# Customize Inputs

In this section, you have the power to tailor your chatbot's responses to a variety of user inputs, ensuring a conversational experience that aligns with your project's unique needs.

Explore the different directive types that can be customized to enhance your chatbot's conversational versatility:

**YES**

Customize how the chatbot recognizes affirmative responses, including variations like "Roger that" and "Affirmative."

**NO**

Define how the chatbot understands negative responses, encompassing expressions like "Negative" and "Not really."

**DONT\_KNOW**

Tailor the chatbot's response to user expressions of uncertainty, such as "Don't have a clue" and "No idea."

**EOC (End of Conversation)**

Customize how the chatbot acknowledges the user's desire to end the conversation, offering responses like "Terminate this conversation" and "Exit."

**APPRECIATION**

Craft responses that reflect the chatbot's appreciation of user satisfaction, with expressions like "Appreciate the help" and "Thanks for the service."

**CONFIRM\_CLOSURE**

Tailor the chatbot's confirmation responses when a user requests to close the chat, providing variations like "Exit the chat" and "Please close."

**ESCALATE**

Define how the chatbot responds when a user expresses a desire to speak with an associate, with phrases like "Talk with the associate" and "Connect me with support."

**CANCEL\_PROCESS**

Customise the chatbot's response when a user wants to halt the execution of a specific intent, offering options like "Cancel this process" and "Stop the flow."

By customizing inputs, you empower your chatbot to interpret and respond to a diverse range of user expressions, creating a tailored and responsive conversational 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://readme.dhee.ai/platform-reference/entities-and-other-data/directive-utterances/customize-inputs.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.