Guides: using AI without exposing personal data

Detection rules let you always or never flag specific terms and RegEx patterns, and define your own entity types with their own placeholders like [CLIENT_1]. How to set them up in Stript, with examples for firms and companies.

A detection profile bundles PII types, sensitivity, language, detection depth, and your active rules into one saved configuration. Free presets for legal, medical, HR, and financial documents get you started; your own profiles make recurring document types a one-click setup.

How to anonymize a PDF locally on your device: personal data is detected, reviewed, and replaced with placeholders, including scanned PDFs via on-device text recognition.

To use ChatGPT safely with client or patient data, remove personal data before the text ever leaves your device. Here is the secure four-step workflow.

Don't take 'local-first' on trust. Disconnect from the internet, watch the network traffic with Little Snitch or Wireshark, and check the complete list of network requests Stript makes.

Stript offers two detection depths: Thorough checks every finding in context; Fast skips the deepest analysis for a much quicker first pass. When to use which, how hardware tiers affect speed, and how to keep quality where it matters.

Even for personal use, you shouldn't put personal data into ChatGPT and similar tools. Everything you paste is processed on someone else's servers. The safe way: remove personal details locally, before the text leaves your device.

Tax advisors can use AI without breaching confidentiality by removing client data locally, before the text ever leaves the device.

Doctors and clinics can use AI without exposing health data by removing patient data locally, before the text ever leaves the device.

Data protection officers can enable AI instead of banning it by removing personal data locally, before employees paste it into an AI tool.

Lawyers can use AI tools like ChatGPT without breaching client confidentiality by removing client data locally, before the text ever leaves the device.

An all-in-one AI chat with built-in anonymization is convenient, but it usually costs more, gives you only the raw model, and has to receive your original text first. Anonymizing locally and using your own AI keeps the full product, predictable cost, and your data on your machine.

With on-device anonymization, the document content never leaves your machine. Cloud services still transmit the data to someone else's server, even when hosted in Germany.

anonymization.ai (Glanos) is an enterprise anonymization platform: SaaS hosted in Germany or on-premise Docker, sold via demo. Stript is a self-serve desktop app where documents never leave the device. A factual comparison.

anymize.ai is a German cloud service: documents are uploaded and processed on Hetzner servers in Germany. Stript is a desktop app: the document never leaves your machine. A factual comparison of architecture, pricing, and compliance.

On our German and English benchmark, Stript's on-device pipeline reaches an F1 of 97.3 (English) and 95.8 (German), with 95 to 98% recall. Checksum-validated identifiers like IBANs, credit cards, and bank accounts are caught at 100% recall. Every detection can be reviewed before anonymization.

Anonymization removes the link to a person irreversibly. Pseudonymization replaces identifying data with placeholders and stays reversible with separately held information. What that means for using AI.