AI for insurance brokers: claims files stay in the office.

Insurance broking is correspondence at industrial scale: claims files, policy schedules, renewal letters, advice to clients. The files mix financial detail with health and incident information, which is why generic cloud AI sits badly with the obligations a brokerage carries. Ermos hardware brings the drafting and summarisation capability into the office, with the claims files staying put. Our current unit is Dominion.

What your team does with it

Claims file summarisation

Condense a claims file, correspondence, reports, assessments, into a chronology and position summary the broker verifies.

Renewal preparation

Draft renewal comparisons and client letters grounded in the client's schedule and your market notes.

Policy comparison summaries

Summarise wording differences across your own policy library, cited to the documents.

Client advice letters

First drafts of advice and recommendation letters in your house style, for broker review.

Incident chronologies

Reconstruct the timeline across emails, reports and file notes on a claim.

Practice knowledge

Staff query past placements, wordings and precedents instead of digging through archives.

The compliance frame, plainly

Broking runs on an AFSL under the Corporations Act, and since the 2021 reforms claims handling is itself a financial service, with the conduct obligations that follow. The Insurance Brokers Code of Practice adds the profession's own commitments on acting in the client's interest and protecting their information. Claims files routinely contain health and incident information, which is sensitive information under the Privacy Act 1988, the category with the strictest handling rules and the sharpest cross-border questions. Each framework asks the same thing of an AI tool: where does the client's information go? A no-egress unit answers in one word. If your practice runs entirely in the cloud with no file server, Ermos Edge is hosted for your business in Australia.

For the wider deployment picture, our on-premise vs cloud comparison maps the four postures side by side.

Built for how a brokerage actually runs

Your Ermos unit is installed on your network and fully managed: monitoring, model updates and support included, with ErmosIQ learning your markets, wordings and letter conventions. Unlimited users on the unit, whatever renewal season looks like.

The use case library

Process-level guides to running specific workflows on an Ermos unit, each on its own page. We add to this library as clients show us new ways they work.

Dominion is priced per unit, per month on a 12-month term, sized to your practice: unlimited users, no per-user licences, no usage charges. Exact pricing is confirmed in the scoping consultation.

Common questions

Can insurance brokers use ChatGPT on claims files?
Claims files routinely contain health and incident information, which is sensitive information under the Privacy Act with the strictest handling requirements. Transmitting it to an offshore cloud service is a hard position to defend; processing it on-premise avoids the question.
Does this replace our broking platform?
No. The unit works over your documents, correspondence and knowledge as a drafting and retrieval layer. Placement, quoting and policy administration stay in your existing systems.
How does it help at renewal season?
Renewal packs, comparisons and client letters draft from the client file in your house style, and with no per-seat licences or usage charges, seasonal workload and temporary staff cost nothing extra.
Where does the client data go?
Nowhere. Files are indexed and queried on the unit in your office. Ermos monitors hardware health, never file contents, and support sessions run only when you initiate them.

See Dominion answering from your own documents.

A demonstration takes 30 minutes, uses no client data, and comes with no obligation.

Book a demo
Keep reading
On-premise vs cloud AI What on-premise AI costs The Dominion AI unit How ErmosIQ learns your practice