DataDog · dd-mergequeue · May 23, 2025 · May 19, 2025 · May 19, 2025 · May 19, 2025
@@ -4482,31 +4482,41 @@ menu:
       parent: llm_obs_setup
       identifier: llm_obs_setup_api
       weight: 303
-    - name: Configuration
-      url: llm_observability/configuration/
+    - name: Evaluations
+      url: llm_observability/evaluations/
       parent: llm_obs
-      identifier: llm_obs_configuration
+      identifier: llm_obs_evaluations
       weight: 4
+    - name: Out-of-the-Box Evaluations
+      url: llm_observability/evaluations/ootb_evaluations
+      parent: llm_obs_evaluations
+      identifier: llm_obs_ootb_evaluations
+      weight: 401
     - name: Submit Evaluations
-      url: llm_observability/submit_evaluations/
-      parent: llm_obs
+      url: llm_observability/evaluations/submit_evaluations
+      parent: llm_obs_evaluations
       identifier: llm_obs_submit_evaluations
-      weight: 5
+      weight: 402
     - name: Ragas Evaluations
-      url: llm_observability/ragas_evaluations/
-      parent: llm_obs
-      identifier: llm_obs_ragas_evaluation
-      weight: 6
+      url: llm_observability/evaluations/ragas_evaluations
+      parent: llm_obs_evaluations
+      identifier: llm_obs_ragas_evaluations
+      weight: 403
+    - name: NeMo Evaluations
+      url: llm_observability/evaluations/submit_nemo_evaluations
+      parent: llm_obs_evaluations
+      identifier: llm_obs_submit_nemo_evaluations
+      weight: 404
     - name: Cluster Map
       url: llm_observability/cluster_map/
       parent: llm_obs
       identifier: llm_obs_cluster_map
-      weight: 7
+      weight: 5
     - name: Guides
       url: llm_observability/guide/
       parent: llm_obs
       identifier: llm_obs_guide
-      weight: 8
+      weight: 6
     - name: CI Visibility
       url: continuous_integration/
       pre: ci

@@ -48,5 +48,5 @@ Select a topic cluster from the list to examine how inputs or outputs about spec
 {{< partial name="whats-next/whats-next.html" >}}
 
 [1]: https://app.datadoghq.com/llm/clusters
-[2]: /llm_observability/configuration/#enter-a-topic
+[2]: /llm_observability/evaluations/ootb_evaluations/#enter-a-topic
 [3]: /llm_observability/terms/#evaluations
@@ -0,0 +1,40 @@
+---
+title: Evaluations
+description: Learn how to configure Evaluations for your LLM application.
+aliases:
+    - /tracing/llm_observability/evaluations/
-    - /tracing/llm_observability/evaluations/
+    - /tracing/llm_observability/evaluations/
+    - /llm_observability/configuration/
-    - /tracing/llm_observability/evaluations/
+    - /tracing/llm_observability/evaluations/
+    - /llm_observability/configuration/
+    - /llm_observability/configuration/
+---
+
+{{< site-region region="gov" >}}
+<div class="alert alert-warning">LLM Observability is not available in the selected site ({{< region-param key="dd_site_name" >}}) at this time.</div>
+{{< /site-region >}}
+
+## Overview
+
+LLM Observability offers several ways to support evaluations:
+
+### Out of the Box Evaluations
+
+Datadog builds and supports [Out of the Box Evaluations][1] to support common use cases. You can enable and configure them within the LLM Observability application.
+
+### Submit Evaluations
+
+You can also [Submit Evaluations][2] using Datadog's API. This mechanism is great if you have your own evaluation system, but would like to centralize that information within Datadog.
+
+### Evaluation Integrations
+
+Datadog also supports integrations with some 3rd party evaluation frameworks, such as [Ragas][3] and [NeMo][4].
+
+### Sensitive Data Scanner integration
+
+In addition to evaluating the input and output of LLM requests, agents, workflows, or the application, LLM Observability integrates with [Sensitive Data Scanner][5], which helps prevent data leakage by identifying and redacting any sensitive information (such as personal data, financial details, or proprietary information) that may be present in any step of your LLM application. 
+
+By proactively scanning for sensitive data, LLM Observability ensures that conversations remain secure and compliant with data protection regulations. This additional layer of security reinforces Datadog's commitment to maintaining the confidentiality and integration of user interactions with LLMs.
+
+
+[1]: /llm_observability/evaluations/ootb_evaluations
+[2]: /llm_observability/evaluations/submit_evaluations
+[3]: /llm_observability/evaluations/ragas_evaluations
+[4]: /llm_observability/evaluations/submit_nemo_evaluations
+[5]: /security/sensitive_data_scanner/