> For the complete documentation index, see [llms.txt](https://docs.patagon.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.patagon.ai/en/agent-optimization/capabilities.md).

# How to configure agent capabilities

Capabilities are feature toggles that control how your agent handles conversations. Access them from Agent > Capabilities > Features tab.

## Available features

| Feature                 | What it does                                                                                 | Default |
| ----------------------- | -------------------------------------------------------------------------------------------- | ------- |
| Follow Up               | Automatically follows up with leads after 24 hours using an approved template                | On      |
| Message Batching        | Groups multiple short messages into one before sending, for a more natural conversation flow | On      |
| Real-Time Processing    | Processes incoming messages instantly instead of queuing them                                | On      |
| Parallel Tool Execution | Runs multiple agent tools simultaneously for faster responses                                | Off     |
| Outbound Rate Limiting  | Limits how many outbound messages the agent sends in a given period to prevent spam flags    | Off     |

## How to toggle a feature

1. Go to Agent > Capabilities and click the Features tab.
2. Click the toggle next to the feature you want to turn on or off.
3. The change takes effect immediately — no save button required.

{% hint style="warning" %}
Turning off Follow Up means leads who don't respond within 24 hours will not be contacted again automatically. Only disable this if your team handles re-engagement manually.
{% endhint %}

## Attribution tracking setup

The Attribution tab contains the technical setup for tracking where your leads come from. To connect UTM data from your landing pages to Patagon AI:

**Step 1: Add the tracking script to your landing page.** Copy and add this script to every landing page where you have a WhatsApp button:

```
<script src="https://api.patagon.ai/api/v1/tracking.js"></script>
```

This script captures UTM parameters, Google Click IDs (gclid), and Facebook Click IDs (fbclid) automatically when a lead visits your page.

**Step 2: Set the opening message.** Edit the pre-filled message leads see when they click your WhatsApp button. The default is 'Hi! I would like more information.' Customize it to match your campaign context.

**Step 3: Use the tracking link.** Copy the tracking link from the Attribution tab and use it as your WhatsApp button URL instead of a direct wa.me link. The link captures attribution data and passes it to Patagon AI automatically.

For more on reading your attribution data once it's set up, see How to read your attribution metrics.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.patagon.ai/en/agent-optimization/capabilities.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.