AI extract pdf information of incoming mails into input fields

Feature requests
1

AI extract pdf information of incoming mails into input fields

  1. What is your original issue/pain point you want to solve?

We get order information emails into zammad with attachments (pdf) which contains the e.g. order number.

  1. Which are one or two concrete situations where this problem hurts the most?

none

  1. Why is it not solvable with the Zammad standard?

Currently you can only categorize tickets not extract certain information from attachments.

  1. What is your expectation/what do you want to achieve?

I would like to extract the order number via AI from the pdf files of different providers into a generic input field in zammad.

(example pdf files in Ticket#10221228)

2

That sounds to be best solved with an MCP connected AI

3

I think with the already existing OCR handling for some situations, it should not be a big deal to extend the AI-Agent text extrator for that.

4

Maybe something like Docling or Kreuzberg to support more than PDF?

1 Like
5

This goes then already in a much more advanced direction, then a simple extension of existing stuff :smiley: