# Starting Your Conversation Design

1. If you don’t have a pre-set idea, determine what you want your bot to do, based on what problems you want to solve. Make a list of the use cases that your bot will handle.
2. Collaborate with a Customer specialist and create a list of all the Requests you can think of that a customer might ask your bot.
3. For requests and questions that have a definitive answer, mark them as ICM.
4. For open-ended inquiries, mark them as LLM.
5. Ask others to look over and expand your lists.
6. For the questions that you marked as ICM, add the answer or answers for each question.
7. For the questions that are open-ended, designate where you want the bot to look for answers (your tickets, your knowledge base, specific public web sites).
8. Create an Aisera Service User, Integrate your Data Source, and Create a bot.\
   \
   Now you’re ready to start building.

### Edit Your Conversation Messages

1. In the bot **Details** window, click on the [**View App Conversation Messages**](https://docs.aisera.com/aiseragpt/how-to-set-up-an-aiseragpt-bot/view-conversation-messages) link.
2. Edit the Conversations for your bot to include [**initial greeting messages**](https://docs.aisera.com/aiseragpt/how-to-set-up-an-aiseragpt-bot/view-conversation-messages#initial-conversation-messages) and the answers to each of your ICM requests, with links to more information, as needed.

### Set the Initial Logic for your Bot

1. Navigate to **Settings > AiseraGPT** and open your new bot.
2. Choose the **pencil icon** in the upper right corner of the bot **Details** window. This will take you to the bot **Configuration** parameters.
3. Select the **Advanced** configuration tab. 
4. In the **Fulfillment Engines** section, specify the ICM and Neural+ options if you plan to build a Hybrid bot with both ICM and LLM models. If you are using the AiserGPT bot, choose the fulfillment engines that your bot will use, and the order you want your bot to use them.<br>

   <div align="left"><figure><img src="https://lh7-rt.googleusercontent.com/docsz/AD_4nXfwfgaOFj1roglffudEJyaE8BdRUp-9vOCrQGaZpmnv6K8ImlKqHpzyfAEqea42i-ulwDEPN-JTSei46mwEWYYrgpHEDjBhNkzuyvH41Bfs7X41ShDBEFTVy7ul_44QIJpguV-Pvw?key=9iLPBMpGOVCiFGJixK6LSN6c" alt="" width="563"><figcaption></figcaption></figure></div>
5. Other settings that affect the conversations your bot can perform include:\
   \
   **Domain (Enterprise Domain Pack)** - Determines the type of default terminology, default conversations and ontology for your bot.\
   **Conversational AI** - Original service was built to use Intents and Fulfillments (ICM) more often.\
   **Conversational AI 2.0** - Built to mostly use Titles and Descriptions to infer Intents.<br>

   <figure><img src="https://lh7-rt.googleusercontent.com/docsz/AD_4nXcCcKrA4gxJ-7HWSDFmWjTbxG62tIWPFrdW81ZaEcHHqJD6CHx192jpUsWybZRL2sHnTVmoIM9QfCbGQqrjGdPNYbttRT5kHS3zOtkEgzR97j1uGsNGMwfvuRyj7DbLQfPKtSg4?key=9iLPBMpGOVCiFGJixK6LSN6c" alt=""><figcaption></figcaption></figure>

The **Conversational AI v2.0** setting must be selected when you are first creating your bot. It cannot be changed in the Edit window.

<figure><img src="https://lh7-rt.googleusercontent.com/docsz/AD_4nXc9m8Z7FDLeiL63UCBZMQhZV8DowaKytrDgFBAO4R7QOIdXbzpItKoS6KYxtjfOPu1LKpuDmye_RZ9JyG95wj1NL6Jf7L2c7rq3PkOuer87Pu3weK9pnYHmtsCwWoc5tDZYEzoUBA?key=9iLPBMpGOVCiFGJixK6LSN6c" alt=""><figcaption></figcaption></figure>

### Next Steps:

Your next steps include setting up your Knowledge Base Articles for RAG Indexing, and Creating Workflows.<br>


---

# 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://docs.aisera.com/aisera-platform/crafting-the-conversation/starting-your-conversation-design.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.