Tools › Use cases

Use case

Redact PII from support tickets

Support transcripts are full of the things customers paste when they are frustrated: card numbers, addresses, order confirmations, and screenshots of their account page. That is exactly the data you want summarised, and exactly the data you should not hand to a third party unredacted.

Try it on the live API No signup. 2,000 characters, 20 runs per 10 minutes.
Output appears here.

What this gives you

  • Works on the raw body of a ticket, including quoted email chains and inline signatures.
  • Catches credentials customers paste by accident, such as API keys and passwords.
  • Leaves the narrative intact, so sentiment and intent analysis still work.
  • Runs in one call per ticket, so it drops into an existing ingestion pipeline.

Request

curl -X POST https://api.bitbanger.in/v1/redact \
  -H "X-API-Key: rdct_your_key_here" \
  -H "Content-Type: application/json" \
  -d '{"text": "Hi, I am locked out. My email is sam.okafor@example.com and the card ending 4242 is on the account.", "style": "replace"}'

Questions

Will it break the conversation structure?

No. Only the detected spans are replaced; everything else, including line breaks and quoted text, is returned unchanged.

Does it catch credentials?

Yes. API keys, JWTs, connection strings, and passwords are separate entity types and are redacted in the same call.

Related