> For the complete documentation index, see [llms.txt](https://docs.avonnicomponents.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.avonnicomponents.com/dynamic-components/component-builder/interactions/open-agentforce-panel.md).

# Open Agentforce Panel

The Open Agentforce Panel interaction opens an Agentforce side panel in the Salesforce desktop interface so users can work with an agent without leaving the page.

## Overview

The Open Agentforce Panel interaction opens an Agentforce side panel within the Salesforce Lightning desktop interface. Use it to give users one-click access to an AI agent right next to the record or data they are working on — without leaving the page.

Unlike the [**Invoke Agentforce Agent**](/dynamic-components/component-builder/interactions/invoke-agentforce-agent.md) interaction, which sends a message to an agent behind the scenes and captures the response, Open Agentforce Panel surfaces the conversational panel itself so the user can chat with the agent directly.

***

## Configuration

* Add an On Click interaction to the triggering component (e.g., an "Ask the Agent" button).
* Action Type: Select `Open Agentforce Panel`.
* **Agentforce Panel ID**: The ID of the Agentforce panel to open. This is the agent's bot ID.

{% hint style="info" %}

#### Finding the Bot ID

Retrieve the botId for your agent by checking the URL within the Agent Builder in Salesforce Setup.
{% endhint %}

If you don't provide a bot ID, the panel opens using the last used agent.

***

## Important Considerations

* **Desktop only**: The interaction opens the panel within the Salesforce Lightning desktop interface.
* **The agent must already exist**: This interaction opens a panel for an existing agent — build and activate your agent in Agentforce Studio first.
* **Last-used fallback**: Leaving the Agentforce Panel ID empty is a valid configuration — the panel simply reopens with whichever agent the user interacted with last.


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.avonnicomponents.com/dynamic-components/component-builder/interactions/open-agentforce-panel.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.