# Advanced Settings

The advanced settings section of the agent configuration interface provides users with additional control and customization options to fine-tune the behavior, security, and integrations of the agent.

## **Advanced settings include:**

<figure><img src="https://2455207419-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FnZwCwAN15BUJcXMA5avi%2Fuploads%2Fz4qdKeyQSlOj58pWPosW%2Fimage.png?alt=media&#x26;token=8fb59041-0015-496c-adbf-57ab929b7143" alt=""><figcaption></figcaption></figure>

### **Usage:**

* *Description:* This setting allows the user to specify the **Max Messages** and **LLM Temperature** for the agent. **Max Messages** refers to the number of messages the agent will refer back to in the chat to create a response.
* *Usage:* Enter the values that are appropriate for the agent you are creating. To learn more about **LLM Temperature** click [here](https://deepchecks.com/glossary/llm-parameters/).

  <figure><img src="https://2455207419-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FnZwCwAN15BUJcXMA5avi%2Fuploads%2FByRMUy49Fqzkwc2jHnlF%2Fimage.png?alt=media&#x26;token=7497fba3-4c31-47c5-8cc3-d7bd13d3bba2" alt=""><figcaption></figcaption></figure>

### **Scanners:**

* *Description:* This field allows the user to specify which unique scanners the agent will use.
* *Usage:* Enable the AI Scanners appropriate for the agent you are creating. The seven proprietary scanners are: [Toxicity](https://docs.aicrisk.com/admin/agent-scanner-defaults/toxicity), [Personal Information](https://docs.aicrisk.com/admin/agent-scanner-defaults/personal-information), [Topic](https://docs.aicrisk.com/admin/agent-scanner-defaults/topic-scanner),[ Prompt Injection Detection](https://docs.aicrisk.com/admin/agent-scanner-defaults/prompt-injection-detection), [Regex](https://docs.aicrisk.com/admin/agent-scanner-defaults/regex-scanner), [Geographic Gating](https://docs.aicrisk.com/admin/agent-scanner-defaults/geographic-gating), and [Language Detection](https://docs.aicrisk.com/admin/agent-scanner-defaults/language-detection).

  <figure><img src="https://2455207419-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FnZwCwAN15BUJcXMA5avi%2Fuploads%2FkdJJLHmZAX9GucoPbS3t%2Fimage.png?alt=media&#x26;token=dc709649-4873-4f3e-b64a-ed8d80f0d4ab" alt=""><figcaption></figcaption></figure>

### **API Keys:**

* *Description:* This field allows the user to view the company's AIR Key and external agent engine key.
* *Usage:* Enter an updated external agent engine key if the present one is outdated.

  <figure><img src="https://2455207419-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FnZwCwAN15BUJcXMA5avi%2Fuploads%2F2K5KDRS9q8zYtfGOHIBS%2Fimage.png?alt=media&#x26;token=b513f802-4ef0-497d-81b3-2f77a6c3131a" alt=""><figcaption></figcaption></figure>

### **Files:**

* *Description:* This field allows the user to specify which file types are allowed to be uploaded to the agent. This setting will only become visible if File Uploads are enabled.&#x20;
* *Usage:* To enable File Uploads, make sure you select an agent engine and model that supports this feature. You must also enable the ***Is Assistant*** and ***Code Interpreter*** options to tell the agent it can analyze the attached data. The screenshot below shows the OpenAI agent engine selected utilizing its`gpt-4`model:

  <figure><img src="https://2455207419-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FnZwCwAN15BUJcXMA5avi%2Fuploads%2FFa9SzKxReAhIIfLLKJLo%2Fimage.png?alt=media&#x26;token=71617d88-f9d7-467f-87ec-8aec848a0089" alt=""><figcaption></figcaption></figure>

  <figure><img src="https://2455207419-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FnZwCwAN15BUJcXMA5avi%2Fuploads%2FV4xw2P0Oxw5uvBcFgEdn%2Fimage.png?alt=media&#x26;token=e7b9cd51-c737-4785-ab62-cb1bda665d7c" alt=""><figcaption></figcaption></figure>