CaseFlow Automation Ltd

How We Protect Your Data

How our PII masking protects your data

CaseFlow Automation Ltd is designed to minimise the personal data that ever reaches the AI model, while still giving you high‑quality legal drafts.

Two‑Layer Privacy Design

Layer 1 — Local PDF Processing

When you upload a PDF, it is processed directly in your browser. The original document is not uploaded to our servers; only extracted text is sent securely for analysis.

Layer 2 — PII Masking Gateway

Before any text is sent to the AI model, it passes through our server‑side PII masking gateway. This gateway attempts to detect and replace common identifiers with neutral placeholders, so the model sees the structure of the case but not the underlying personal details.

What We Try to Mask

Our gateway uses pattern‑based rules tuned for UK claims data. It attempts to detect and replace items such as:

Each item is replaced with a generic placeholder (for example, [EMAIL_REDACTED] or [VRM_REDACTED]), so you can still understand the draft, but the AI model does not see the raw identifier.

Always‑On, Logged, and Auditable

The masking gateway is a mandatory step for all AI‑related features (such as analysing correspondence, generating replies, and case advice). There is no bypass path.

Every call records how many items were masked and which categories (e.g. "3 items redacted: email, VRM, postcode"), but we never log the original values.

This supports GDPR principles of data minimisation, privacy by design, and accountability, and gives you an audit trail for your own DPIA and compliance checks.

How Can You Be Sure?

We understand that "trust us, it's local" isn't enough — especially when dealing with client data. Here's a plain-English explanation of why this is verifiable, and what to tell a sceptical client or IT team.

📄
Think of it like a photocopier with a shredder built in.
When you load a letter into a photocopier, the machine reads it and produces a copy — but the original letter never leaves the room. CreditHire Assist works the same way. Your PDF is "read" inside your own browser. The system extracts the words, then the original document stays put. Only the extracted words — with personal details stripped out — are ever sent anywhere.

The Technical Reason

PDF processing is performed using a standard browser technology called PDF.js, which is the same open-source library used by Firefox to display PDFs natively. It runs entirely within the browser tab — no server connection is made during this step. This is not a policy choice; it is how the technology is architected.

What an IT Team Can Verify

Any IT professional can confirm this using their browser's built-in traffic monitor. If they watch the network traffic while a PDF is uploaded, they will see:

🔍 In plain terms: Your PDF document never travels across the internet. The words inside it do — but only after personal details have been replaced with placeholders like [NAME_REDACTED]. The document itself stays on your computer at all times.

What This Means for You

✅ The AI works on masked text, not raw personal identifiers.

✅ Original PDFs stay on your device; we only receive extracted text.

✅ We do not use your data to train AI models, and we design our architecture to send as little personal data as possible to the external model.

We still encourage users to redact or anonymise live customer details before upload wherever possible — our masking layer is an extra safeguard, not a substitute for good data hygiene.