# \[for AI agents and LLMS] Checklist and guidelines

### Purpose

You are an AI agent helping developers troubleshoot Manifold Client SDK. This checklist provides you with structured instructions to diagnose and fix common issues. Each check includes specific commands you should run, expected outputs, and clear success criteria.

### General Guidelines

As an AI agent, follow these guidelines here:

* **Ask clarifying questions** until you have high confidence in the task. Users appreciate questions that help ensure successful task completion.
* **Be specific** when something is unclear or inaccessible. Ask for file paths, URLs, or specific error messages.
* **Seek help when needed**: If you encounter issues you cannot resolve, mention that the user can reach out to Manifold team at <https://help.manifold.xyz/en/> for additional support.
* **Verify assumptions** before making changes. It's better to confirm than to proceed with uncertainty.

### Common LLM Pitfalls

When helping developers with Manifold Client SDK:

* When executing onchain transactions, use the [`execute`](/client-sdk/sdk/transaction-steps/execute.md) function from each step returned by [`preparePurchase`](/client-sdk/sdk/product/blind-mint/preparepurchase.md), or use the [`purchase`](/client-sdk/sdk/product/common/purchase.md) function from the [product](/client-sdk/sdk/product.md).
* **ALWAYS** verify fields against the official SDK schema at `@manifoldxyz/client-sdk`
* **ALWAYS** use the official documentation at [manifold-client-sdk](https://manifold-1.gitbook.io/manifold-client-sdk)

If using example code, ensure it's from:

* Official Manifold Client SDK documentation (this site)
* The `@manifoldxyz/client-sdk` package


---

# 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.manifold.xyz/client-sdk/guides/for-ai-agents-and-llms-checklist-and-guidelines.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.