# Build using AI

*Accelchain's innovative AI-driven approach to smart contract development streamlines the coding process, providing a rapid and user-friendly experience.*

#### User-Prompt Interaction

Accelchain's AI initiates a two-step process, starting with a user prompt to comprehend the smart contracts intended use case. 

<figure><img src="/files/0VdWuP5v1LJOqIubC24p" alt=""><figcaption></figcaption></figure>

> *The accuracy and relevance of the AI-generated list and descriptions depend heavily on the quality of the user's prompt. Providing a well-defined prompt enhances the AI's ability to deliver precise and tailored results.*

#### Functions List and Descriptions

After processing the prompt, the AI generates a list of functions with detailed descriptions tailored to the user's use case. Users then select the specific functions they require for their contract from the list.

<figure><img src="/files/9ngFWjDFIq9cmkP95lDC" alt=""><figcaption></figcaption></figure>

#### Complete Contract Generation

Based on the selected functions, Accelchain's AI dynamically generates a complete smart contract. Users are seamlessly directed to the contract edit page within the integrated development environment (IDE), where the generated contract is ready for further customisation.

<figure><img src="/files/0RhVQdUXdsU9XL5bNCF6" alt=""><figcaption></figcaption></figure>

***

{% hint style="info" %}
*Accelchain's AI, while proficient in generating functions and contracts, is not currently configured for automatic contract imports. If imports are necessary, users can customize the contract in the IDE and upload imported contracts into the project structure.*
{% endhint %}


---

# 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://accelchain.gitbook.io/docs/design/build-using-ai.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.