- Home
- AI use cases
- Bookkeeping and filing
AI use case · built in Ledgerline
Books that keep themselves, with an accountant still signing
For a practice looking after many small companies, most of the month is moving numbers from one place to another. We built a ledger that takes the moving out, so the accountant's time goes on review and advice.
The problem
Every client sends their records differently: a spreadsheet one month, a shoebox of receipts the next. The practice re-keys them, chases what is missing and races the same deadlines every quarter: VAT, CT600 or CT1, CS01 or B1, payroll.
Errors creep in at the re-keying, and the audit trail is whoever remembers what changed.
How it works
Each step is done by whichever is right for it: a model where something has to be read or drafted, tested code where a rule applies, and a person where a decision is made.
- 01InputClient workbook and bank statementRe-uploaded each month, cumulative
- 02Rules in codeCompare and postAlready-posted lines skipped, new ones posted, changed ones shown side by side
- 03Rules in codeSuggest matchesBank lines to open invoices, existing postings or an account with VAT
- 04A personPreparer confirms, manager approvesOptional maker-checker per client
- 05OutputReturns and accountsVAT (MTD), CT computations, CS01 / B1 data, statutory PDFs
AI reads, plans or draftsTested code applies the rulesA person reviews and decides
Live today
What it already does
Labelled honestly: AI where a model does the work, Rules where tested code does.
- RulesMonthly uploads without double countingEach client's sales and purchases workbook re-uploaded every month; duplicates skipped, changes shown, corrections posted as reversals.
- RulesBank reconciliation with suggestionsStatement lines matched to open invoices, part payments allocated, and the statement agreed to the books and signed off.
- RulesDeadline calendar for every clientGenerated from each year end, VAT period and payroll for both the UK and Ireland, rolled forward daily.
- RulesReturns and statutory accountsUK MTD VAT submitted to HMRC over the API, Irish VAT3 and RTD, CT600 and CT1 computations, micro and small accounts as PDFs.
- RulesControls a reviewer can trustGapless entry numbers, posted entries that can only be reversed, lock dates, and a hash-chained audit trail with a verify button.
What AI adds next
Builds we can scope on the same foundations, each kept inside the same rules and the same review step.
Invoices and receipts read for you
PDFs, photos and forwarded emails read into coded lines with the right VAT treatment. The supplier's usual account is learned, and anything below a confidence threshold waits for a person.
Bank matching that learns
Remittance text read, one payment split across several invoices, and your past confirmations used to suggest the next ones, with the reason shown.
Anomaly watch
The same invoice under two numbers, a VAT rate unusual for that supplier, a cost line that has doubled, round-sum payments to new payees: each raised with the entries behind it.
Month-end commentary
Variance notes for the management accounts drafted from the ledger ("wages up 12% on two new hires from March"), for the accountant to edit.
Ask your books
A client or partner asks "why is VAT higher this quarter?" and gets an answer built from the actual postings, reviewed before it is sent.
Chasing agent
Two weeks before a deadline, the agent checks what is missing and emails the client a specific list of what is still needed. Replies with attachments are read straight into the file.
Cash forecast from the ledger
Thirteen weeks ahead, built from payment history plus the VAT, corporation tax and payroll dates already in the calendar.
Through the lens of your sector
The same build answers a different problem in each business. Pick yours.
- The problem
- Dozens of small clients, the same deadlines every quarter, and junior time spent typing rather than learning.
- Live today
- One ledger for every client, deadline calendar across the practice, maker-checker approval, statutory PDFs from the books.
- What AI adds next
- Receipts read on arrival, chasing agent before deadlines, and month-end commentary drafted for every client.
- Stays with a person
- Professional judgement, client advice and the signature on every return.
- The problem
- The owner does the books at night, the accountant sees them once a year, and cash surprises arrive with the VAT bill.
- Live today
- Clean monthly books, VAT done on time, and a cash flow statement tied to the bank.
- What AI adds next
- A thirteen-week cash forecast with tax dates in it, and plain-English answers about the numbers.
- Stays with a person
- Decisions about pricing, hiring and borrowing.
- The problem
- Daily takings across sites, card settlements a few days later, tips, supplier invoices by the hundred, and margins that move with every menu.
- Live today
- Bank lines matched to settlements and invoices; supplier workbooks uploaded without double counting.
- What AI adds next
- Supplier invoices read from photos, food and drink cost spikes flagged by supplier, and a weekly site P&L commentary.
- Stays with a person
- Menu, staffing and supplier negotiations.
- The problem
- One property company per building means many small sets of books, each with its own year end, VAT position and annual return.
- Live today
- Every company in one practice view, with deadlines and statutory accounts generated per company.
- What AI adds next
- Rent received matched to tenants automatically, service charge anomalies flagged, and lender covenant figures drafted from the books.
- Stays with a person
- Valuations, lender relationships and tenant decisions.
- The problem
- Payroll is most of the cost, local authority and HSE payments arrive late and in bulk, and the margin depends on rota efficiency.
- Live today
- PAYE and VAT deadlines on the calendar; bulk receipts allocated across the invoices they settle.
- What AI adds next
- Remittance advice read to split a single local authority payment across many invoices, and an alert when staff costs outgrow funded hours.
- Stays with a person
- Care decisions, staffing and conversations with commissioners.
- The problem
- Imports, postponed VAT, many suppliers and stock that ties up cash.
- Live today
- Reverse charge, EU and postponed import VAT handled in the ledger with evidence attached to each document.
- What AI adds next
- Import documents read to post postponed VAT correctly, and supplier price changes flagged against the last order.
- Stays with a person
- Sourcing, pricing and stock decisions.
Other AI use cases
Relationship intelligence
Screenshots read into a clean contact book, replies drafted inside guardrails, and every follow-up on time.
See the use caseWealth ProfilerClient onboarding and KYC
A household captured once, checked against KYC and AML rules, and turned into a balance sheet, risk profile and investment policy.
See the use caseManagewise WorkspaceOperations inbox and compliance
Every email tagged to the right building, replies drafted with that building's context, and every statutory deadline and arrears run in one place.
See the use caseFinance StudioFinance content studio
Record once; get edited, illustrated and captioned videos with sourced news cards, ready for every channel.
See the use caseWant your version of this?
Tell us how the work is done today. We will tell you which parts a model should do, which parts need rules around them, and what a pilot on your own data would look like.