Data Sorting & Context Engine

Upload any financial data.
QuirkBot knows what it is.

QuirkBot automatically recognizes your file's source system, parses it with purpose-built logic, and injects domain-specific context into its 80-dimension AI risk pipeline — so every engine scores smarter from the first row.

10
Live Modules
80-D
Risk Vector
26
AI Engines
3
Regions

How automatic sorting works

A five-stage pipeline turns a raw upload into a context-rich, risk-scored dataset — no manual mapping required.

STAGE 1

Fingerprint

Headers, sample values, delimiters, currency, date formats and software watermarks are extracted.

STAGE 2

Match

Every module scores the fingerprint. The most confident, most specific module wins.

STAGE 3

Parse

Source-specific logic normalizes dates, signs amounts correctly and preserves the original row.

STAGE 4

Context

Tax rules, chart-of-accounts and domain risk flags are injected for the 26 engines to read.

STAGE 5

Score

The 80-dimension pipeline produces a risk score, decision and explainable factors.

Supported data sources

Production-ready modules, each with bespoke detection, parsing and risk context. More are added every release.

Context is what makes it intelligent

QuirkBot doesn't just map columns. Each module teaches the AI engines how to think about your data.

🏦

Jurisdiction-aware thresholds

FICA R25,000 for South Africa, CTR $10,000 for the US, SAR £10,000 for the UK — applied automatically per source.

📊

Chart-of-accounts knowledge

Sage, QuickBooks and trial-balance modules understand account groupings, suspense accounts and normal balances.

🔍

Domain risk rules

Ghost-employee checks for payroll, void/discount abuse for POS, structuring detection for banking — built in.

💱

Correct amount handling

Debit/Credit, Money In/Out, bracket-negatives and currency symbols are all signed correctly, every time.

📅

Locale date parsing

dd/mm/yyyy vs mm/dd/yyyy is disambiguated from the data and the source region — no more swapped days and months.

Confidence & confirmation

High-confidence sources are auto-selected; ambiguous ones ask you to confirm, and learn from your choice.

On the roadmap

Coming to QuirkBot in upcoming releases.

📗Xero
🏢SAP
🔶Oracle Financials
🍃FreshBooks
🇦🇺MYOB
🌊Wave
🛡️Insurance Claims
📋Audit Working Papers
🧾Tax Returns (VAT201 / VAT100)

Bring your own data. We'll handle the rest.

Export from your bank, accounting package or ERP and drop it into QuirkBot. Classification, parsing and risk scoring happen automatically.

Start Analyzing →