> For the complete documentation index, see [llms.txt](https://help.botpenguin.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.botpenguin.com/bots/sms-bot/ai-settings/ai-settings-legacy.md).

# AI Settings (Legacy)

{% hint style="warning" icon="triangle-exclamation" %}
**Legacy Feature Notice:** This page applies to older BotPenguin accounts using the **AI Response** component inside Chat Flows. If your account was created recently, you are using the newer **AI Settings** experience instead. [View the current AI Settings documentation](/bots/website-mobile-app-bot/chatbot-settings/ai-settings.md)
{% endhint %}

The AI Response Setting gives you control over how your chatbot handles AI-powered responses within your Chat Flow. This includes configuring the chatbot's persona, setting up your GPT credentials, defining response scenarios, and managing AI chat summaries.

Use the pages in this section to configure each part of your AI response setup:

* **Basic Configuration** — Set up the foundational AI response behaviour for your bot
* **Configuring Chatbot Scenarios** — Define how the bot responds to different conversation scenarios
* **Chatbot Persona** — Customise the personality and tone of your AI-powered bot
* **AI Chat Summary** — Configure how the bot summarises conversations
* **How to get the GPT Assistant key and connect it with the bot** — Step-by-step guide to generating and connecting your OpenAI API key

{% hint style="info" %}
If you are unsure which version you are on, check your Chat Flow. If you see an **AI Agent** component, refer to the [AI Settings](https://claude.ai/chat/be7c1a8a-b08d-46cf-9b0b-0cb87d243a8a#) documentation. If you see an **AI Response** component, you are in the right place.
{% endhint %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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://help.botpenguin.com/bots/sms-bot/ai-settings/ai-settings-legacy.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.