The Rossum Extensions Environment effectively automates workflows and can provide new capabilities using pre-built or custom solutions.

For example, you can cross-check sums, pair extracted data against your database, or modify export data to meet the requirements of your external ERP system.

To learn more, visit this guide from our Developer Hub.

To learn about more terms, visit our glossary.

A basic learning feature that enables Rossum to learn quickly based on customers’ previous annotations. It recognizes the document’s confirmed layout and then applies predictions based on this information to other documents with the same format.

To learn about more terms, visit our glossary.

It is a unique space where users can import documents that need to be processed.

Each queue has an extraction schema, which you can modify depending on the requirements.

Within a queue, users have the option to configure custom automation settings. You can also add extensions to improve document workflows when linking up with other systems.

To learn more about how to create a queue, you can visit this article from our Help Center.

To learn about more terms, visit our glossary.

It defines which data should be extracted from incoming documents.

Go to Queue settings and select the “Fields to capture” tab to access the Extraction schema.
You can customize the labels, IDs for integration and export, data type, score threshold, visibility, and RIR field name for each field.

If you want to learn how to set up the Extraction schema in Rossum, check out our guide.

To learn about more terms, visit our glossary.

A workspace acts as a folder where you can group related queues. It can represent a specific customer or region.

Read this guide to learn more about workspaces in Rossum.

To learn about more terms, visit our glossary.

The Manage users view is a space for Rossum account administration. Here an admin can add new users, assign them to a specific role and queue or deactivate them.

Once created, the User detail page provides more information and is an excellent place to keep track of current access management settings.

To learn about more terms, visit our glossary.

The validation screen is available for all imported documents in the main Rossum UI. Here a user can review and confirm data extracted from a document.

To learn about more terms, visit our glossary.

The Document editing screen allows you to effectively edit documents. You can change page orientation, delete pages, and split single documents into multiple new documents.

To access it, click the Edit button on the right side of the document review page.

See this article for more information on document splitting options.

To learn about more terms, visit our glossary.

It is a single piece of information captured from a document.

You can modify a data field’s label, ID, and more for every queue. You can also hide them to speed up the validation process if preferred. 

For a more in-depth look at extracted field types, you can visit this link from our API documentation.

To learn about more terms, visit our glossary.

Data fields that Rossum’s Generic AI Engine captures automatically straight out of the box.

Check this link to learn more about the currently recognized data fields.

To learn about more terms, visit our glossary.

Rossum’s unique AI engines incorporate neural networks to identify and extract document data. The two main types are the Generic AI Engine and the Dedicated AI Engine. Users can use either engine to achieve the desired results based on individual needs.

To find out which AI Engine you need, learn more about their differences here.

To learn about more terms, visit our glossary.

A process that involves collecting documents and highlighting the data required for extraction in a consistent and precise manner.

It is vital to have high-quality annotations to ensure that the AI engine learns what data is needed and successfully captures it.

You can learn more about annotations by reading our Annotation Guide.

To learn about more terms, visit our glossary.

It is a custom engine trained to recognize customer-provided data and is tailored to the customer’s specific data capture needs. Dedicated Engine helps process documents with diverse layouts. It can also extract custom data fields and increase levels of data capture accuracy over time.

It is a paid feature.

You can refer to this guide from our Help Center for a more in-depth look at how Dedicated AI Engine training works.

To learn about more terms, visit our glossary.

It allows the user to extract fields that the Generic AI Engine does not automatically capture.

You must adjust the queue schema if you want to add a Custom data field. Used alongside the Dedicated Engine, they enable the effective processing of documents with custom layouts and fields.

Read our guide to learn more about adding Custom data fields.

To learn about more terms, visit our glossary.

It is a pre-trained AI engine that recognizes a variety of datasets for several different use cases.

Currently available Generic Engines include:

• the Accounts Payable And Receivable (pre-trained to process Tax Invoices, Proforma, Receipts, Orders)
• the Chinese Invoices Engine (pre-trained to process Governmental Tax Invoices from Mainland China, also called fapiao) BETA
• Certificate of Analysis Engine (pre-trained to process Certificates of Analysis that are quality control documents standard in the food and beverage industries) BETA

To learn about more terms, visit our glossary.

A line item is any product or service listed in an invoice or any other type of document. Line item data includes quantity, price, and other relevant attributes.

To learn about more terms, visit our glossary.

It is a blue rectangle that defines the position of captured data on the document’s validation screen. You can always edit or re-adjust it to ensure that the annotations are successful.

To learn about more terms, visit our glossary.

The Magic Grid feature allows you to quickly and efficiently capture tabular data. With just a few clicks, you can quickly extract dozens or hundreds of items.

For more information about Magic Grid and how it works, see this user guide in our Help Center.

To learn about more terms, visit our glossary.

It is a section of Rossum where you can modify the extraction schema. You can specify which data fields should be captured in a specific queue. Custom fields and sections can also be added to allow the user to extract all required data.

To learn about more terms, visit our glossary.

It is available from the Statistics tab and allows users to explore document-related information for all queues and workspaces. It is an excellent tool for continuous improvement on both an individual and team basis.

To learn more, visit our Help Center guide here.

To learn about more terms, visit our glossary.

To learn about more terms, visit our glossary.

Admin and Manager level users can see the automation blockers (red “A” icon) on the validation screen. They appear when Rossum’s engine finds fields that block automation process.

To learn about more terms, visit our glossary.