Blog

Benchmarks, methodology, engineering notes.

Engineering
· 6 min read

The alphabet tax: shrinking our AI to fit a browser tab

Our detection model carried a vocabulary for 104 languages. We ship seven. How we cut 39 MB without touching a weight — and why a browser tab is the hard part.

Read the post
Future of Work
· 8 min read

We built the perfect conditions for hiding AI use

Admit you use AI and your trade calls it cheating; be overheard and your employer bans it. Hiding is rational — and it makes AI policy unenforceable.

Read the post
Legal
· 7 min read

Redact PII from legal PDFs without uploading to the cloud

Online redaction tools put privileged client data on someone else's servers. How to redact legal PDFs on your own machine, with the text truly removed.

Read the post
How it works
· 5 min read

Reversible redaction: how tokenization un-redacts a file

Reversible redaction swaps each name for a stable code and keeps the map on your machine — share the document, decode it later. How tokenization works.

Read the post
Compliance
· 6 min read

GDPR anonymization: what actually counts as anonymized

Under the GDPR, data is anonymized only if no one can realistically re-identify anyone. Keep a mapping and it is pseudonymized — still fully in scope.

Read the post
Guides
· 5 min read

How to redact scanned PDFs and images

A scanned PDF is a picture, not text, so text-based tools find nothing and miss everything. The OCR pipeline that actually redacts scans, on your device.

Read the post
AI Safety
· 7 min read

Is it safe to upload my contract to ChatGPT?

Most NDAs and commercial contracts restrict who you may disclose them to — and uploading a copy to a third-party service is a disclosure. Read the clause.

Read the post
Engineering
· 8 min read

Why we built our own demo studio

We started with an off-the-shelf demo-video tool. Two themes, seven languages and a weekly-changing UI broke it — so we built our own. Why that matters.

Read the post
Positioning
· 7 min read

Why nobody built a redaction tool for the person holding the scan

Almost every PII tool takes text, not a page — so it starts after the hardest part is done. That assumption is why redacting a PDF full of images is still so hard for everyone who isn't a developer.

Read the post
Workflow
· 9 min read

The same name, the same code, every time

Professionals iterate with the AI across many turns. That only works if one entity keeps one code the whole way — conversation-stable anonymization.

Read the post
Positioning
· 11 min read

How companies protect PII — and the gap we fill

Companies protect personal data four ways: governance platforms, cloud APIs, managed redaction, manual blackout. An honest map, and the gap we fill.

Read the post
Engineering
· 9 min read

Why we built our own PII engine instead of shipping Presidio

Presidio is an excellent toolkit. We still wrote our own engine, because we ship a bounded PDF on a laptop, not a text stream in a cloud pipeline.

Read the post
AI Safety
· 9 min read

Is it safe to paste documents into ChatGPT?

Short answer: sometimes — and which case you're in is entirely under your control. What determines the risk, and the one step that makes it moot.

Read the post
Responsible AI
· 7 min read

A machine can't be responsible. You can

Responsibility means having something to lose when things go wrong, and a machine has no stake to forfeit. Why a human stays in the loop, always.

Read the post
Data Risk
· 7 min read

To those who quietly share client documents with a chatbot

AI makes exposing confidential data effortless, and the consequences are neither theoretical nor distant. What you risk pasting client files into a chatbot.

Read the post
Privacy Engineering
· 8 min read

PII protection is different when AI is in the loop

For 30 years, protecting personal data meant controlling database access. AI created a frictionless path from controlled documents to the public cloud.

Read the post
Benchmarks
· 8 min read

promptShield vs Microsoft Presidio: a PII benchmark

A reproducible head-to-head on 14 PDFs in 7 languages. Presidio's default install emits 666 spans, promptShield 252. Most of the gap is noise, not skill.

Read the post