> For the complete documentation index, see [llms.txt](https://learn.withessential.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://learn.withessential.com/administration/settings/set-up-invoice-prompt-templates-for-ai-drafting.md).

# Set up invoice prompt templates for AI drafting

Invoice Prompt Templates are reusable instructions for AI-assisted invoice and subscription drafting, organized by asset group type, and work the same as quote prompt templates. On Settings -> Invoicing, use **New prompt** to create one with a name, choose the asset group types it covers in **Asset Group Types covered**, add an optional description, and enter the instructions the assistant should follow when drafting for those asset groups.

Use the Use for field to choose where the prompt appears: Invoices only, Subscriptions only, or Invoices & Subscriptions. Subscriptions reuse invoice prompt templates because a subscription is a recurring invoice template.

When someone drafts an invoice or subscription with AI for a covered asset group type, the matching prompt's instructions are applied. Open a prompt from the list to edit or delete it.

## How the description is used

The description is customer-facing. When an invoice or subscription is drafted with this template, the description is copied into the document word for word as its summary — unless your instructions tell the assistant what to write in the description, in which case the assistant writes it instead. Leave the description blank to always let the assistant write the summary. The Description editor supports rich text — bold, italics, underline, headings, lists, divider lines, and tables — and that formatting carries into the generated document exactly (see [Format descriptions and terms with rich text](/revenue/quotes/format-descriptions-and-terms-with-rich-text.md)).

> **Where to find it:** Settings -> Invoicing, Invoice Prompt Templates (New prompt)

## Related guides

* [Learnings for AI quote and invoice drafts](/administration/settings/learnings-for-ai-quote-and-invoice-drafts.md)
* [Set up quote prompt templates for AI drafting](/administration/settings/set-up-quote-prompt-templates-for-ai-drafting.md)
* [Generate a subscription draft with AI](/revenue/subscriptions/generate-a-subscription-draft-with-ai.md)
* [Choose and customize your invoice document template](/administration/settings/choose-and-customize-your-invoice-document-template.md)
* [Add or edit a pricebook item](/administration/settings/add-or-edit-a-pricebook-item.md)
* [Add the intake form to your website](/administration/settings/add-the-intake-form-to-your-website.md)
* [Automate task statuses with Task Automations](/administration/settings/automate-task-statuses-with-task-automations.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://learn.withessential.com/administration/settings/set-up-invoice-prompt-templates-for-ai-drafting.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.
