> 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/how-to-use-the-agents-tools-and-integrations.md).

# How to use the agent's Tools and Integrations

The **Tools / Integrations** tab in **Agent > Channels and Integrations** lets you connect your agent to external tools: CRMs, document bases, search engines, and custom APIs. Each enabled tool can be called by the agent during a conversation to perform actions or retrieve information in real time.

**How tools work**

When a tool is active, the agent can call it automatically during the conversation whenever the context requires it. For example, create a contact in the CRM when a lead is qualified, or retrieve a document from the knowledge base when the lead asks a specific question.

Tools are organized into five categories: **Active**, **Documents**, **CRM**, **Search**, and **Custom**.

***

**Active Tools**

The **Active** tab shows all the tools that are currently enabled for this agent. Use it to get a consolidated view of what's running.

***

**Document Tools**

These allow the agent to query a knowledge base during the conversation. This is ideal for answering questions about products, pricing, policies, or any content you want to make available to the agent.

| Tool                                  | What it does                                                                                               |
| ------------------------------------- | ---------------------------------------------------------------------------------------------------------- |
| Document Retrieval Tool               | Retrieves relevant documents from your knowledge base based on the lead's question                         |
| Document Retrieval and Reranking Tool | Retrieves documents and reranks them by relevance before sending them to the agent (more accurate, slower) |

**When to use simple Retrieval:** for smaller knowledge bases, where response speed is the priority.

**When to use Retrieval and Reranking:** for larger knowledge bases or when answer accuracy matters more than speed.

***

**CRM Tools**

These allow the agent to create, update, and manage records in your CRM directly during the conversation. CRM tools connect to your CRM via ApiDeck (see How to connect your CRM via ApiDeck).

<table><thead><tr><th width="270.46484375">Tool</th><th>What it does</th></tr></thead><tbody><tr><td>CRM Contact Creation Tool</td><td>Creates a new contact in the CRM when a lead is identified</td></tr><tr><td>CRM Contact Update Tool</td><td>Updates information for an existing contact in the CRM</td></tr><tr><td>CRM Contact Meeting Tool</td><td>Schedules and manages meetings with CRM contacts</td></tr><tr><td>CRM Opportunity Tool</td><td>Creates or updates sales opportunities in the CRM</td></tr><tr><td>CRM Create Lead Tool</td><td>Creates a new lead (a record distinct from contact) in the CRM</td></tr><tr><td>CRM Update Lead Tool</td><td>Updates information for existing leads in the CRM</td></tr></tbody></table>

{% hint style="warning" %}
Before enabling CRM tools, make sure your CRM is connected via ApiDeck in **Agent > Channels and Integrations > Tools / Integrations**. CRM tools enabled without an active connection will fail silently.
{% endhint %}

***

**Search Tools**

These allow the agent to query data in external search engines.

<table><thead><tr><th width="359.2890625">Tool</th><th>What it does</th></tr></thead><tbody><tr><td>Meilisearch Tool</td><td>Searches and retrieves data using Meilisearch</td></tr><tr><td>Elasticsearch SQL Tool</td><td>Queries data using Elasticsearch SQL</td></tr></tbody></table>

These tools are recommended for teams that maintain product catalogs, inventories, or structured databases in Meilisearch or Elasticsearch and want the agent to query that data in real time during the conversation.

***

**Custom Tools**

These allow your agent to connect to any external API or AI workflow.

<table><thead><tr><th width="255.95703125">Tool</th><th>What it does</th></tr></thead><tbody><tr><td>HTTP Request Tool</td><td>Makes custom HTTP requests to external APIs (GET, POST, PUT, DELETE)</td></tr><tr><td>OpenAI Agent Builder Tool</td><td>Builds and integrates conversational AI workflows using the OpenAI Agent Builder</td></tr></tbody></table>

The **HTTP Request Tool** is the most versatile: use it to connect the agent to any API that doesn't have a native tool on the platform. Examples include scheduling systems, ERPs, e-commerce platforms, and internal webhooks.

**How to enable a tool**

1. Go to **Agent > Channels and Integrations** and click the **Tools / Integrations** tab.
2. Click the desired category (Documents, CRM, Search, or Custom).
3. Click the card of the tool you want to enable.
4. Configure the required parameters (credentials, endpoints, etc.) as prompted.
5. Save the configuration. The tool will automatically appear in the **Active** tab.


---

# 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/how-to-use-the-agents-tools-and-integrations.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.