Before you can start with creating a Metamaze project, you need to have a clear view of what the process is that you want to automate and how. Specifically, an answer is needed to the following questions
How many document types are there? Is there an exhaustive list available?
Is document type prediction needed?
Does text information need to be extracted with entity extraction?
Are image detection models needed?
Which type of page management is needed?
How will the documents be sent to Metamaze? Where should the results be sent to?
Do you require Single-Sign-On?
Which languages are in scope
Dutch, French, English, German are supported by default
Which deployment mechanism is desired?
Is human validation needed?
Do you have labelled data? Describe the format and size of the data you have.