> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gidr.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# ReAct Node

> Advanced reasoning engine that can combine thought processes with tool execution.

The **ReAct Node** (Reasoning + Acting) is a powerful agentic component that allows the AI to "think" (reason about a problem) and "act" (use tools) iteratively to solve complex tasks.

## Typical Usage

The ReAct node is the core of agentic workflows, enabling the AI to autonomously determine which tools to use to achieve a goal.

### Example Configuration

<img src="https://mintcdn.com/gidrai/La57oM6sCecLAz60/images/ai-studio/react-clean-workflow.png?fit=max&auto=format&n=La57oM6sCecLAz60&q=85&s=6602eba4de089a149b269044db4eeee6" alt="ReAct Node Clean Workflow" width="2770" height="1844" data-path="images/ai-studio/react-clean-workflow.png" />

1. **Connection**: The node sits between a 'Start' triggering event and an 'End' output.
2. **Tool Access**: Crucially, this node can be configured with access to various tools (Search, Database, API, etc.) which it can call during its execution loop.

## Configuration Details

<img src="https://mintcdn.com/gidrai/La57oM6sCecLAz60/images/ai-studio/react-config-top.png?fit=max&auto=format&n=La57oM6sCecLAz60&q=85&s=2a7b440288e8a4c2992f36800f585aed" alt="ReAct Config Top Section" style={{ width: '300px' }} width="2770" height="1844" data-path="images/ai-studio/react-config-top.png" />

### Core Settings

* **Title**: A descriptive name for the node (e.g., "Customer Service Agent").
* **Description**: Documentation of the node's purpose.
* **Prompt**: The system instruction that guides the agent's behavior and personality (e.g., "You are a helpful assistant...").

***

<img src="https://mintcdn.com/gidrai/La57oM6sCecLAz60/images/ai-studio/react-config-middle.png?fit=max&auto=format&n=La57oM6sCecLAz60&q=85&s=14b6bcf1865e3a486fe777435004ea75" alt="ReAct Config Middle Section" style={{ width: '300px' }} width="2770" height="1844" data-path="images/ai-studio/react-config-middle.png" />

### Model & Reasoning

* **LLM**: The language model driving the reasoning (e.g., GIDR LLM 2).
* **Reasoning level**: The depth of thought process to apply.
* **Max iterations**: (If applicable to your version) Controls the maximum number of thought-action loops the agent can perform.

***

<img src="https://mintcdn.com/gidrai/La57oM6sCecLAz60/images/ai-studio/react-config-bottom.png?fit=max&auto=format&n=La57oM6sCecLAz60&q=85&s=70a37ae0335de255a531fa2dc1d76b43" alt="ReAct Config Bottom Section" style={{ width: '300px' }} width="2770" height="1844" data-path="images/ai-studio/react-config-bottom.png" />

### Tools & Advanced Options

* **No. of previous exchanges**: Context window measurement.

* **Tools**: A toggle or selector to enable specific tools this agent can use (e.g., Web Search, Calculator).

* **MCP Servers**: Connect to Model Context Protocol servers to extend capabilities.

* Users must configure MCP Servers by providing:
  * **Server URL**
  * **Auth Header**
  * **Auth Value**

* MCP Servers can be configured as:
  * **Internal (GIDR) MCP Server**
    * **Auth Header** must be `x-api-key`
    * **Auth Value** must be the **GIDR API Key**
  * **External MCP Server**
    * **Auth Header** and **Auth Value** are Optional and should be provided according to the external server’s authentication requirements.

* **Variable Selectors**:
  * **Input**: Bind data variables to the agent's context.
  * **Prompt**: Inject dynamic values into the system prompt.