1. Home
  2. AI use cases
  3. 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.

  1. 01InputClient workbook and bank statementRe-uploaded each month, cumulative
  2. 02Rules in codeCompare and postAlready-posted lines skipped, new ones posted, changed ones shown side by side
  3. 03Rules in codeSuggest matchesBank lines to open invoices, existing postings or an account with VAT
  4. 04A personPreparer confirms, manager approvesOptional maker-checker per client
  5. 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.

  • Rules
    Monthly uploads without double countingEach client's sales and purchases workbook re-uploaded every month; duplicates skipped, changes shown, corrections posted as reversals.
  • Rules
    Bank reconciliation with suggestionsStatement lines matched to open invoices, part payments allocated, and the statement agreed to the books and signed off.
  • Rules
    Deadline calendar for every clientGenerated from each year end, VAT period and payroll for both the UK and Ireland, rolled forward daily.
  • Rules
    Returns 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.
  • Rules
    Controls 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.

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.

Want 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.

Get a quote