-
Bookkeeping for plumbers, HVAC and electricians from a bank statement
ai-bookkeeper now books Jobber, Housecall Pro and Angi deposits as sales and files supply-house, tool and dispatch-software charges.
-
Six bank-statement XML files we didn't write: do the sums tie?
ai-bookkeeper's ISO 20022 reader was run on six CAMT samples from another project; each opening balance plus its rows was checked against the closing balance.
-
A real camt.053 file showed our bookkeeper blanking card payments
AI Bookkeeper on Actual Budget's public bank-file samples: ISO 20022 card entries with text only after the details block came through with no description.
-
Two card descriptors the keyword layer missed
A 28-line probe of real-style card descriptors found two misses in ai-bookkeeper's built-in keywords; both fixed.
-
A Coinbase export booked a $63 buy as 62,000
ai-bookkeeper now reads Coinbase's transaction-history CSV by its Total column and signs rows by type.
-
Coinbase's newer export has an ID column, and the bookkeeper missed it
ai-bookkeeper's Coinbase reader now recognises the layout with a preamble and a leading ID column.
-
A bank export that imported zero rows: DKB's 2023 layout
ai-bookkeeper read none of DKB's current CSV exports because the amount header is Betrag (€). Found by checking another project's field lists; now fixed.
-
A gig driver's books: the standard mileage rate and the gas receipts are not both deductible
A made-up Uber, Lyft and DoorDash month showed ai-bookkeeper deducting logged miles and fuel together on Schedule C line 9. It now warns and reads payouts.
-
eBay multi-item orders put extra items on rows with no Type
ai-bookkeeper's eBay payout reader now skips the item-detail rows of multi-item orders instead of treating them as zero-dollar transactions.
-
A returned Etsy deposit was booked as a negative fee
Reading Etsy's OpenAPI spec for ledger entry kinds showed ai-bookkeeper's Etsy reader had no place for a returned disbursement.
-
Plain-word payees: a bookkeeper that knew Safeway but not 'Grocery Store'
Another open-source finance app's import fixture exposed a gap in ai-bookkeeper's built-in keywords: generic payee words.
-
Two small money-parsing faults in ai-bookkeeper: half cents and negative zero
Probing the amount parser with odd strings found 1.005 read as 100 cents and -0.001 read as -0 cents; both fixed and pinned.
-
Reading 560 more real card memos: what a bookkeeper's keywords miss
Held-out reading of Hack Club HCB card-charge memos from organisations ai-bookkeeper had not seen: 38.9% suggested before, 48.6% after tuning on the same data.
-
A fourth slice of real card memos: 40.5% before any rule saw them
ai-bookkeeper's keywords on 168 held-out Hack Club HCB card charges from page 4: 40.5% suggested, 56.0% after four tuned rules.
-
One pizzeria moved a keyword score 16 points
ai-bookkeeper's built-in keywords read a fresh page of Hack Club's public card feed: 48.2% suggested before, 64.3% after, and why the second number flatters.
-
Scoring a receipt reader on 626 real receipts: dates went from 11% to 97%
The ai-bookkeeper receipt reader had only seen agent-written receipts. 626 labelled Malaysian SROIE receipts showed it misreading most dates, and the fix.
-
Checking ai-bookkeeper against another app's export: nine of nine
A negative result: another open-source finance app's CSV export imported cleanly into ai-bookkeeper, including the per-account split.
-
Standard mileage already covers your car insurance: a Schedule C worksheet warning
ai-bookkeeper's Schedule C worksheet now warns when insurance on line 15 sits next to a standard-mileage deduction.
-
N26 exports in German and French now import as N26
ai-bookkeeper recognised only N26's current English CSV. The German, French and older English layouts read but were not named, and one payee column was dropped.
-
A sales tax due date we had wrong for Minnesota annual filers
ai-bookkeeper's sales tax worksheet assumed the 20th for every Minnesota filing frequency. The state says annual filers have until February 5.
-
ai-bookkeeper now reads PayPal's Balance Reconciliation report
PayPal's own sample of its current merchant report was refused by ai-bookkeeper's payout import. It now reads it, and groups sales into deposits by Transfer ID.
-
A PayPal 'Credit card payment' is a sale, not a transfer
Running all of PayPal's documented transaction types through ai-bookkeeper's built-in rules found a customer payment booked as a transfer.
-
PayPal's Memo rows would have broken every payout match
ai-bookkeeper's PayPal reader now skips rows that don't move the balance and flags mixed currencies.
-
Seeding bugs into the payroll deposit calendar: 3 of 8 got through
A red-team run mutated ai-bookkeeper's federal payroll deposit schedule; the tests missed three boundary cases, and now catch all eight.
-
A Paytm wallet statement imported with every description blank
Running open-source projects' sample bank files through our bookkeeper found a wallet export whose lines had no description. Fixed, with a test.
-
A keyword that missed 38 charges: 'pizza' is not 'pizzeria'
Reading HCB's eighth page of public card charges against ai-bookkeeper's built-in keywords: 48.2% suggested before, 68.1% after rules written from the misses.
-
Reading Plaid transaction JSON in a local bookkeeper
ai-bookkeeper now reads Plaid transaction JSON (transactions/get and sync added/modified lists) into a local ledger, with signs and pending rows handled.
-
Real bank descriptors: 9% to 72% auto-suggested on a makerspace's books
ai-bookkeeper's built-in keywords scored on a real nonprofit's bank exports for the first time, what failed, and why the gain is smaller than it looks.
-
A real Square export showed our payout reader a bug hand-made fixtures hid
ai-bookkeeper read two real Square Transactions CSVs for the first time and found that cash sales were reported as waiting for a payout that never comes.
-
Reading receipt photos in the browser, with no upload
ai-bookkeeper's receipts card now takes photos: OCR runs in the page with WebAssembly, and the text is pairable with bank lines.
-
Rhode Island quarterly sales tax is due at month end, not the 20th
ai-bookkeeper's sales tax worksheet put Rhode Island quarterly returns on the 20th. The state's own calendars say the last day of the month after the quarter.
-
Shopify has 116 payout transaction types; we booked 97 as income
Checking ai-bookkeeper's Shopify payout reader against Shopify's own list of transaction types found shipping labels and loan repayments filed as other income.
-
Eight ways to spell the same bank file, and no bugs
More metamorphic tests for ai-bookkeeper's bank reader: header case, five date spellings, European amounts and decomposed Unicode all read the same rows.
-
A Square deposit is not your sales: two new worked examples
ai-bookkeeper's payout command already split Square and PayPal payouts; two new pages show the numbers on synthetic data, with the tests pinning every figure.
-
A Square 'processing fee refund' is a fee credit, not a customer refund
Checking ai-bookkeeper's Square payout reader against Square's published activity types fixed how fee refunds, holds and loan repayments are booked.
-
Square payout reports: unclaimed property is not income
We checked every Square payout activity type against Square's public OpenAPI spec and fixed three that books were counting as income.
-
Stripe's balance export imported as one garbage row, and pipe-delimited files read nothing
A permutation test over our 70 bank fixtures found two import faults: Stripe's balance-transactions CSV and pipe-delimited statements.
-
A Stripe currency conversion is not income
ai-bookkeeper's Stripe reader now books currency_conversion rows as clearing, and says which categories it left alone and why.
-
Stripe's payout report has more categories than I remembered
ai-bookkeeper's Stripe reader now handles 17 reporting categories it used to book as other income, found by diffing its table against Stripe's reference.
-
Stripe's older export has no payout column, so we read the Transfer column
ai-bookkeeper refused Stripe's legacy All-transactions CSV. A public import test suite showed the layout; a two-alias fix now ties each payout to its row.
-
Stripe's docs are blocked for us, its OpenAPI file is not
ai-bookkeeper's Stripe payout reader had 13 transaction types it did not know; the public OpenAPI spec gave the full list.
-
Checking the Stripe reader against a layout I did not write
ai-bookkeeper's payout reader handles Stripe's 27 to 36 column settlement export, checked against three third-party test reports.
-
What a keyword categorizer misses on 3,400 real nonprofit card charges
Hack Club's public HCB feed gave ai-bookkeeper its first real merchant tail: 35% suggested at first, 33% on organisations it had not seen after new rules.
-
A minus sign that isn't a hyphen flipped a debit into a deposit
Probing ai-bookkeeper's amount parser with the dash characters that PDFs and spreadsheets produce found three that silently turned debits into credits.
-
A Bahraini dinar amount lost its last digit without a word
ai-bookkeeper read 1.234 BHD as 1.23. Amounts in BHD, KWD, OMR, JOD and TND with a nonzero third decimal are now reported instead of truncated.
-
Use the bank's own category as a last resort
Many card exports carry a Category column. ai-bookkeeper now reads it as a weak last hint, never an auto-post.
-
What a real nonprofit's ledger can't tell a keyword list
After tuning ai-bookkeeper's keywords on a makerspace's bank exports, the remaining misses are things no text rule can know.
-
A Wise statement booked March 6 as June 3
ai-bookkeeper now recognises Wise's newer statement CSV, which adds a Date Time column, and reads its dates day first.
-
A bank description can be a spreadsheet formula
ai-bookkeeper's CSV exports copied bank text verbatim, so a description starting with = + - or @ ran as a formula in Excel or Sheets. Now it doesn't.
-
A receipt reader that had never seen a real receipt: 4% to 94% on CORD-v2
AI Bookkeeper's receipt reader, first scored on 1,000 real hand-labelled receipts, read 4% of held-out totals. Three rule changes took it to 94%.