Frequently asked questions

Parashift AG, founded in 2018, is a deep-tech company focusing on the autonomization of document extraction through machine learning. Parashift is based near Basel (Switzerland) and employs around 30 people in the field of machine learning engineering and development. Forbes named Parashift 2019 as one of 30 promising AI startups in Europe.

Intelligent Document Processing refers to the methods of automatically identifying objects, collecting data about them, and entering them directly into computer systems, without human involvement. To do that, such data capture systems make use of a variety of powerful technologies such as OCR engines, machine learning, deep learning, and natural language processing.

In contrast to traditional OCR software, intelligent data capture software provides much more flexibility, does not require templates and therefore less configuration, and is capable of learning based on experience, or in other words data.

Parashift Platform uses various artificial intelligence (AI) technologies to make sense of gathered data and provide the best possible extraction performance. The successful application, especially when it comes to scaling training efforts among the entire customer base, of such technologies heavily relies on a constant and seamless communication flow between users and server. Moreover, a cloud infrastructure represents the most reliable medium through which Parashift can deliver a globally scalable service with the highest level of security and ongoing software improvements to give you the world’s best user experience.

Parashift Platform is run in Switzerland.

We are convinced that sooner or later, all enterprise software will be running in the cloud. Other than that, Parashift’s AI-first approach is only conceivable in such a cloud setup. Nevertheless, we offer on-premise options as part of the Enterprise Edition offering.

GDPR is at the core of what we do at Parashift. We are fully EU-GDPR (EU-DSGVO) compliant and are used to handle compliance concerns and governance. Talk to one of our consultants regarding your specific data privacy requirements.

Yes, all data, as well as all connections from/to our platform, is fully encrypted.

Data processed by Parashift can be deleted immediately after processing via API call. However, to ensure the quality of the extraction, Parashift recommends keeping it stored in Parashift for at least 3 months to allow for retraining of the engine.

Every language using a variation of the Latin script is supported out-of-the-box. The most popular languages processed by Parashift customers are currently German, French, Italian, English, Nordic languages (Danish, Norwegian, Swedish, Finnish), Spanish, Portuguese, Czech, Slovak, Polish, Hungarian and Romanian.

With some adjustments, Parashift Platform can also handle other characters sets like Chinese.

Parashift’s user interface currently supports English only.

As Parashift Platform is not a template-based extraction platform, dealing with ever-changing document layouts and formats is at the core of its capability. With Parashift, you never will be in need to configure static templates for new documents again.

Parashift Platform supports any kind of document type through either Parashift standard document types or individual document types.

The standard way of sending documents to the Parashift Platform is through our REST API. However, you are also able to upload documents manually using the user interface. Later in 2021, we will add more document input channels such as e-mail, SFTP and the like.

We don’t know it yet.

The average processing time for standard document types and individual document types is 30 seconds, depending on various factors such as file size and others. Fully validate standard document types – where we also validate data with a human operator –  may take up to 3h until the document is fully processed and data is ready for further processing in your business software.

Document data streams for all document types are made available through our REST API. Alternatively, you are able to export data manually (JSON or CSV format).

You can set up webhooks for diffferent workflow stages in order to know when a payload can be consumed by your peer system(s).

In general, there are three ways:

Contact one of our consultants to get all the details about your specific integration possibilities.

The technical integration of the RESP API should not take longer than a couple of hours. Onboard an enterprise organization usually takes 1-4 weeks without Parashift being the limiting factor.

There are no annual maintenance costs. All costs are fully included in the monthly subscription and the actual document processing fee. You only pay for what you use. No surprises, no additional costs.

We built Parashift Platform for all sorts of use cases in document extraction. It’s built with the following in mind:

For enterprises making Parashift Platform their strategic central point for all things document extraction, Parashift Platform is crucial for significantly speeding up all digital transformation efforts.

To make it easier for you to benefit from Parashift’s high-quality extraction software in your RPA projects, we have partnered with the leading RPA provider UiPath. Thus, you can simply make use of the Parashift activity package on UiPath’s marketplace. We work with UiPath partners, just get in touch so we can intro you to one.

Our pricing is dependent on your process and use case requirements. Let us dive into your case and find an answer together.