Upload a PDF, DOCX, TXT file, or pasted text. Review what should be removed, then create a cleaned version before using AI. Names, account numbers, addresses, IDs, and other sensitive details stay out of the prompt.
Upload a file in the full workflow.Clean first. Analyze second. That is the whole point of the product.
Clean it, inspect it, then decide what happens next.
Start with a PDF, DOCX, TXT file, or pasted document text for quick testing.
See the private details detected before anything moves forward.
Download the cleaned result in the formats supported for that document type, or continue to AI analysis using the reviewed cleaned version.
Most people want AI help with private documents, but they do not want names, IDs, account numbers, or addresses floating around in the raw prompt. That gap is exactly what this product is designed to solve.
| Raw AI upload | Doc Rinse workflow |
|---|---|
| Original file goes straight to the model | Doc Rinse is designed to create a cleaned version first; optional analysis uses that reviewed version |
| Little visibility into what should have been removed | Private-detail redactions and counts are surfaced explicitly |
| Hard to verify what changed | Audit record keeps document hashes, workflow settings, and processing details |
| Trust depends on vague promises | Trust comes from visible workflow control and inspectable outputs |
Built for narrow, real use — especially tax, banking, benefits, and client-facing document review.
Use AI to understand your tax return, bank statements, or account documents without uploading your SSN, address, or account numbers to an AI tool.
Clean client-ready text, Word docs, or text-based PDFs before running AI analysis on them. Best fit today is tax and statement workflows, not every document under the sun.
If your main need is “clean this before I paste it into AI,” Doc Rinse is a better fit than a vague promise and a blind upload button.
Best current fit: pasted text, TXT, DOCX, and text-based PDFs. Start with sample or low-risk data, then test a real file when the workflow earns it.
Fastest path for testing: start with sample or low-risk text, upload a text-based PDF, DOCX, or TXT file, or paste document text below.
Free Preview works immediately. Paid plans unlock export and analysis after checkout or access-code verification.
Direct identifiers include names, SSNs, tax IDs, account numbers, routing numbers, full street addresses, dates of birth, and similar private details. Doc Rinse defaults to the stricter setting even when readability gets a little worse.
If this run is a generic document type or comes from a scanned/image-based file, slow down and review more aggressively before export or AI use.
Maximum Anonymization is planned for cases where privacy matters more than readability.
Processing pipeline
Straight answers on what this does and what it does not do.
You can. But that means names, SSNs, account numbers, dates of birth, and addresses may go directly to the model. Doc Rinse is designed to create a cleaned version first; AI analysis, when you choose it, uses that cleaned output only.
Your original document is used to create the cleaned version for that run. Doc Rinse is not intended to be a long-term document vault. Anything you want to keep should be exported from the cleaned output only.
Doc Rinse removes direct identifiers first. Depending on the privacy setting, some contextual details — such as institution names, dates, ZIP codes, or document labels — may remain so the document stays readable and useful. Privacy Strict is the default because trust matters more than preserving every bit of context.
Doc Rinse is designed to catch common direct identifiers in structured financial documents: SSNs, tax IDs, account and routing numbers, dates of birth, addresses, labeled IDs, and repeated name variants. You should still review the redaction report and cleaned output before export or AI analysis.
PDF, DOCX, and plain text uploads, plus pasted document text. The engine is tuned for tax returns (1040, W-2, 1099s), bank statements, brokerage statements, lending documents, and several benefits-style records. Support varies by file type. The available export options depend on the document and what can be safely generated and validated.
Scanned and image-based documents can be more difficult to verify than text-based documents. Doc Rinse may identify information that should be removed, but you should carefully review the cleaned result before using AI or sharing the output.
Sometimes. Cleaned PDF export is available only for PDFs that can be safely regenerated and validated. Other document types may provide cleaned text or other reviewed export options instead.
Start with Free Preview, then use the full app when you want to test a real file.