evaluator. This will open the evaluator editor window.

After you click Save and Publish, the evaluator goes live. Alternatively, you can Save as Draft and edit or enable it later.

## Edit existing evaluators{% #edit-existing-evaluations %}

1. Navigate to [AI Observability > Evaluators](https://app.datadoghq.com/llm/evaluations).
1. Hover over the evaluator you want to edit and click the Edit button.

### Supported managed evaluators{% #supported-managed-evaluators %}

- [Language Mismatch](https://docs.datadoghq.com/llm_observability/investigate/evaluations/language_mismatch.md) - Flags responses that are written in a different language than the user's input
- [Sensitive Data Scanning](https://docs.datadoghq.com/llm_observability/investigate/evaluations/managed_evaluations/security_and_safety_evaluations.md) - Flags the presence of sensitive or regulated information in model inputs or outputs

## Further Reading{% #further-reading %}

Additional helpful documentation, links, and articles:

- [Gain visibility into Strands Agents workflows with Datadog LLM Observability](https://www.datadoghq.com/blog/llm-aws-strands)
- [Learn about Agent Observability terms and concepts](https://docs.datadoghq.com/llm_observability/quickstart/terms.md)
- [Learn how to set up Agent Observability](https://docs.datadoghq.com/llm_observability/setup.md)