Scanned in. Structured out. Seen by no one else.
Schema Law turns the documents your firm receives, usually as scanned PDFs, into Word, Excel, CSV, or JSON files. It runs as a closed system, and your documents are never used to train an AI model.
COMMERCIAL LEASE AGREEMENT This Lease is entered into as of March 3, 2021, by and between HARLOW PROPERTIES LLC, a Delaware limited liability company ("Landlord"), and DUNMORE FREIGHT, INC. ("Tenant"). 1. PREMISES. Landlord leases to Tenant the warehouse at 4410 Quarry Road, Unit B. 2. TERM. Sixty (60) months, commencing April 1, 2021. 3. BASE RENT. $18,450.00 per month, due on the first day of each calendar month.
14HARLOW-0004127
Illustrative example. The parties and figures are fictional.
Built for the paper that actually lands on your desk
- Scanned and faxed PDFs
- Contracts and leases
- Court filings and orders
- Discovery productions
- Deposition transcripts
- Medical and billing records
- Exhibits with tables
- Photos of paper documents
From a box of scans to a working file in three steps
- 1
Upload the file as it arrived
A PDF, PNG, or JPEG of up to 20 MB, straight from your browser. There is nothing to install and nothing to prepare.
- 2
Schema Law reads every page
Each page is read into text and tables. You see the result page by page on screen, so you can check it against the original before you export.
- 3
Export the format your matter needs
Choose the file type, download it, and drop it into the tools your firm already uses.
Export the format you want
One upload, as many exports as you need. Change your mind later and export the same document again in a different format.
- Word.docx
- Editable text with its headings, lists, and tables
- Excel.xlsx
- Each table on its own sheet, with the rest of the text on another
- CSV.csv
- The document's tables, or its text line by line with page numbers
- JSON.json
- Each page's text and tables, for your own systems
- Searchable PDF.pdf
- Your original file with a hidden text layer, so search finds the page
- Plain text.txt
- The text alone, for quoting and comparison
- Markdown.md
- Headings, lists, and tables as plain text
- HTML.html
- One web page, with a section for each source page
Privileged stays privileged.
You owe your clients confidentiality, so we wrote our commitments the way you would log them: plainly, one entry at a time.
| Entry | Commitment | What it means for your firm |
|---|---|---|
| 001 | No model training on your documents | What you upload is never used to train or improve an AI model. Not ours, and not anyone else's. |
| 002 | A closed system | Documents stay inside the account that uploaded them. Nothing is pooled across firms, published, or made visible to other customers. |
| 003 | Encrypted in transit and at rest | Files are encrypted from the moment they leave your computer and stay encrypted while stored. |
| 004 | You decide how long anything is kept | Delete any document whenever you choose. The original file and everything parsed from it are removed. |
Questions partners ask first
Will my clients' documents be used to train AI?
No. Documents you upload are used only to produce your export. They are never used to train or improve any model.
How bad can the scan be?
Upload it as it is and look at the result. Recognition is strongest on clean print and weaker on faint faxes, stamps over text, and handwriting. Nothing marks a passage as uncertain, so check names, dates, and amounts against the original.
Which formats can I export?
Word, Excel, CSV, JSON, searchable PDF, plain text, Markdown, and HTML. Every plan includes all eight.
Do I need to install anything?
No. Upload from your browser and download the result. Nothing changes about how your firm stores its files.
Bring a document you have been dreading.
We will parse it with you on a call and send back the export in the format you choose.