> For the complete documentation index, see [llms.txt](https://imbrace.gitbook.io/imbrace-documentation/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://imbrace.gitbook.io/imbrace-documentation/ai-agent/advanced-settings.md).

# Advanced Settings

The Advanced Settings tab gives you deeper control over your AI agent’s response quality, memory, and delivery style. These settings fine-tune how the agent behaves in conversation and how dynamic or consistent its responses should be.

<figure><img src="https://3400071099-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FypCKq44Psaly6khgrY7x%2Fuploads%2FwP38wknBFDyBDIVaWZWX%2Fimage.png?alt=media&amp;token=2226a2bf-4fda-4c57-ace8-7d2c435e5c59" alt=""><figcaption></figcaption></figure>

1\. Temperature

The Temperature setting controls how creative or precise your AI’s responses will be.

* Lower temperature (0.1–0.3) → More focused and predictable answers.
* Medium temperature (0.4–0.6) → Balanced mix of creativity and accuracy.
* High temperature (0.7–1.0) → More imaginative and varied responses.

Tip:\
For business or customer service agents, keep the temperature low (0.1–0.3) to maintain reliability. For creative or brainstorming agents, increase it (0.6–0.8) for more flexible outputs.

<figure><img src="https://3400071099-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FypCKq44Psaly6khgrY7x%2Fuploads%2FQxSF14a3IoYoNmlbuZ94%2FPicture3.png?alt=media&amp;token=d4d91ba3-da6c-4a3f-b28a-fab443b95dc5" alt=""><figcaption></figcaption></figure>

2\. Chat History Memory

When enabled, this feature allows your AI agent to remember details within an ongoing conversation. It helps maintain context, continuity, and coherence across multiple interactions.

* Enabled: The AI recalls previous user inputs in the same chat.
* Disabled: The AI treats each message as an independent query.

<figure><img src="https://3400071099-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FypCKq44Psaly6khgrY7x%2Fuploads%2FEOBCfTI7t7DdEoyaxuhp%2FScreenshot%202025-11-19%20170740.png?alt=media&amp;token=c7ed4fbd-76a3-4243-b503-113aefb91452" alt=""><figcaption></figcaption></figure>

Keep this feature enabled for customer engagement or lead management bots, where context matters.

3\. Enable Streaming

Controls how the AI’s responses are displayed to users.

* Enabled: The reply appears word-by-word, mimicking a live chat typing experience.
* Disabled: The reply appears all at once after processing.

<figure><img src="https://3400071099-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FypCKq44Psaly6khgrY7x%2Fuploads%2FBinid6JbU3j7rkxGjg4c%2FScreenshot%202025-11-19%20170942.png?alt=media&amp;token=4591057e-f62a-4545-867e-749fba361c1e" alt=""><figcaption></figcaption></figure>

Enable this feature if your AI agent is integrated into chat-based platforms such as WhatsApp, Web Widget, or Facebook Messenger for a more interactive and real-time experience.