# How do I process vendor credits with Invoice AI?

When a vendor sends a credit memo, Invoice AI will scan the document and initially load the extracted data onto the standard Vendor Bill form — the same way it handles regular invoices. You won’t need to re-enter any of the information manually. Instead, a single action converts the bill into a vendor credit.

### Steps

1\.   **Open the Bills Inbox**.  Navigate to Charted › Automate › Bills. Select Bills Inbox in the sidebar.

<figure><img src="/files/J8b7uQkLaPn4MPbDJryF" alt=""><figcaption></figcaption></figure>

2\.    Click into the scanned document.  Invoice AI will automatically extract the relevant information from the PDF and load it onto the Vendor Bill form.

3\.    Select “**Switch to Bill Credit**”.  In the header bar of the open document, click the **Switch to Bill Credit** option under the ellipsis(····) menu. The page will reload and all extracted data will automatically populate onto the Vendor Credit form (the exact name of this record may vary depending on your account configuration).

&#x20;

<figure><img src="/files/qG2fxMGGVifduSRexXNS" alt=""><figcaption></figcaption></figure>

4\.    **Review the populated fields**.  Confirm that the extracted values — such as vendor name, credit amount, and line items — are accurate.

5\.    **Save the record**.  Once you’ve confirmed the details, click Save to create the vendor credit in NetSuite.

**Note:** *Invoice AI does not automatically detect that an incoming document is a credit memo. The document will first appear as a Vendor Bill. Use the Switch to Bill Credit option in the header to convert it.*


---

# 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.charted.com/ap-automation/charted-faqs/invoice-ai/how-do-i-process-vendor-credits-with-invoice-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.