---
title: System tools for Content Recommendations
slug: agent-platform/docs/system-tools-for-content-recommendations
docTags: 
createdAt: 2026-08-12T15:37:10.000Z
---

Agent Platform includes system tools that Optimizely provides and maintains. System tools are built-in features that help Mark take action. Each tool performs a specific task, such as creating a campaign, uploading files, or generating images. Think of tools like attachments on a Swiss Army knife. Each one has a distinct purpose that helps you get work done.

In addition to the [system tools available in Mark](docId\:ZExsvHuX-MENKqR8_eAvw), Optimizely Content Recommendations includes a set of system tools designed to help you find high-performing content items and topics and analyze recommendation widget performances.

:::hint{type="info"}
**Note**

Ask Mark what tools it has at any time. For example, enter "*Please list the tools you have with a brief description of what they do and the parameters*" into [Mark chat](../../use-opal/opal-chat/access-and-explore-opal-chat.mdx).
:::

Click a tool's name to expand it and learn when to use it, its required and optional parameters, and example prompts for calling the tool. If you do not provide a required parameter, Mark prompts you for it.

To enable the Content Recommendations tools, go to **Connections > Content Recommendations** and select one or more product instances. When you enter a prompt in **Chat**, select the instance from the **Set Product Instance** drop-down list to get data for that instance. You can access data for the past 30 days.

:::ExpandableHeading
### `contentrecs_top_content`– Retrieves the highest-performing content items ranked by user interactions within a specified date range. Helps identify which articles, posts, or content pieces resonate most with your audience

- **When to use**
  - Understand which content drives the most engagement.
  - Identify successful content patterns and formats.
  - Discover content worthy of promotion or repurposing.
  - Measure content engagement rates.
- **Parameters**
  - `from_date` – Start date in ISO 8601 (YYYY-MM-DD) format.
  - `to_date` – End date in ISO 8601 (YYYY-MM-DD) format.
  - `limit` – (Optional) Maximum number of results (10 – 1000, default: 200).
- **Example prompts**
  - *Show me the top-performing articles from last week.*
  - *Could you please provide me with the top 5 articles for each month in 2025?*
:::

:::ExpandableHeading
### `contentrecs_top_topics` – Retrieves performance metrics for the most engaging topics based on user interactions. Identifies trending topics and reveals which topics resonate most with your audience.

- **When to use**
  - Discover high-performing topics for content creation.
  - Identify content gaps where popular topics are underrepresented or lack coverage.
  - Find underperforming topics that need improved content quality.
  - Guide content strategy decisions.
- **Parameters**
  - `from_date` – Start date in ISO 8601 (YYYY-MM-DD) format.
  - `to_date` – End date in ISO 8601 (YYYY-MM-DD) format.
  - `limit` – (Optional) Maximum number of results (10 – 1000, default: 200).
- **Example prompts**
  - *What are the trending topics my audience engaged with in the last 30 days?*
  - *Based on the previous month's data, what should we focus on writing next?*
:::

:::ExpandableHeading
### `contentrecs_top_recommendation_widgets` – Analyzes recommendation widget performance with detailed A/B testing metrics comparing personalized and unpersonalized recommendations.

- **When to use**
  - Evaluate ROI of recommendation strategies.
  - Identify the widgets that benefit most from personalization.
  - Optimize widget placement and configuration.
  - Measure the lift from personalization investment.
  - Make data-driven decisions on enhancing recommendation algorithms.
- **Parameters**
  - `from_date` – Start date in ISO 8601 (YYYY-MM-DD) format.
  - `to_date` – End date in ISO 8601 (YYYY-MM-DD) format.
- **Example prompts**
  - *How did our recommendation widgets perform last month?*
:::

:::hint{type="info"}
**Note**

If you use Opti ID, administrators can turn off generative AI in the Opti ID Admin Center. See [Turn generative AI off across Optimizely applications](docId\:X5U0kKD2azV5cIdNqwGNj).
:::