Free · no signup · browser-local

AI Prompt Redactor for Emails, Secrets and Custom Terms

Review email, IP, phone, authorization and custom literal matches before replacing selected values in a prompt. Local rules, per-occurrence controls and secret-free reports.

Browse all tools →

Browser-local preparation · no model calls · no input storage

Choose rules and review

Secret labels: Authorization, Proxy-Authorization, X-API-Key, api_key / api-key / apikey, access_token / access-token, password, secret. Detects values after : or =, including escaped single/double quoted values and Basic authorization credentials. No arbitrary regex, names, addresses or NER.

Overlapping matches merge into one complete range, including chained overlaps; every rule label is retained for review. Placeholder names follow secret / email / IPv4 / CN mobile / custom priority. Unchecking a range retains that entire range. Mask length counts Unicode code points.

Your output

redacted-prompt.txt

Process the input to preview, copy and download a result.

Fixed format detection can miss personal data and secrets. It does not recognize names or addresses and offers no anonymity guarantee. Review all remaining text before sending it to any service. The report never contains original match values or custom terms. Editing input or options invalidates results and pending exports. Inputs are never saved or placed in URLs.

Getting started

Choose the detection rules, add literal private words, scan, review each occurrence and export the redacted text or a report without original values.

Before you use the result

Rules can miss sensitive data and produce false positives. This is not semantic name detection, guaranteed anonymity or a compliance certificate.

Try an example

Scan a sample email and authorization header, leave one occurrence unchanged and inspect the numbered replacements.

How it works

Bounded local pattern matching with explicit overlap handling and per-occurrence selection. No cloud model, reversible identity map or stored input.

Frequently asked questions

Review fixed-pattern matches and custom literal words, then replace selected values before sharing a prompt.

How do I use AI Prompt Privacy Redactor?

Choose the detection rules, add literal private words, scan, review each occurrence and export the redacted text or a report without original values.

Does this tool upload my data?

Inputs and files are processed in your browser. Page-view analytics do not contain your tool input.

What should I check before using the result?

Rules can miss sensitive data and produce false positives. This is not semantic name detection, guaranteed anonymity or a compliance certificate.

Related tools

AI Training Dataset ConverterMap single-turn CSV or JSON question and answer fields into messages or Alpaca JSONL, with an explicit row report.AI Dataset Train / Validation / Test SplitterSplit JSONL reproducibly with a seed, explicit ratios, optional duplicate removal and a field that keeps groups together.AI Response JSON ExtractorFind complete JSON objects and arrays inside mixed response text, select a candidate and export without rounding numeric values.