Due-diligence exhibits in. Schedules you can compute on out.
A CIM is 100 pages of schedules: rent rolls, AR aging, debt amortisation, operating statements. Each one is a table you need to test — and each one arrives in a different layout. SheetParser turns every schedule into its own clean sheet so the model starts from data, not from retyping.
First file free, up to 10 pages · paid packs run up to 600 pages per file · files shredded after conversion
Real estate acquisitions
Rent rolls and operating statements extracted so the underwriting model starts from real numbers.
Debt & equity analysts
Debt schedules and AR aging pulled into sheets that can be tested against the assumptions.
Due-diligence consultants
Every exhibit from a CIM in one workbook, per-table, with source references.
What this actually fixes
One hundred pages, twenty layouts
Each schedule in a CIM is formatted differently; template-based extraction fails after the first one.
Merged cells destroy formulas
Rent rolls with merged unit cells cannot be summed or pivoted without manual cleanup.
You cannot tell where a number came from
When a schedule is challenged, finding the page it came from is a manual search.
What comes out
One upload, one set of compute-ready outputs — not a screenshot of a table.
One sheet per schedule
Rent roll, AR aging, debt schedule and operating statement each land on their own clean sheet.
No merged cells
Rows and columns arrive as a real grid so sums, pivots and lookups work immediately.
Arithmetic preserved
Negatives, parentheses and totals are kept as numeric values rather than strings.
Source page per value
Click any figure to jump to the highlighted region of the CIM.
Excel, CSV or Markdown
A workbook for the model, CSV for a pipeline, Markdown for a memo.
Optional certificate
Hash-bound proof of which document a schedule came from.
Documents we read
Native PDF, scan, phone photo, Word, Excel, PowerPoint, CSV, HTML, email or image.
How it works
Upload the CIM
One file is one credit, up to 600 pages. Free tier: one file per day up to 10 pages.
Every schedule becomes a sheet
Tables are detected and reconstructed separately, with headers and totals kept intact.
Start the model
Download the workbook and link it into underwriting.
Every plan, every audience
- One file = one credit, up to 600 pages on a paid pack
- No merged cells; numbers arrive as numbers
- Every extracted value traces back to its source page
- Files shredded after conversion, never used for training
- A fresh file allowance every billing cycle; cancel anytime
- An optional hash-bound certificate anyone can verify for free
Questions
Does it split a CIM into separate sheets?+
Yes — each detected table becomes its own sheet, so the rent roll does not sit underneath the debt schedule.
What about merged cells in rent rolls?+
They are reconstructed into a real grid with one value per row, so the result can be summed and pivoted.
Can it handle a 200-page offering memorandum?+
Yes on a paid pack, up to 600 pages per file. The free tier is 10 pages per file.
How much is it?+
Per file: $79 for 10, $199 for 30, $499 for 100, each up to 600 pages. Credits never expire.
Run your next file
Upload the document, get compute-ready output with the source page behind every number. The first file each day is free.