diff --git a/content/en/llm_observability/monitoring/patterns.md b/content/en/llm_observability/monitoring/patterns.md
index 84428c9c57f..fa2a6cd3159 100644
--- a/content/en/llm_observability/monitoring/patterns.md
+++ b/content/en/llm_observability/monitoring/patterns.md
@@ -55,7 +55,13 @@ Each topic shows its interaction volume and share of total traffic. Interactions
    - **Which spans do you want to cluster?:** Filter by application, environment, span type, or other tags to scope the Pattern to a specific slice of traffic.
    - **Sampling Rate:** The percentage of matching interactions to include. Patterns processes up to 10,000 records per run; if your filter matches more than that, records are randomly sampled down to the cap.
 5. Under **What should we detect Patterns on?**, enter a template that defines what gets sent to the model for analysis. Use {{variable}} syntax to reference any span field — for example, {{meta.input.value}} to analyze patterns by user input, or {{meta.span.kind}} to analyze by span kind. Click {{< ui >}}Template Examples{{< /ui >}} to see common configurations. As you type, the right panel previews matching spans and shows what percentage of interactions have values for the variables you've referenced.
-6. Click **Save**
+6. Under **How often should we run Patterns?**, choose how the Pattern runs:
+   - **On demand** (default): Run the Pattern manually.
+   - **Daily**, **Weekdays**, or **Weekly**: Run automatically at a time (and, for weekly, a day) you choose.
+   - **Custom**: Run automatically every 1 to 7 days.
+
+   Scheduled times use your Datadog timezone preference. Scheduled runs use the same pipeline as a manual run, so results appear in the same place, and the Patterns page always shows your most recent run.
+7. Click **Save**
 
 ## Explore your Patterns