Try it Product Vision Security Book a demo
For Australian audit firms

Audit testing,
automated.

Less ticking. More thinking.

Sample, vouch, quantify, project — the substantive testing that eats your busy season, run end to end. The same procedures, the same standards. On a live pilot engagement, Kritos checked all 65 sampled transactions against their invoices and bank evidence in about three minutes. Your judgement, not your time.

Book a demo → Try it live
✓ Live pilot running now with a mid-tier Australian accounting firm
✓ Built by Ishwar Chugh, CA, a practising auditor
On a live pilot engagement
65sampled
transactions
→
~3minutes
to check
  • ✓End to end — sample to signed workpaper, in one run
  • ✓Built to the standards — ASA 530 sampling, ASA 450 documentation
  • ✓Built by a practising auditor — every step reflects real audit judgement
Checked against invoices and bank evidence. Measured on production, 6 October 2026; review time not included.
ASA 530 / 450 methodology Hosted in Australia · Azure Never used to train AI Built by a Chartered Accountant
Still done by hand

Most of an audit is still manual. Tools automate slices of it — sampling here, document extraction there — but none of them runs substantive testing end to end. So the sampling and the vouching still happen by hand, in the weeks when deadlines are tightest.

  • Senior time goes to ticking. Chargeable hours absorbed by repetitive testing, not analysis.
  • The work is scattered. Spreadsheets, extraction tools and manual checks, re‑keyed at every step.
  • Graduates learn ticking, not judgement. Early years on repetition, not the judgement that builds a career.
Try it — no login

Substantive testing, live.

Set performance materiality and run the procedure. Kritos derives the sample, matches each document, computes the variances and projects the result. Amend anything and the numbers recompute.

$14.2M
// revenue population · 240 transactions
Performance materiality $240,000
$200k$600k
$80,000
Sampling interval
113
MUS sample
12
Target tested · 100%
Sample derived per ASA 530 (confidence factor 3.0). The clearly-trivial threshold of $5,000 is an auditor input, never a percentage of materiality.
Workpaper — Substantive Testing Ready
#GL (ex GST)InvoiceVarianceResult
Set materiality, then run the procedure.
What Kritos does

From population to workpaper, in one pass.

One workflow, not four tools stitched together. Step through it:

ASA 530 · Audit Sampling

Monetary-unit sampling, derived in full

Confidence factor, risk assessment, target testing, residual population — documented so that a reviewer can re-perform the derivation without asking how the sample was drawn.

selected at interval
$850,000
$425,000
$680,000
$312,400
interval $93,333 · high-value items 100% examined
Occurrence · Accuracy

Every item vouched to its document

Every sampled item vouched to its invoice — number, amount, date, currency — with the evidence on the page, so that you check extractions rather than key them.

GL · INV-2025-0418$312,400
⇅ matched on number + amount
Invoice · INV-2025-0418$309,950
✓ evidence captured · original preserved
ASA 530 · Projection · ASA 450 accumulation

Variance computed and extrapolated

Variances computed and projected over the residual population; the projected total is judged against your clearly-trivial threshold and performance materiality. Kritos accumulates and projects; you evaluate and conclude — so that the schedule is ready, not built from scratch.

✓ within $0.02 → Pass
! any other difference → Exception — Amount variance, open until you conclude
■ the projected total → against clearly-trivial and PM
Projected misstatement$215,000
Audit-ready output

Review-ready, not a starting point

Derivation, results, exceptions and extrapolation, assembled into a workpaper your reviewer signs — so that the export is the deliverable, not a draft you rebuild in Excel.

Workpaper — one Excel file
Audit parameters✓
MUS sample · testing results✓
Variance extrapolation✓
✓ exported · ready for your audit file
Your firm’s numbers

What it’s worth to your firm.

Enter your own numbers. The result is your estimate.

—
hours your team spends on revenue testing a yearhours × engagements
—
their value at your charge-out ratehours × engagements × rate

Your estimate, from your numbers. This is the time and value at stake — not a promise of what Kritos saves.

Why existing tools fall short

Plenty of tools. None go end to end.

Firms already own pieces of this. Each tool does one step and hands the work back.

Tool categoryWhat it doesWhy firms stop short
Analytics & sampling suites
Sampling and data analytics
Complex, costly per seat, heavy training — too cumbersome for everyday testing.
PDF extraction tools
Pull document data into Excel
Begin at extraction — no sampling, no methodology, no matching.
In‑Excel matching add‑ins
Match documents inside Excel
Excel‑dependent; no sampling engine, no methodology layer.
Manual Excel (MUS)
Auditor‑built sampling model
No AI, manual entry throughout, no document processing, high error risk.
Kritos
Sampling → extraction → matching → projection → workpaper
One workflow, end to end — built to ASA 530 and ASA 450.
Where this goes

It doesn’t stop at revenue.

Two cycles run today. The same engine extends across the file, so this doesn’t stay a one-cycle tool sitting beside everything you still do by hand.

RevenueLive
ExpensesLive
Trade creditorsPlanned
AccrualsPlanned
Fixed assetsPlanned
Inventory & COGSPlanned
CashPlanned
BorrowingsPlanned
EquityPlanned
Live today In development On the roadmap
Before your risk partner asks

The questions procurement gets to first.

InsuredProfessional indemnity and cyber insurance in place.
Data processing agreementAvailable on request.
Hosted in AustraliaMicrosoft Azure, Australia East. Your data is stored only in Australia.
Tenant isolationEach firm’s accounts are isolated, and a test run opens only for the auditor who started it.
Document processingDocuments are read by Microsoft’s Azure OpenAI service under Microsoft’s enterprise data protections. Your data is stored only in Australia, and is never used to train AI models. AI reading may use Microsoft capacity outside Australia.
Questions auditors ask

Straight answers.

No. Kritos performs the mechanical work — sampling, vouching, computing variances — and drafts a conclusion. You make every determination, amend anything you disagree with, and sign off. The judgment, and the conclusion, stay yours.

Then you see it, and you correct it. Kritos compares the amount it reads from each invoice with your ledger, so a misread shows up as a variance for you to check, and you can open each document from its row to see what Kritos read. You can amend the figures it read; the variance and the conclusion recompute, and the workpaper keeps both: what the AI read and what you decided. A document Kritos cannot read is listed as not extracted, and a bank transaction that only nearly matches is shown to you, not used.

Sampling and the projection of sample misstatements follow ASA 530. Misstatements are accumulated against your clearly-trivial threshold and documented as ASA 450 requires. Evaluating uncorrected misstatements, communicating them, and concluding remain yours. Not a US framework relabelled.

Your data is stored only in Australia, on Microsoft Azure (Australia East); the database sits on a private network. Every sign-in requires multi-factor authentication, each firm’s accounts are isolated, and a test run can only be opened by the auditor who started it. Documents are read by Microsoft’s Azure OpenAI service under Microsoft’s enterprise data protections. AI reading may use Microsoft capacity outside Australia, and nothing is ever used to train AI models.

No — and it matters to be clear about that. Kritos tests occurrence and accuracy by vouching recorded items to their source documents. Completeness — the search for unrecorded items — remains your separate procedure. Kritos doesn’t claim to do everything.

You are. Kritos assembles the evidence and a draft conclusion; the auditor reviews it, applies judgment, and signs. Kritos is a tool that does the tracing — it is not a signer.

A general ledger listing for the period (CSV or Excel), and the settings you already have for the engagement — performance materiality, your risk assessments, the period dates and the accounts to test. Kritos draws the sample; you then upload the sampled invoices (PDF), the bank statements (PDF, CSV or Excel) and any remittance advices. There is nothing to install: Kritos runs in the browser, and each auditor signs in with an authenticator app. We set the pilot up with you on one of your engagements.

Pricing on request — hello@kritos.com.au.

There isn’t one hiding in the methodology — it’s the same procedures, traced and documented faster. On a live pilot engagement, Kritos checked 65 sampled transactions in about three minutes; the review is still yours.

The founder
Ishwar Chugh, CA — founder of Kritos
Built by Ishwar Chugh, CA.

I did substantive testing by hand every busy season while everything around it got automated. So I built the part that hadn’t been. The work Kritos takes over is the work nobody trained for — opening invoice after invoice, keying amounts into a spreadsheet, chasing a variance that turns out to be a rounding difference.

Assistant Audit Manager in Melbourne. Chartered Accountant (CAANZ). Master of Management in Accounting and Finance, University of Melbourne. Statutory audit across two Australian firms, graduate to assistant manager.

“Every workflow decision in Kritos was made by someone who has done the work, supervised it, and signed it off.”

How a pilot works

From first look to live workpaper.

Low commitment, high signal.

1STEP 01

See it live

A walkthrough on representative engagement data. No setup required.

2STEP 02

Run a pilot

Kritos on one of your real engagements — your data, your materiality, your review. Supported the whole way.

3STEP 03

Keep the workpaper

A review-ready workpaper out the other side. Your conclusion, your sign-off. Judge it on the output.

Book a demo

See it run.

Sampling to signed workpaper, on representative engagement data. You watch the procedure execute, not a slide deck.

  • 01The sample, derived. Confidence factor, target testing, residual population.
  • 02Documents read and matched. Every figure traced to its invoice.
  • 03The workpaper you'd sign. Variances, exceptions, extrapolation.

Want to judge the output first? Download a sample workpaper (.xlsx)

Pick a time
Duration30 minutes
WhereMicrosoft Teams
To prepareNothing
Your dataNot required
Open the calendar →

Opens in a new tab. Prefer email? hello@kritos.com.au