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

# Custom Max Iterations

## ⚙️ Advanced Configuration

Lyzr Studio allows you to fine-tune an agent's reasoning depth and operational persistence through **Advanced Settings**. This is critical for managing the balance between thoroughness and latency during complex tasks.

### **How to Configure**

1. Navigate to your agent in the **Agent Builder**.
2. Click the **three vertical dots** (menu icon) located in the top-right corner of the agent header.
3. Adjust the settings in the dropdown menu that appears:
   * **Store messages**: Toggle this **On** to maintain conversation history for context.
   * **Maximum iterations**: Use the slider to set a custom limit for the agent's inference cycle.
     <img src="https://mintlify.s3.us-west-1.amazonaws.com/lyzrinc/assets/images/studio/max.png" alt="" />

***

### **🔄 Custom Max Iterations**

The **Maximum iterations** setting (ranging up to 25) defines how many consecutive steps an agent can take to complete a single request.

An iteration is consumed whenever the agent performs the following:

* **Tool Calls**: Interacting with external integrations like Gmail, Notion, or Slack.
* **Sub-Agent Calls**: Delegating tasks to other specialized agents within a workflow.
* **Artifact/File Creation**: Generating documents, code snippets, or images.
* **Self-Correction**: If **Reflection** is enabled, each review and refinement step counts as an iteration.

> 💡 **Tip:** Set a higher iteration limit for complex research or data-heavy tasks. For simple, direct responses, a lower limit helps minimize credit consumption and response time.