# 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="/files/TbcBuRm47wWBoBsZpq6t" 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="/files/TPhchnpP2LxHOmVmiYzZ" 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="/files/Whutd4JobIbQztcaRBGY" 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="/files/u9sTUJfQNQJBWLSV4nBs" 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.


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://imbrace.gitbook.io/imbrace-documentation/ai-agent/advanced-settings.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.