PerplexityAI & privacy

Perplexity privacy: anonymize files before you ask

Perplexity privacy is not only about search queries but above all about uploaded files: reports, spreadsheets, contracts. Diskretio removes personal data from them before Perplexity analyzes them.

AI assistantNew chat
Microsoft Word

Tenancy_agreement_anonymized.docx

DOCX · 4 pages · 14 placeholders

Summarise [PERSON_2]'s obligations under this tenancy. When can [PERSON_1] end it at the earliest?

Summary for the tenant [PERSON_2]:

• Rent £1,050 per month by standing order to [IBAN_1]

• Deposit £1,210, protected within 30 days

• Keep the flat in good repair (clause 9)

The landlord [PERSON_1] can serve a section 21 notice no earlier than 4 months into the term, with at least 2 months' notice.

Draft a short question to [PERSON_1] about using the storage unit.

Dear [PERSON_1], clause 1 includes storage unit 4. May I also keep bicycles there? Kind regards, [PERSON_2]

Message AI assistant …

Only placeholders leave your device – the assistant never sees the real names.

Your formats and the AI tools you work with afterwards

  • Word
  • Excel
  • PowerPoint
  • Outlook (emails)
  • PDF
  • Scans & photos
  • TXT Text & CSV
  • ChatGPT
  • Claude
  • Microsoft Copilot
  • Gemini
  • Mistral
  • DeepL
  • Perplexity

What to watch for in Perplexity

  • Check the “AI data retention” setting on individual accounts
  • Check uploaded PDFs and spreadsheets for names and ID numbers
  • Avoid customer names in search questions
  • Reset settings when moving from Enterprise to an individual plan
  • Replace internal company and project names as custom terms

How it works

  1. 1

    Clean the file

    Anonymize a PDF, Excel or Word file in Diskretio; table structure and layout are kept.

  2. 2

    Analyze in Perplexity

    Upload the clean file and combine it with web search, without real names flowing into queries.

  3. 3

    Use the result

    Placeholders like [ORG_1] show where to put your own details back.

What Perplexity says about data use

According to Perplexity’s help center, “AI data retention” is on by default for Free, Pro and Max; turning it off under Settings > Preferences stops data from being used for model training. Per Perplexity, the opt-out only covers data collected after that date. Perplexity states that Enterprise data is never used for AI training.

When an organization moves from Enterprise to an individual plan, Perplexity says the consumer defaults apply again. If you would rather not rely on such settings, anonymize first.

Answer engine and internal data

Perplexity combines your questions with web searches. If a question contains a customer’s name, that name can flow into the research. Phrase questions neutrally and upload internal documents only once cleaned.

Diskretio replaces names, companies, addresses and ID numbers consistently, so Perplexity sees the relationships without knowing who is involved.

FAQ

Questions. Answered briefly.

Try it with your own document

10 pages per month are free. No subscription, no credit card.