Airclerk puts AI to work on the document-heavy side of brokerage: the renewal pack, the submission to market, the shared inbox, the client file that has to pass a spot check. The workflow does the assembling and the checking. The broker keeps the client, the market and the advice.
We implement Claude, Microsoft Copilot and ChatGPT; the platform is chosen around your systems and the work.
Illustrative example
Commercial renewals are the pattern we have taken furthest, so it is the one drawn here. The client, the figures and the dates are made up. The shape of the work is not.
Pulled from the broking platform and the client folder as they are. Nothing is re-keyed, and the broking platform stays the source of record; what the AI platform processes and what Airclerk retains is agreed before the build.
What changed since last year, with each change traced to the document it came from. A draft note to the client and a draft submission to market, written in the brokerage's own format. Anything the file does not support is listed as missing rather than filled in.
The broker reads the exceptions before the draft, decides the market strategy and the advice, and approves the note before anything reaches the client or an insurer. The workflow never sends.
Insurance brokers and intermediaries use AI models such as Claude, Microsoft Copilot or ChatGPT to support brokerage workflows such as submission-to-market preparation, renewal pack assembly, broker inbox triage, file-completeness and compliance review, client onboarding, claims advocacy, complaints handling and adviser supervision evidence. In a regulated brokerage, the assistant needs to be connected to broking platforms, client documents, conduct and compliance evidence, and human approval workflows before it can be used safely with clients, insurers and MGAs.
Each of these is a candidate first workflow. The renewal above is where most brokerages start, because the reviewer already knows how to check the output: last year's file sits beside the draft.
Risk summaries, market lists, exposure schedules and submission letters drafted from client data and prior policies.
Shared-mailbox classification, urgency, missing documents, draft client and carrier responses.
Spot checks across client files for record-keeping, conduct and audit obligations, with gaps flagged for remediation.
Scope of service, fact-find synthesis, suitability commentary and disclosure pack drafts.
Claim chronology, evidence assembly and broker advocacy letters in support of clients.
Triage, statutory and policy timeframes, evidence packs and response drafts.
Sample review across an adviser's book, exception flagging and supervision evidence packs.
GWP and book commentary across insurers and MGAs, exception narratives and board pack input.
Whichever workflow goes first, the evidence record behind it is the same: what the AI did, what it relied on and who signed it off. With Assurance enabled that record is retained as an AI Workpaper. That is AI Process Assurance, available as an optional platform subscription and implemented alongside the workflow.
The same four stages for every firm we work with. A brokerage of 30 seats and one of 120 get the same path; only the scope changes.
Where AI could make the biggest difference, how that work runs today, the systems it touches and who owns it. We also work out together whether Airclerk is the right partner for it. If we are, the conversation gives us enough to quote.
One document: the outcome we are aiming for, what we deliver, what your team contributes, the fixed fee and timeline, and what acceptance looks like. Nothing starts until it is agreed on both sides.
The engagement opens with the detailed design, agreed with you before anything is built. Then we configure and connect the workflow to your documents and systems, build in the agreed review controls and audit trail, test it on real work, and prepare the people who will run it.
Handover, and the support that follows go-live, are written into the scope so you know what is covered before you sign. Ongoing operations and further workflows are a separate agreement, made when you want them rather than switched on by default.
Read how an engagement runs in detail →
Hosted by Airclerk, or deployed single-tenant into your own Azure tenant on request, so the controls, evidence and audit trail sit where your conduct supervision and record-keeping obligations need them.
Roadmaps follow market size. ANZ brokerage networks, AR/AB structures and broking platforms are unlikely to be on the early-adopter list.
NZ brokerages operate under FMA conduct supervision, IBANZ standards and, for advice-heavy books, FSLAA/FAP. AU sits under ASIC and the Insurance Brokers Code of Practice: adjacent but distinct.
Airclerk operates across New Zealand and Australia with active relationships across brokerages, the insurers and MGAs they place with, and the platforms that connect them.
The Contracts of Insurance Act 2024 introduces a statutory duty to pass on policyholder representations and tightens premium-handling expectations, with a backstop commencement of 15 November 2027. AI fits on the document side: client-file pass-on audits, disclosure pack drafts and consistency checks across the book.
Insurance brokers and intermediaries use AI to support document-heavy brokerage work such as submission-to-market preparation, renewal pack assembly, broker inbox triage, file-completeness and compliance review, client onboarding, claims advocacy, complaints handling and adviser supervision evidence. Airclerk identifies, designs and implements these as governed workflows for brokerages across New Zealand and Australia, connected to existing broking platforms, client documents and human approval, rather than leaving the assistant as an open chat tool.
Commercial renewals. It is the pattern Airclerk has taken furthest, because the company began by building renewal software for insurance: the renewal runs as a governed, evidenced workflow that prepares the year-on-year diff, the exposure changes and the draft client correspondence, holds anything the file does not support for the broker, and, with Assurance enabled, retains an AI Workpaper behind every outcome. Each of the other workflows on this page is a candidate first workflow, and Airclerk has broker-specific accelerators to shorten the path to production.
In plain terms: we agree the checks a renewal or submission must pass before the build, and keep a readable record of what happened on each one. Airclerk calls this AI Process Assurance: a Workflow Charter defines the path the work should follow, a Semantic Audit records what actually happened, and the result is a retained AI Workpaper. For a brokerage, the controls, approvals and audit trail behind a renewal, submission or advice file are built for conduct supervision and record-keeping, and can be hosted by Airclerk or, on request, deployed single-tenant into your own Azure tenant so the evidence sits where your obligations need it.
No. Airclerk records the work that runs through the instrumented workflows and approval steps it implements, producing the evidence and audit trail for those governed paths; it does not claim to capture every interaction or guarantee total capture. Assurance covers the work a brokerage routes through the rails Airclerk builds, which is why the first step is choosing and governing the workflows that matter most.
The Contracts of Insurance Act 2024 introduces a statutory duty to pass on policyholder representations and tightens premium-handling expectations, with a backstop commencement of 15 November 2027. These are the brokerage's obligations to meet, not legal advice from Airclerk. AI fits on the document side, supporting client-file pass-on audits, disclosure pack drafts and consistency checks across the book so a brokerage can evidence how it met those duties.
Bring the renewal, the submission or the inbox you would most like off your brokers' desks. A free introductory conversation is enough to tell you whether it is a good first workflow and what it would cost to build.