Whatever arrives, whether it's a scanned letter, a photographed form, a forty-page PDF or an attachment on an email, SwiftCase reads it and puts the details where they belong on the case. It's set up around your own paperwork, so it's useful from the first morning, and everything it enters stays visible and editable, because the typing is its job and the judgement is still yours.
What you get
Whatever arrives, the bits you need end up in the fields you would have filled in yourself.
The reference numbers, names, dates, addresses and amounts you would have copied from the front of the file are already in the case by the time anyone opens it.
An attachment on an incoming email can be read the moment it lands, so when someone picks the case up the detail is already there waiting for them.
It copes with a photographed form, a scanned letter or a picture of a site, a plate or a meter, because if a person could read it, it can be read.
It's set up around your own forms and your own vocabulary, so it knows that a site reference and a patient number are different things and which one you mean.
Everything it enters sits on the case like any other field, where your team can see it, check it and change it in a click.
It's configured to your paperwork as part of implementation, which means it's reading your documents from the first morning rather than after a training period.
What it reads
The paperwork that arrives at a working firm is rarely tidy. It's a photographed form, a scanned letter with a coffee ring on it, or a forty-page PDF where the one number you need is on page thirty-one, and that's exactly the paperwork this is built for.
And because it's set up around your own fields, it reads for the things you would look for rather than for a generic list of what a document might contain.
Built for work that has to stand up
Extraction exists to get the detail in front of the right person faster. It decides nothing on its own, and the person who signs the report is still the person who made the call.
Whatever it entered is on the case where your team already works, so there's no separate queue for anyone to remember to check.
Any value it fills in can be changed like any other field, which means it never has the last word.
The fields and the vocabulary are yours, so it reads for what you would look for, in the terms you use.
On every plan
It is useful on the first morning, and it improves just from your team doing their jobs.
Day one
It reads your paperwork and fills in your fields from the first case, before there is any history for it to learn from.
As you work
Every correction someone makes and every case that closes adds to the record, so nobody has to feed it anything.
When it earns it
Where your own history can do a better job than a general model, a model built on that history takes over, and it's checked against what really happened before it does.
Quick answers about document extraction.
PDFs, Word and RTF documents, scanned pages, photographs and attachments on incoming email. The forms your own clients complete are read the same way. If a person could read it, it can be read.
No. It is set up to your paperwork and your fields during implementation and works from the first case. As your record builds, models trained on your own history can take over the parts where that earns its keep, so it gets better the longer you use it without a project to make it happen.
Everything it enters sits on the case as an ordinary field, visible to the person handling it and changeable in a click. Its job is the typing, and the call stays with the person who signs the report.
Yes. It is configured around your fields and your vocabulary rather than a generic set. A site reference, a patient number, a policy number and a job number are different things, and it is set up to know which is which for your firm.
Yes, from the entry tier. Higher tiers add reading attachments straight off incoming email, across more mailboxes.
Bring a real file to the demo and see what your own paperwork looks like once it reads itself.
