Guides
The detail, explained.
Practical guides to sending documents to AI without personal data, what GDPR and HIPAA say about it, and how LEXARIS features work.
How to use AI with client documents without leaking personal data
To use ChatGPT, Claude or Gemini with client documents safely, replace every piece of personal data with a neutral token such as [PERSON_1] before sending, confirm nothing identifying is left, send only the tokenised text to the AI, then restore the real names and details in the answer on your side. The AI sees tokens instead of the client's details.
Read the guide →FeaturesKeys stay with you: client-side pseudonymisation explained
Client-side pseudonymisation explained: where the key lives, why not a cookie, what you gain, limits versus Cloud, and what if you lose the key.
Read the guide →Features7 ways to replace personal data, and when to use each
Seven ways to replace personal data compared: token, pseudonym, mask, hash, format-preserving encryption, synthetic data and differential privacy.
Read the guide →LawPseudonymisation vs anonymisation under the GDPR
Pseudonymisation vs anonymisation under the GDPR: Article 4(5), Recital 26, EDPB guidance, the SRB judgment, and what it means for sending tokens to AI.
Read the guide →LawHIPAA de-identification before you use AI
HIPAA de-identification before using AI: Safe Harbor vs Expert Determination, the 18 identifiers, re-identification codes and a practical workflow.
Read the guide →GuideRedacting scans, spreadsheets, emails, audio and video
How to redact personal data in scanned PDFs, spreadsheets, emails with attachments, audio recordings and video, and what each format needs.
Read the guide →