> For the complete documentation index, see [llms.txt](https://guide.digicust.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://guide.digicust.com/features/ai-generated-goods-descriptions.md).
# AI-Generated Goods Descriptions
Often, goods descriptions on invoices, packing lists, delivery notes etc. are incorrect or simply insufficient for the customs authorities. To that end, our system can automatically generate correct goods descriptions for you.
### Use tariff number as goods description
An extracted tariff number can be used to extend goods descriptions. For example, in Germany we use the EZT tariff number description or a shorter, more precise version of it, in combination with the (shortened) description we find on an invoice, to generate a correct goods description.
### Automatic translation
Digicust can automatically translate goods description it finds on your documents into your preferred language so that customs authorities accept them without manual modification. Digicust can automatically translate into >100 different language with high contextual accuracy.
### Custom goods descriptions
Every organization works slightly differently. You can adapt Digicust to your individual requirements. You can customize the goods description to be automatically structured the way you define it.
### Goods descriptions from master data
In addition, you can set goods descriptions per material or tariff number in the master data. This description will then be used as soon as we find a relevant material on processed documents.
---
# 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 dynamically by asking a question.
Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:
```
GET https://guide.digicust.com/features/ai-generated-goods-descriptions.md?ask=&goal=
```
`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.
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.