Airclerk puts Claude to work inside Australian accounting practices, on real client engagements and on the systems the firm already runs. We built two things for it. The Australian Accounting Pack is twenty-five skills for the work that fills the year, written to the Income Tax Assessment Acts, the GST Act 1999, the Taxation Administration Act 1953 and the ATO's own published guidance, and kept verified against those sources rather than remembered. The second is a Xero connection that assumes a client list rather than a single business, and that covers every operation Xero publishes for accounting and fixed assets. Anthropic's nearest accounting release is written for a US business owner. This is the Australian practice version, built in September 2026 from the New Zealand pack already in use in practices there. Behind it is a team that spent years implementing systems inside regulated firms on both sides of the Tasman, including years at Trineo, a Salesforce partner that grew from Christchurch into Australia.
Here for your own finance function rather than client engagements? See finance teams →
Illustrative example · one skill of the Australian Accounting Pack
The franking account is a memorandum account, so it gets reconstructed from the ATO account transactions, the dividend statements, last year's closing schedule and the prior-year return figures that set the rate. A company with no dividends and no refunds is a short job. This one has both, which is the version that eats an afternoon. One skill of the twenty-five, and the clearest illustration of what tying a figure to evidence actually costs. Figures are illustrative. Source material sits in the right-hand column, the checks in the reconciliation rows beneath the table, and the whole schedule stays marked draft until the reviewing accountant has been through it.
| Movement | Credit / (debit) | Tied to |
|---|---|---|
| Opening balance, 1 July | 38,400 | Last year's closing schedule, agreed to the ATO account transactions behind it |
| PAYG instalments, four payments in the year | 42,000 | ATO account transactions, by payment date. Last year's June quarter, paid in July, is in; this year's June quarter, paid 28 July, is next year's credit. |
| Credits on a franked distribution received | 1,500 | Distribution statement from the investee company |
| Credits attached to the December interim dividend | (20,000) | Dividend statement. $60,000 cash plus $20,000 credits, so $80,000 gross: 25 cents in the dollar, the maximum at a 25% rate. The first frankable distribution of the period, so it sets the benchmark franking percentage for the period, here 100%. |
| March refund on assessment | (5,200) | ATO account transactions |
| Closing balance, 30 June | 56,700 |
Five sources agreed. The sixth, the one place the account appears to live already, was out by exactly the refund. That is the ordinary outcome of this job, and it is the reason the schedule has an evidence column at all.
Two things this workflow will not do. It will not assume the period. For most companies the franking year is the income year, and a late balancer's period and return timing are checked against the entity's own elections rather than defaulted, so a preparer who learned the job on the New Zealand side of a trans-Tasman group does not get to bring 31 March with them. And it will not lodge: a debit balance at year end is franking deficit tax, due with a franking account tax return on the entity's own timetable, and where the part of the deficit that comes from franked distributions, and from tax refunds in a year that also had them, is more than 10% of the credits that arose in the year, 30% of the offset on that part is lost unless an exception applies, so it quantifies both, flags them, and hands the return notes to the reviewer.
The other twenty-four cover the rest of the year, from year-end workpapers to ATO correspondence →
Australian accounting firms use Anthropic's Claude models across the bounded, reconciled work that fills the year: year-end workpaper assembly tied to the trial balance, PAYG instalment plans and client letters, FBT workings, STP and super reconciliations, ATO correspondence triage and client questionnaires. In public practice Claude needs to be connected to the ledger and practice systems, with engagement isolation so one client's records are walled off from another's, and a reviewer's sign-off before anything leaves the building.
Candidate workflows, one of which becomes the first implementation. The implementation anchors on year-end workpapers; most of the rest of the pack feeds that file or follows it.
Lead schedules per balance-sheet line, tied to the trial balance, with capital allowances, the tax reconciliation and the return mapping, queries listed and reviewer notes flagged by severity.
Taxable, GST-free and input-taxed classifications, cash against non-cash timing and the financial supplies, reconciled to the ledger before the BAS goes in.
Amount or rate, a variation modelled against the 85% shortfall test, one dated calendar for instalments and assessment, client letter drafted.
Notices from the firm's approved feeds classified by client, clock and severity; drafts for routine items, director penalty notices and garnishees escalated the same day.
Agent-list progress against the program dates, missing-information status, 15 May risk flags and payment reminders, with questionnaires and chasers drafted in the firm's tone.
The benefit register on the year to 31 March, type 1 and type 2 gross-ups, exemptions and employee contributions, with the reportable amounts laid out for the reviewer's call.
STP Phase 2 disaggregation checked, PAYG withholding recalculated, super tested on both sides of the Payday Super changeover, state payroll tax by actual nexus.
The designated-service gate first, then CDD level, beneficial-ownership maps and the record the firm's programme requires.
A practice briefing from the ATO, the Federal Register, Treasury, the courts and the state revenue offices, filtered to what touches your client base.
P&L against budget, working capital, a 12-month three-way forecast with stated assumptions, and owner commentary for the reviewer's sign-off.
A substantive question worked at a stated depth, every claim cited to a source that was opened, with a contrary-authority pass and a result state on the front page.
Someone else's memo or letter checked claim by claim against official sources, cited ATO material status-checked. It corrects and never rewrites.
Accruals, prepayments, depreciation and reclassifications drafted from the workpaper that computed them, posted on the reviewer's approval with the supporting schedule attached to the journal.
Aged receivables, coding exceptions or a trial balance pulled straight from Xero for a named client, with writes gated behind the organisation they land in.
Livestock movements reconciled by class under the tax stock valuation choices with natural increase shown, and dairy income tied to the processor statements on the contract's actual price terms.
Retention schedules both directions and WIP reconciled to progress claims, with state trust-account requirements tabled by project and jurisdiction for the reviewer.
The account rolled on the income year and dividends tested against the benchmark and the rate for imputation purposes, with a deficit flagged for the reviewer.
Each loan vintage rolled, complying agreements and minimum yearly repayments tested, UPEs not treated as loans by default, with actual loans, trust terms and Subdivision EA still worked through against the judgment and the ATO's response.
Foreign shares and funds reconciled in units and currency, distributions and CGT parcels built in Australian dollars, foreign income tax offset tested rather than assumed.
Rental deductions, CGT or revenue character, GST, foreign-resident withholding and land tax mapped by state for the reviewer.
Optional AI Process Assurance can sit behind the workflows we implement: the reasoning, sources and sign-off retained as an AI review record, the AI Workpaper, so the firm can show what the AI did, how it was checked and who signed off. It is a platform subscription, implemented alongside the workflow, and the workflow runs without it.
The implementation is built around year-end workpaper preparation: the highest-volume work in the practice, with a trial balance to tie back to and a review a partner already knows how to run. Most of the other skills in the pack support that job, from the BAS and payroll reconciliations that feed the file to the chasers that unblock it. Final numbers, tax positions, structuring advice and anything lodged stay behind stricter gates, with the accountant.
Each workflow defines who reviews what: partner, manager or the engagement's responsible reviewer. The AI Workpaper records which sources were attached, what changed in review and whether any required gate was missed.
We run the workflow on held-out client jobs before an accountant relies on it: does every schedule tie to the ledger or state its difference, does it verify rates and dates against current sources, does it respect engagement isolation, does it route consequential outputs to the right reviewer. Prompt-injection and cross-client-leakage checks are part of the production gate.
The configured workflow on your systems, a Workflow Charter setting out stages, evidence and approval gates, the evaluation results from the held-out tests, a runbook with training run separately for accountants and support staff, a retained AI Workpaper for each material run, and the check-ins after go-live that confirm the workflow is being used rather than installed, shaped to your firm and written into the scope. Ongoing operations beyond that are a separate agreement.
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 →
The pack is built as Claude skills and is deployed to your own Claude instance, under your own agreement with Anthropic. We also implement Microsoft Copilot and ChatGPT; if your firm runs one of those, the workflow is scoped for it in the first conversation. We work from Christchurch, two hours ahead of Sydney for most of the year, and on site where an implementation needs it.
The argument for partners is about margins, not technology. Compliance work is priced against a market that keeps compressing, so the hours a job absorbs decide its realisation. When the workpaper pack arrives assembled and tied, the reviewing accountant starts at review instead of assembly, and the same partner can stand behind more jobs without reading any less carefully. We won't invent a percentage for a practice we haven't met; the implementation puts numbers against your own jobs instead. The quieter effect is retention. The graduates a firm wants to keep did not join to key numbers into workpapers.
See the New Zealand partner briefing (PDF) →
One page to circulate before the first conversation: what this is, where client data goes, the quality-review answer, and what the implementation asks of the firm. The New Zealand version is linked for the shape of it; an Australian one comes with the first conversation.
Engagement isolation between clients is written into every skill as a rule, and the implementation enforces it in the connections rather than trusting the model to remember. Each output names the client, the legal entity, the period and the state or territory where it matters. The job is sorted for materiality before it is worked, so a $500 coding query does not come back as a research memo. Consequential steps stop for the named reviewer, and a schedule that will not tie to the ledger states its reconciling difference rather than carrying a plug figure.
PAYG instalments by amount or rate, with the variation and the 85% shortfall test. GST as the component of the BAS: taxable, GST-free and input-taxed, cash against non-cash timing, financial supplies treated one fee at a time. STP Phase 2, PAYG withholding and super on both sides of the Payday Super changeover. FBT on its own year to 31 March. Division 7A, franking, the CGT and foreign income tax offset workings behind offshore holdings, and the AASB tiers, ASIC size tests and ACNC thresholds that decide what a set of accounts has to be. Every skill cites to the Income Tax Assessment Acts 1936 and 1997, the GST Act 1999, the Taxation Administration Act 1953, the Fringe Benefits Tax Assessment Act 1986, ATO material, the AASB or the APESB, with the retrieval date attached, and state and territory rules are selected by the client's actual nexus rather than assumed to be national. Where a rate cannot be verified, the skill declines to state the number instead of reaching for one.
Eighteen carry a deliverable end to end: year-end workpaper packs that tie to the trial balance, with capital allowances, the tax reconciliation and the return mapping; PAYG instalment plans on the ATO calendar; FBT workings; payroll reviews across STP, withholding, super and state payroll tax; GST on the BAS; ATO correspondence triage; AML/CTF onboarding support; management accounts with a linked twelve-month three-way forecast; the reporting tier check; the client query chaser; and the balances that fill real Australian client files: franking accounts, Division 7A loan accounts, offshore holdings with their CGT and offset workings, livestock on the tax stock valuation choices, dairy income tied to the processor statements, construction contracts with their retentions and state trust accounts, and residential property with its rental, CGT and land tax questions. Five are tax research skills, covered below. One runs the practice's monitoring rig across the ATO, the Federal Register, Treasury, the courts and the eight state and territory revenue offices. One interviews the firm on the way in and writes the practice profile every other skill reads, so the pack knows your client mix, year ends, states, systems and reviewers before it does any work.
The pack was built in September 2026 from our New Zealand Accounting Pack, skill for skill, with Australian law written in rather than translated: PAYG instalments replace provisional tax, Division 7A replaces the current account rules, franking replaces imputation, actual offshore income and CGT replace the FIF regime Australia repealed in 2010. No Australian firm has run it in production yet. The New Zealand pack it came from has, and every control in it came across. The pack is an accelerator, not a finished product: it is where an implementation starts, and each firm's version diverges from there as skills are adapted to the firm's own workpapers, templates and risk settings. We provide the skills index behind it, and the source review that records which ATO, AUSTRAC, High Court and Federal Register pages were opened when it was written. Ask us about it.
Claude can be given a Xero connection, and Xero ships one itself. For a single business it does the job. A practice needs two harder things: reach across every client, and reach into every part of the ledger the work touches. Ours covers 241 operations, which is every one Xero publishes for its Accounting and Assets APIs, generated from a checksum-pinned copy of Xero's own specification. Australian payroll is the gap.
Raise a $4,200 consulting invoice for Acme.
Two of your clients match Acme: Acme Holdings Pty Ltd and Acme Trading Pty Ltd. Which one?
Trading.
Drafted in Acme Trading Pty Ltd, $4,200 to consulting income. Ready to post?
This is what joins the pack to the ledger. The year-end workpaper pack can read the asset register behind its capital allowances schedule, and the adjusting journals it proposes can be posted from it. Completeness here means every operation in Xero's published specification for those two APIs, generated from a pinned copy and held to it by the test suite; running each one against a live organisation is a separate exercise. It is Airclerk's own tool rather than a Xero product, and not affiliated with or endorsed by Xero. We install and configure it as part of an implementation, and which ledgers it is pointed at stays the firm's call.
Australian tax settings move constantly, which is why the pack treats every rate and date as something to re-open rather than something it knows. The twelve months to July 2026 alone, every date below checked on 8 September 2026, with the ATO, AUSTRAC, High Court and Federal Register pages opened recorded in the pack's source review and the Tax Practitioners Board dates checked against the Board's own guidance:
The pack does not memorise any of this. Every skill verifies rates and dates against the ATO, the Federal Register of Legislation and the relevant state revenue office when it runs and carries the date it was retrieved, and a monitoring skill sweeps ATO legal releases and the newsroom, Federal Register amendments, Treasury and Budget material, the courts and the eight state and territory revenue offices, holding the line between proposed, enacted and in force. The pack itself was authored against sources opened on 8 September 2026, and its source review is published with it: which ATO, AUSTRAC, High Court and legislation pages were read, what they said, and where the ATO's own site refused an automated request and a browser had to do the job instead.
A tax question that ends in a memo fails differently from a workpaper pack. Not a number that will not tie, but a confident answer resting on a search result nobody opened. Five of the twenty-five skills do that work, and they run one method between them.
Every substantive research run is routed Lookup, Quick, Standard or Deep from the complexity of the question and how far the firm intends to rely on the answer, and the output names the depth it ran at. A $500 coding query does not get a research memo.
A search result is not a source. Each run separates what it relied on from what it reviewed and set aside, and discloses the leads it never opened at all. The ATO's website and Legal Database refuse a good share of automated requests, so there is an order of fallbacks behind them, and the output names which one supplied the text rather than implying it read the ruling.
Every substantive research output goes looking for what cuts against the position it is building, and records what it found. A question about an earlier income year either confirms the version of the law in force at the time or says it could not, instead of quietly answering with current law. ATO material is classified by whether it actually binds, so a public ruling, a practical compliance guideline and a web page are never given the same weight, and a Bill or a consultation is never described as law.
A figure that matters is not computed in a research note when a skill owns that deliverable. It goes to that skill, where it has to tie to the ledger or carry a stated reconciling difference. Court and tribunal coverage in the public record is uneven and the outputs say so rather than implying a citator. Cross-border questions get their Australian component answered and the foreign-law or treaty question named for a specialist. No client name, figure or identifying detail goes into a public search query. Each run ends in a stated result state, so a partial or blocked run cannot be mistaken for a finished one.
The five split by the job in front of you: a question to answer, a single provision or ruling to status-check before it is relied on, client documents to work through before any conclusion is formed, someone else's draft to check, or a date-bounded sweep of what changed in a window. Every output is draft research for a CA or CPA to review. None of it is advice.
Australian accounting firms use Claude across the bounded, reconciled work that fills the year: year-end workpaper assembly tied to the trial balance, PAYG instalment plans and client letters, FBT workings on the year to 31 March, STP and super reconciliations on both sides of the Payday Super changeover, ATO correspondence triage, client questionnaires and chasers, AML/CTF onboarding support for the designated services that came into scope on 1 July 2026, and the GST classifications the ledger software does not finish before the BAS goes in. Airclerk designs and implements these as governed workflows, connected to the firm's ledger and practice systems, whether that is Xero, MYOB, Xero Practice Manager, FYI, Karbon, CCH iFirm or another stack, with engagement isolation between clients and a reviewer's sign-off on every output that leaves the building. For Xero we built the connection ourselves, because the ones that exist assume one business rather than a practice carrying hundreds of client organisations.
Airclerk's Australian Accounting Pack is the Australian answer to that question: 25 skills for public practice, covering year-end workpapers with capital allowances and the tax reconciliation, GST on the BAS, PAYG instalments, FBT, payroll with STP Phase 2 and super, ATO correspondence, reporting tiers under the AASB, ASIC and ACNC tests, AML/CTF onboarding, management accounts with a three-way forecast, franking accounts, Division 7A loan reviews, offshore holdings with CGT and foreign income tax offset workings, livestock and dairy clients, construction contracts with state trust-account checks, residential property triage and Australian tax research, each source-linked to the Federal Register of Legislation, ATO material, the AASB and APESB with retrieval dates. Anthropic's nearest release, Claude for Small Business, is written for a US business owner rather than a practice. The pack is built to the shape of public practice instead: engagement isolation between clients as a hard rule, every output naming its client, entity and period, rates and dates verified against the source when a skill runs rather than stated from memory, and a named reviewer gate before anything leaves the building. Eighteen skills carry a deliverable end to end. Five are tax research skills: all of them cite only sources the run actually opened, the substantive one routes a question by depth and argues against its own conclusion, and a figure that matters is handed to the skill that owns that deliverable, where a schedule has to tie to the ledger or state its difference. One runs the practice's monitoring of ATO, Federal Register, Treasury, court and state revenue sources, and one interviews the firm on the way in and writes the practice profile every other skill reads. The pack was built in September 2026 from Airclerk's New Zealand Accounting Pack, skill for skill, with Australian law written in rather than translated. No Australian firm has run it in production yet; the New Zealand pack it came from has. It is an accelerator rather than a product: it is where an implementation starts, and each firm's version diverges from there as skills are adapted to the firm's own workpapers, templates and risk settings.
No. Every output is a draft for the firm's own accountants to review, with sources cited, rates and dates carrying retrieval tags, and uncertainty flagged. The reviewing accountant takes professional responsibility for anything that leaves the building. The workflow is supervised like delegated work, with added AI-specific controls: schedules must tie to the ledger or state their reconciling difference, proposed tax positions carry their statutory basis, and consequential actions stop for human sign-off. Airclerk is an AI implementation consultancy, not an accounting firm and not a registered tax agent: nothing we build lodges with the ATO, operates Online services for agents or sends anything to a client except by the firm's own people. Where the firm's practitioners are registered tax agents, workflows are designed to support their obligations under the Code of Professional Conduct in section 30-10 of the Tax Agent Services Act 2009: honesty and integrity, independence, confidentiality and competence, together with the duties the Code of Professional Conduct Determination 2024 added, among them competence for work done on the practitioner's behalf, record-keeping and quality management. For members of CA ANZ and CPA Australia the same discipline supports APES 110, APES 220 on taxation services and APES 315 where the work is compilation.
Two protections come before anything else. Engagement isolation: one client's records are walled off from another client's work. Scoped access: the workflow reaches only the systems and clients the firm has connected and scoped for it. Before any client records are connected, we check the vendor terms: whether inputs are used for training, what is retained and for how long, who the subprocessors are, and where data goes offshore, where APP 8 may apply. Everything runs on the firm's own Claude instance, under the firm's own agreement with Anthropic; client records reach it through connections the firm approves and scopes, and nothing routes through Airclerk. Whether that arrangement is a use or a disclosure, and which of APP 6, APP 8 and APP 11 it engages, turns on who controls the information and on the actual terms, so we assess it rather than assume a provider processing on the firm's behalf settles the question. Tax file numbers are minimised and never put into a public search, whatever the firm's Privacy Act coverage, because the TFN Rule applies regardless. Some steps never move into the workflow at all: lodging returns or activity statements, taking final tax positions, moving client money, AML/CTF compliance-officer decisions and suspicious matter reports, and signing anything stay with the firm's own people. And where people at the firm are already pasting client figures into personal AI accounts, we treat that as the first thing to fix, not a fact of life: an engagement starts by finding where AI is already in use and moving that work onto governed rails.
The AI arriving inside Xero, MYOB and Karbon is genuinely useful, and it belongs to their platforms: it works where their product works, on their roadmap, in their shape. What we implement is different in kind. Claude runs on the firm's own instance and works across systems: the ledger, the practice manager, the document store and the email trail in one workflow, encoded with the firm's own review standards and templates. The ledger connection is our own build, and it treats the client list as the normal case rather than the exception. The firm controls its configured workflows and prompts, and keeps the record of what the AI did. For most practices the two are complements, and the honest comparison is platform features against a build the firm keeps.
Yes, through a Xero connection Airclerk built for public practice. The connections that already exist assume one business with one ledger; a practice has hundreds, and the failure mode is an invoice or payment landing in the wrong client's file. Ours selects a client by name, alias or enough of the name to be unambiguous, and refuses with the candidates listed rather than guessing when two clients match. Reads are open; every write has to name the organisation it is landing in. Xero caps the organisations one app can connect to by tier, and the connection runs more than one credential profile, so a practice is not held to a single app's cap. It runs on the firm's own machine, so Xero credentials and refresh tokens stay there rather than in a hosted middleman. Coverage is the whole published surface for Xero's Accounting and Assets APIs: 235 accounting operations across 31 route families and 6 fixed-asset operations, 241 in total, generated from a checksum-pinned copy of Xero's own specification. That includes manual journals end to end, twelve operations covering the journal itself, the supporting attachment and its history record, so a year-end adjusting entry can be drafted from the workpaper that computed it and posted once a reviewer approves. The Payroll AU API is not covered yet: the connection was built for New Zealand practices first and its payroll coverage is New Zealand's, so for an Australian firm the payroll review runs from STP submissions and payroll exports, and Payroll AU joins the connection when an Australian implementation needs it. Every create and update carries an idempotency key that holds across its own retries, so a dropped connection mid-write cannot leave a client with two of the same invoice. It is Airclerk's own tool, not a Xero product and not affiliated with or endorsed by Xero, and we install and configure it as part of an implementation.
They do different jobs, and Xero's is very good at the one it was built for. Its connector in Claude's directory is read-only by design, which Xero states plainly in its own listing, and its seven tools all return summaries: financial position, cash position, profit and loss, top customers by revenue, contacts and receivables, and the organisation's details and financial year. For an owner asking what their profit looks like this quarter, that is the right tool. Xero also publishes an open-source MCP server with write tools, invoices, contacts, payments and manual journals among them; it is built around one organisation's credentials at a time, and it does not pick a client by name out of a practice's list. Public practice needs two things it does not set out to offer. The first is depth: a year-end workpaper pack is built from a trial balance, aged receivables and payables and transaction-level listings of invoices, bank transactions and payments, and a summary figure will not reconcile to anything. The second is the ability to act, because a practice does not only ask questions about a ledger, it raises the invoice, records the payment, fixes the contact and posts the year-end journals. Ours covers 241 operations, every one Xero publishes for its Accounting and Assets APIs, so a workpaper pack can pull a trial balance and the fixed-asset register behind the capital allowances schedule. Writes name the organisation they land in, every time. It also picks a client by name out of the whole client list, which is a problem a tool built for one business has no reason to solve.
Yes, and the Xero connection is often the faster win in-house. The pack is written for public practice, which is why so much of this page talks about engagement isolation and reviewer gates, but most of the work underneath is the same: the BAS, FBT, STP and super, PAYG instalments, year-end preparation for your auditor or accountant, monthly management accounts with a rolling cash-flow forecast, and keeping up with ATO and AASB changes. The skills that assume a client list do not apply, AML/CTF client onboarding and client chasers among them, and engagement isolation becomes entity isolation instead. The connection needs no adaptation at all. A finance team gets the same 241 operations, which means month-end accruals, prepayments, depreciation and reclassifications posted as manual journals from the workpaper that computed them, the fixed-asset register behind the depreciation, aged receivables and payables, and the standard reports. If the group runs several entities in separate Xero organisations, the multi-organisation design does the same job it does in a practice: a consolidation journal landing in the wrong subsidiary is the same error as one landing in the wrong client, and the same guard stops it. What does not change in either setting is the review boundary. Outputs are drafts, and whoever signs the return or the accounts still signs them.
Because the pack is the easy part. What is left is the work that decides whether it sticks: drawing out the firm's own review standards and encoding them, connecting the ledger and practice systems with the right scopes, designing the reviewer gates, testing the workflow on held-out jobs before an accountant relies on it, and training people so adoption is deliberate rather than informal. A firm with engineering capacity can do this itself. Most firms would rather buy the weeks back, especially the weeks either side of 30 June and the run-up to 15 May.
A quality review samples engagement files and tests the firm's system of quality management: APES 320 for compilation, tax and advisory engagements, ASQM 1 where the firm does assurance work, and APES 110 over all of it. An AI-assisted file has to show a reviewer the same things any file shows. What the work relied on, what was checked, who reviewed it, who signed it off. That is the discipline the pack is built around: outputs are drafts for a reviewing accountant, rates and dates carry retrieval tags, and every schedule ties to the ledger or states its difference, so the file a reviewer samples reads the way a well-run file reads. The boundary is worth stating plainly. Airclerk does not make a file compliant; the firm's quality management system does that. Our work is making sure AI-assisted output leaves the evidence that system needs.
A free introductory conversation to qualify the fit: your systems, your client base, your year-end load. Then six weeks to year-end workpapers your partners can stand behind, at a fixed fee quoted in writing after that conversation.