Everything you need to know, without the jargon — Australian Edition
We know that "AI", "data privacy", and "Privacy Act" can sound intimidating. This guide explains what CaseFlow actually does, how it keeps your information safe, and what you need to know — all in plain English.
What Does CaseFlow Do?
📄
CaseFlow helps credit hire teams deal with insurer correspondence faster and with greater confidence. You paste in (or upload) a letter from an insurer, and the system analyses the legal arguments they're making, identifies which court cases they're relying on, and helps you draft a professional response.
It also runs a 42-point automated check on insurer rate evidence — covering everything from whether the rate is reasonable in your state, to whether the hire company's subrogation rights are valid, to whether a tow truck referral undermined the claimant's independent choice.
Think of it as a very well-read assistant that's studied all the key Australian credit hire case law — but one that always needs you to check its work before anything goes out the door.
How Does It Handle Different States?
🗺️
Credit hire law in Australia varies by state. There's no single national standard for what a "reasonable" hire rate is — different courts take different approaches:
NSW: Courts look at the "bottom of the range" of available rates (Lazicic v Rossi [2024])
WA: The Court of Appeal endorsed a "median market rate" approach (McKnight v Miller [2025])
SA: Courts apply the "lowest market rate" (Kerin v Zadow [2023])
VIC, QLD, TAS, NT, ACT: No binding state-level authority yet — the system falls back to the High Court's "reasonable" standard from Arsalan v Rixon [2021]
CaseFlow asks which state your matter is in before running any checks, so it applies the right test automatically.
What AI Model Does It Use?
🤖
CaseFlow uses Google's Gemini 3 Pro — one of the most capable AI models available — for tasks that need careful legal reasoning, like case advice and drafting argument letters. For quicker tasks like initial analysis, it uses Gemini 3 Flash, which is faster but still very capable.
These are the same models used by major businesses worldwide. We don't use an experimental or unproven system.
Does the AI Make Things Up?
🔒
This is the biggest risk with AI in a legal context — it's called "hallucination", where the AI invents a case name or citation that doesn't exist. We take this extremely seriously and have built a three-layer protection system that every AI output must pass through before it reaches you:
Layer 1 — Prompt rules: The AI is given strict instructions that it is "strictly prohibited from citing, referencing, or mentioning any case law that does not appear in the knowledge base." If it can't find authority, it must say so — not guess.
Layer 2 — Citation validator: After the AI generates its response, every case name it cites is automatically cross-referenced against our verified Australian case law database. Any citation not found is stripped before you see it.
Layer 3 — Text-body scrubber: A separate scanner reads through all the prose text looking for any remaining case-name patterns. If it finds one that isn't in our verified database, it replaces it with a warning placeholder.
Think of it like a three-checkpoint security gate. First, the AI is told what it's allowed to cite. Then, its citations list is checked against our records. Finally, the entire text is scanned for any case names that slipped through. All three checks happen automatically before anything reaches your screen.
That said, no AI is perfect. We always recommend checking case citations independently — particularly on AustLII — before using them. The system is a starting point, not a final answer.
What Does the BHR Engine Actually Check?
🔍
When you upload insurer rate evidence, CaseFlow runs 42 automated checks across 10 categories. Here's what it looks at:
💰 Rate reasonableness — is the rate the lowest / median / bottom-of-range for the state?
🚫 Non-compensable charges — does the rate bundle in credit costs, claims management, or legal fees?
🏃 Mitigation conduct — did the claimant shop around, read the agreement, or just accept the first offer?
🤝 Intervention offers — did the insurer offer a reasonable alternative that the claimant ignored?
🚗 Vehicle equivalence — is the replacement "broadly equivalent" to the damaged vehicle, or a newer/better model?
📅 Hire period — is the claimed period reasonable for the repairs needed?
🔧 Repair evidence — has the repair timeline been independently verified, or is the repairer affiliated with the hire company?
🏠 Need & credit — did the claimant actually need a vehicle? Can they prove impecuniosity?
⚖️ Subrogation & standing — does the hire company have valid authority to bring proceedings? Did the claimant even know about the case?
🚛 Referral pipeline — was the claimant channelled to the hire company by a tow truck or repairer, without genuine independent choice?
Each check generates specific challenge text with the relevant case law authority, so you can copy and adapt it for your response.
What Happens to My Documents?
💻
Your PDFs never leave your computer. When you upload a document, it's read and converted to text right there in your web browser. The actual PDF file is never sent to our servers or anywhere else.
Only the text content is sent for analysis — and even then, it goes through our privacy filter first.
It's like photocopying a letter at your desk and only sending the copy — the original stays with you, and we blank out personal details on the copy before passing it along.
How Can You Be Sure?
Any IT professional can watch your browser's network traffic while a PDF is being loaded. They will see zero outbound requests at that stage. The only call to our servers happens after you click Analyse, and it carries extracted text — not the original file.
How Is Personal Information Protected?
🛡️
Before any text is sent to the AI, it passes through our PII masking gateway. "PII" stands for Personally Identifiable Information — things like names, email addresses, phone numbers, registration plates, and postcodes.
Our system detects these and replaces them with placeholders. So instead of "Mrs Lisa Chen", the AI sees "[NAME_REDACTED]". Instead of "0412 345 678", it sees "[PHONE_REDACTED]". Instead of "ABC 123", it sees "[REGO_REDACTED]".
Here's what we catch:
👤 Names (when preceded by a title — Mr, Mrs, Ms, Miss, Dr, etc.)
📧 Email addresses
📱 Phone numbers (Australian formats)
🚗 Vehicle registration plates (state formats)
📮 Postcodes
🪪 Driver licence numbers
🏦 BSB and bank account details
📋 Policy and claim reference numbers
🏠 Street addresses
🆔 Tax File Numbers (TFN)
🏥 Medicare numbers
An honest note: No automated system catches everything 100% of the time. That's why we also encourage you to remove or anonymise personal details yourself before pasting text in. Our filter is a safety net, not a guarantee.
Is My Data Used to Train the AI?
🚫
No. Absolutely not. We do not use your data to train AI models. Your correspondence and case details are used solely to generate the specific response you asked for — nothing more. The AI provider's terms also prohibit them from using your data for training.
Can Other Companies See My Data?
🏢
No. Every company on CaseFlow operates in its own completely separate space. Your correspondence, case advice, templates, and history are invisible to other companies. This is enforced at the database level — it's not just a setting that could be accidentally turned off.
Think of it like separate filing cabinets in separate locked rooms. Each company has their own room, and there's no shared key.
What About the Privacy Act?
⚖️
The Privacy Act 1988 (Cth) and the Australian Privacy Principles (APPs) require organisations to only collect and use the minimum personal information necessary, to protect it properly, and to be transparent about what they do with it. Here's how we line up:
✅ Data minimisation (APP 3): PDFs stay on your device. Text is masked before reaching the AI.
✅ Privacy by design: The masking gateway is mandatory — there's no way to bypass it.
✅ Transparency (APP 1 & 5): We tell you exactly what we do (you're reading it now).
✅ Your rights (APP 12 & 13): You can request access to, correction of, or deletion of your data at any time.
✅ Data security (APP 11): All data is encrypted in transit and at rest. Access is role-based and audited.
✅ Cross-border disclosure (APP 8): AI processing uses Google's infrastructure. We ensure appropriate safeguards are in place.
Is It Legal Advice?
⚠️
No. CaseFlow is a decision-support tool. It helps you draft responses and understand legal arguments, but it's not a substitute for qualified legal advice. Every output should be reviewed by someone who understands the specific case before it's used.
We make this clear throughout the platform — you'll see reminders when you first log in, on every page that uses AI, and alongside every generated response.
The Quick Summary
📄 Your documents stay on your device — we only see the text, never the file.
🛡️ Personal details are filtered out before the AI sees anything.
🤖 We use Google's Gemini 3 Pro — a leading, enterprise-grade AI model.
🚫 Your data is never used to train the AI — full stop.
🏢 Your data is completely separate from every other company on the platform.
🔒 3-layer protection against made-up case law — prompt rules, citation validator, and text-body scrubber all run automatically.
🔍 42-point BHR check engine — 10 categories, state-aware, with specific challenge text and authorities.
🗺️ State-specific rate standards — the system knows whether your state applies the lowest, median, or bottom-of-range test.
⚖️ Privacy Act compliant — aligned with the Australian Privacy Principles.
⚠️ It's a tool, not a lawyer — every output needs human review.
Got questions? If anything in this guide isn't clear, or you'd like more detail on any point, get in touch.