> For the complete documentation index, see [llms.txt](https://docs.aicrisk.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.aicrisk.com/admin/ai-agents/adding-a-new-agent/advanced-settings.md).

# 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="/files/JdSwGGC1Xup7JtrXrWI6" 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="/files/he7XzQGLs7vQr0l4Dm0N" 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](/admin/agent-scanner-defaults/toxicity.md), [Personal Information](/admin/agent-scanner-defaults/personal-information.md), [Topic](/admin/agent-scanner-defaults/topic-scanner.md),[ Prompt Injection Detection](/admin/agent-scanner-defaults/prompt-injection-detection.md), [Regex](/admin/agent-scanner-defaults/regex-scanner.md), [Geographic Gating](/admin/agent-scanner-defaults/geographic-gating.md), and [Language Detection](/admin/agent-scanner-defaults/language-detection.md).

  <figure><img src="/files/ySNBaDsf7gNsvcv5qrkJ" 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* *Usage:* Enter an updated external agent engine key if the present one is outdated.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="/files/pyElUEiAxSA4FOEmmwHg" 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="/files/u8lYobeZRsUMwP4c3Iny" alt=""><figcaption></figcaption></figure>

  <figure><img src="/files/IQ2cydrmzYLwwBcR1e2G" alt=""><figcaption></figcaption></figure>