Combine a client’s books for AI, privately.
Drop the folder of statements, invoices, and ledgers. FileConcat reads the PDFs and spreadsheets right here in your browser and gives back one file for ChatGPT, Claude, or Gemini. Nothing is uploaded, so client data stays on your machine.
- Nothing is uploaded
- Statements and spreadsheets read as text
- Client data stays on your computer
Drag your client folder here
Statements, invoices, and ledgers. Read in a second.
The numbers never leave your computer.
Most tools that read a document upload it to a server first. FileConcat does the reading in this browser tab. Nothing is sent, nothing is stored, and there is no account to create. You can open your own network panel and watch: after the page loads, working through a client folder sends zero requests.
Suitable for confidential client and engagement records
- ✓22 files read in this tab
- ✓values pulled from 9 PDFs and 6 spreadsheets
- 0 bytes sent to any serverprivate
From a client folder to a prompt in three steps.
- 1
Drop the client folder
Pull in a whole client at once, or a single engagement. Subfolders of statements and workpapers come along.
- 2
It reads and cleans
Statements, ledgers, and letters are turned into text. Duplicates and system noise are left out.
- 3
Paste into your assistant
Out comes one file, a file tree at the top, ready for ChatGPT, Claude, or Gemini.
The formats a client’s books arrive in.
You do not have to export or convert anything first. Born-digital documents are read straight through, and it is the text and the numbers that go into the file, never the raw document.
- bank and card statements, tax forms
- XLSX
- ledgers, trial balances, workbooks
- CSV
- transaction and payroll exports
- DOCX
- engagement letters and notes
A scanned statement has no text to read
A statement that is a photo or a scan, rather than a born-digital PDF, holds no text to pull. It comes through flagged as “no text found” so you can run it through OCR first. It is never dropped without telling you.
One client, one file.
A folder of statements and workbooks goes in. A single file comes out, labeled as documents so the model reads it as a client file, not as source code.
acme-fy25/
├── statements/
│ ├── jan-mar.pdf
│ └── apr-jun.pdf
├── ledger.xlsx
├── invoices.csv
└── tax-return.pdf<documents project="acme-fy25">
<summary>
This is a packed snapshot of a set
of documents, assembled by
fileconcat.com.
File count: 6.
</summary>
...Common questions.
- Is it safe to use AI on confidential client financials?
- The combining step is fully local: FileConcat reads every file in your browser and sends nothing to a server, so the documents never leave your computer. What you then paste into an assistant is your own choice, but preparing the file leaks nothing.
- Can it read bank statements and spreadsheets?
- Yes. Born-digital PDF statements, Excel ledgers, and CSV exports are read as text, so the assistant works from the actual numbers and tables rather than an image of them.
- Do I need to convert my spreadsheets first?
- No. Drop XLSX and CSV files straight in, and FileConcat pulls the values into the combined file as text alongside the PDFs and Word documents.
- Does anything get uploaded to a server?
- No. Everything, including the PDFs, is read in your browser tab. Nothing is sent, nothing is stored, and there is no account to create.