Bank reconciliation and transaction categorization
Reads transactions from the firm's bank and credit card feeds, matches each one against the bookkeeping system's open items (open invoices, expected receipts, recorded bills), and categorizes the unmatched ones to the right GL account based on description, amount, vendor pattern, and historical categorization. Surfaces the small set of genuinely ambiguous transactions for a human to decide. Replaces the slow, manual back-and-forth between bank statements and the books that bookkeepers traditionally do, and shifts the work from data-entry to exception handling. Builds the categorization model from the firm's own historical books, not a generic chart.
Requirements describe capabilities the pattern needs in your environment, not the vendors you must buy. Any system that fills a requirement satisfies it — that’s what makes the catalog portable across the long tail of SMB tooling.
bank_transaction_feedThe stream of transactions from banking and card sources.
- bank feed integration to the accounting system
- card processor feed
- direct bank API connection
- scheduled CSV import from online banking
open_item_registerReceivables, payables, and other open items the bank transactions might match against.
- accounts receivable and accounts payable modules of the accounting system
- open items ledger
- expected receipts log maintained by treasury
categorization_historyThe firm's historical bookkeeping decisions, which the pattern learns from. Without this, categorization is generic and often wrong.
- complete transaction history in the bookkeeping system
- general ledger with descriptions and categorizations
- imported historical books from prior accounting platform
chart_of_accountsThe valid set of accounts the pattern can categorize into, with definitions.
- chart of accounts in the bookkeeping system
- structured account master maintained by the finance team
bookkeeping_write_destinationWhere matched and categorized transactions get recorded.
- bookkeeping system with API write access
- queue of approved entries the bookkeeper posts
- structured journal staged for bookkeeper review
ambiguity_review_queueWhere genuinely uncertain transactions go for human decision.
- review queue inside the accounting system
- weekly review session with the bookkeeper
- dedicated review UI built for the engagement
rule_definition_layerExplicit rules the pattern must always follow that override learned patterns: 'transactions over $X always need approval', 'transactions to vendor Y always go to project Z'.
- rules table maintained by the finance team
- small admin UI for rule authoring
- documented finance policies captured in build phase
- 01Pull new bank transactions on cadence (daily for most clients)
bank_transaction_feed - 02Try to match each transaction against open items by amount, counterparty, and expected date
open_item_register - 03For matches: stage the application against the open item
bookkeeping_write_destinationDECISION Strong match → propose; weak match → review. - 04For unmatched transactions, predict categorization using historical patterns and any applicable rules
categorization_historyrule_definition_layerchart_of_accounts - 05Score confidence per prediction; high-confidence get auto-categorized, low-confidence go to reviewDECISION Threshold tuned per client based on appetite.
- 06Write high-confidence entries to the bookkeeping destination
bookkeeping_write_destination - 07Queue ambiguous transactions for review with proposed options
ambiguity_review_queue - 08Capture reviewer decisions, write to bookkeeping, feed back to categorization history for learning
bookkeeping_write_destinationcategorization_history
Structured outputs this pattern produces. Other patterns and client systems can subscribe to them, which is how the catalog composes over time.
reconciliation_health_signalMatch rate, auto-categorization rate, review queue depth — the operational health of the books.
- finance dashboards
- month-end close tracking
- bookkeeper performance metrics
categorization_drift_signalCases where the firm's policies seem to be changing, surfaced for finance leadership.
- finance policy reviews
- audit prep
- controller workflows
vendor_emergence_signalNew counterparties appearing in transactions that aren't in the vendor master.
- vendor master maintenance
- procurement
- B2 CRM hygiene if applicable