Phase 1 · Deterministic core

AI bookkeeping for
Australian accountants

Upload CSV or PDF bank statements. Automatically classify transactions, calculate GST, and prepare BAS-ready bookkeeping using explainable AI — grounded in ATO knowledge, not guesswork.

  • Built for Australia
  • ATO knowledge driven
  • Explainable AI
  • Audit ready
  • BAS workflow
processing pipeline
  1. 01

    CSV / PDF

    Bank statement

  2. 02

    Parser

    Rows normalised

  3. 03

    Merchant Recognition

    Fuzzy + prefix match

  4. 04

    Rule Engine

    Deterministic first

  5. 05

    ATO Knowledge

    GST codes · BAS labels

  6. 06

    GST Engine

    Gross ÷ 11 · half-up

  7. 07

    Confidence Engine

    High / review band

  8. 08

    Decision Trace

    Reason + evidence

  9. 09

    BAS Ready

    1A · 1B · export

    ready
Why BAS Flow AI

Built for professional bookkeepers

A layered engine that reaches for AI only when rules and knowledge can't decide — so you get higher accuracy at lower cost.

01

Rule Engine

Most bookkeeping tools hand everything to an LLM. BAS Flow AI applies deterministic accounting rules first — priority-ordered, versioned, and plugin-extensible.

02

ATO Knowledge Base

Official Australian GST treatments and BAS labels power every decision. GST is keyed on the account, not a model's guess — taxable, GST-free, and input-taxed handled correctly.

03

Learning Engine

Every correction a bookkeeper makes feeds back in. Merchant mappings and classifications improve future accuracy without retraining a black-box model.

04

Explainable AI

Every classification carries its reason, a confidence score, and a full decision trace. Nothing is opaque — audit-ready by design.

How it works

From bank statement to BAS-ready

Nine deterministic steps. Each one is inspectable, versioned, and logged.

  1. 01

    Upload statement

    Drop in a CSV or PDF bank statement. Rows are parsed and normalised into clean transactions.

  2. 02

    Normalise merchant

    Bank-feed noise like store numbers and cities is stripped, then matched against a merchant catalogue.

  3. 03

    Apply rules

    Priority-ordered, governance-aware rules classify the transaction to an account — deterministically.

  4. 04

    Consult ATO knowledge

    Each account is resolved against versioned ATO knowledge for its correct GST treatment and BAS label.

  5. 05

    Calculate GST

    The account's ATO GST treatment drives the calculation: gross ÷ 11, rounded half-up, mapped to 1A / 1B.

  6. 06

    Confidence review

    Each decision is scored into a confidence band, so low-certainty rows are flagged for a quick human check.

  7. 07

    Generate decision trace

    A full, append-only trace records the merchant match, rule hit, knowledge source, and reasoning.

  8. 08

    Record audit trail

    An append-only machine log captures every step, keyed by transaction, so the whole run stays reproducible.

  9. 09

    Export BAS-ready data

    Reconciled, labelled transactions export as JSON — ready for your BAS workflow and future Xero sync.

Features

Everything a bookkeeping engine needs

CSV Import

Structured bank exports

PDF Import

Scanned & digital statements

Merchant Recognition

Exact · prefix · fuzzy

GST Calculation

Account-driven, half-up

ATO Knowledge

Versioned GST & BAS codes

Learning Engine

Corrections improve accuracy

Audit Trail

Append-only machine log

Decision Trace

Reason + evidence per row

Confidence Scoring

High · review band

JSON Export

BAS-ready output

Rule Governance

Effective dates · entity scope

Xero Integration

soon

On the roadmap

Why our accuracy is higher

A pipeline, not a prompt

Generic AI tools pipe your statement straight into a language model and hope. We reach for AI only after rules and knowledge fall short.

Traditional AI

black box
CSV
LLM
Guess

BAS Flow AI

explainable
CSV
Parser
Merchant
Rule Engine
ATO Knowledge
Learning
AI (only when needed)
Confidence
Review
Output

AI when needed. Rules when possible. Always explainable.

Dashboard

See every decision, and why

Real product output — merchant, account, GST, confidence, and the reasoning behind each classification.

statement_2026_q1.csv128 rows
BAS ready
MerchantAccountGSTConfidenceReason
OFFICEWORKS
453Office Supplies
$4.55GST
HighRule match · merchant_key
BP CONNECT 1423 SYDNEY
449Motor Vehicle — Fuel
$8.18GST
HighPrefix match · fuel rule
WOOLWORTHS 2981
463Groceries & Basic Food
$0.00GST-FREE
HighAccount-driven · GST-free
ATO PAYMENT
820GST Payable
$0.00BAS-EXCL
HighKnowledge source · ATO
BANK FEE
404Bank Fees
$0.00INPUT-TAXED
HighInput-taxed financial supply
SP * NORTHSIDE CAFE
420Meals & Entertainment
$1.27GST
ReviewLow confidence · needs check
decision_traceWOOLWORTHS 2981
merchant_normalised: woolworthsrule_matched: grocery_foodknowledge: account 463 = GST-freefinal: $0.00 GST
98%+
Automatic classification
99%
GST accuracy
100%
Decision explainability

Indicative targets · to be replaced with live evaluation data

Security

Enterprise-grade security

Financial data deserves engineering discipline. Here's how we handle yours.

Local processing

Statements are parsed and classified within your environment — not shipped to a third-party model by default.

Encrypted storage

Data at rest is encrypted. Connections use direct, unpooled channels for sensitive operations.

Audit logs

An append-only machine log records every decision, keyed by transaction, for full traceability.

No training on your data

Your customers' financial data is never used to train models. Learning stays scoped to your workspace.

Privacy first

Built for Australian compliance expectations, with data handling designed around confidentiality.

Australian data residency

Your financial data stays onshore. Storage and processing are kept within Australian regions by default.

Pricing

Simple plans for every practice

Choose a plan and start automating your BAS bookkeeping today.

Starter

For solo bookkeepers getting started.

  • CSV import
  • Rule + GST engine
  • Decision trace
  • JSON export
Most popular

Professional

For busy bookkeepers running many clients.

  • Everything in Starter
  • PDF import
  • Learning engine
  • Confidence review queue

Accounting Firm

For firms needing scale and governance.

  • Everything in Professional
  • Team workspaces
  • Audit exports
  • Priority support
FAQ

Questions, answered

What banks are supported?

Any Australian bank that exports CSV statements works today. Bank-feed formatting — store numbers, city suffixes, and reference noise — is normalised automatically during merchant recognition.

Do you support PDF statements?

Yes. PDF bank statements are parsed into structured transactions, so you can process both digital and scanned exports without manual data entry.

How accurate is GST calculation?

GST is calculated deterministically from the account's ATO treatment — gross ÷ 11, rounded half-up to two decimals per line, and mapped to the correct BAS label (1A on sales, 1B on purchases). Taxable, GST-free, and input-taxed supplies are each handled correctly.

Can I review transactions before finalising?

Every transaction is scored into a confidence band. Low-confidence rows are flagged for a quick human check, so you stay in control while the engine handles the routine volume.

Can I export to Xero?

Today you can export BAS-ready data as JSON. Native Xero integration is on the roadmap.

How does the AI make decisions?

Rules and ATO knowledge decide first. AI is only invoked when deterministic logic can't classify a transaction — and even then, every decision carries a reason, confidence score, and full decision trace.

Is my data secure?

Statements are processed locally by default, data at rest is encrypted, and your financial data is never used to train models. An append-only audit log records every decision.

Our philosophy

AI when needed.Rules when possible.Always explainable.

Bookkeeping designed by engineers who understand accounting — built for the way Australian practices actually work.