Powered by Anthropic's Claude — purpose-configured for Australian insurance document analysis with AFSL-compliant guardrails, clause-level citations, and zero hallucination tolerance.
Claude leads on three dimensions that matter for insurance: reasoning depth over long documents, instruction-following precision, and safety-first design. It reads your entire 150-page PDS in a single pass.
Here's exactly what happens when you upload a PDS document. Every step designed for accuracy, traceability, and speed.
Your PDF is uploaded securely. Claude reads the entire document natively — no OCR needed for digital PDFs.
7-step analysis — reconnaissance, definitions, coverage, exclusions, conditions, gap analysis, cross-reference audit. Output forced into validated JSON.
Every data point gets High, Medium, or Low confidence with rationale. Medium and Low findings flagged for human review.
Results delivered with clause-level citations — section number, page, clause heading. Click any citation to jump to the source.
A generic AI doesn't know that "Words with Special Meaning" is QBE's definitions section. Our system prompt encodes deep knowledge of Australian PDS formatting across every major insurer.
These aren't suggestions — they're hard constraints built into every API call.
Constrained to general information only. Never recommends a specific product or crosses into personal financial product advice.
If a clause isn't in the document, the AI says "not addressed." Designed to refuse rather than guess.
Responses grounded exclusively in your uploaded documents. No internet, no other clients' data.
General Advice Warning appended automatically to every output. Enforced at the API level — can't be removed.
Every firm's data completely isolated. Enforced at the database level with tenant-scoped queries on every request.
Every claim includes a source reference — section, page, clause. If it can't cite a source, it doesn't make the statement.
Trust comes from verifiability. Every finding includes a precise citation — section number, page, and clause heading — so you can verify any claim in seconds.
Infrastructure hosted in Sydney on SOC 2 compliant servers. Documents encrypted in transit and at rest. Anthropic does not train on your data.
We evaluated every major AI model. Three things made the decision clear.
Claude's 1M-token context window reads an entire 150-page PDS in a single pass. Definitions on page 5 stay connected to exclusions on page 67.
Claude follows complex, multi-step analysis prompts with high fidelity. When told to extract exclusions verbatim and flag carve-backs, it does exactly that.
Anthropic's constitutional AI approach means Claude is designed to refuse rather than fabricate. In insurance, a confident wrong answer is worse than no answer.
We're here to answer your questions. We usually reply within one business day.
Prefer email? Write to hello@insuranceadvice.app
We use cookies to analyse site traffic and improve your experience. Essential cookies are always on. See our Cookie Policy.