All the scenariosFinance and administrationBank Transaction CategorisationComplex
A whole year in one import, 613 rows
The situation
To close the 2025 financial year the firm uploads the whole year's camt extraction: 613 rows, one exported twice by the portal and five settled in dollars and sterling. A total computed across the whole file would mean nothing, and the job is long enough that it may end half-done.
The documents
The same files the agent was handed. Open them before you read the rest: the names, addresses and VAT numbers are invented, the structure is not.
What the agent does
The same four phases as every run, in order. In the console you watch them go by one at a time, with the credits beside them.
- 01DiagnoseReads the input and decides what the job actually is.
- 02AssemblePicks tools, data sources and the model you chose.
- 03ActDoes the work. Anything that leaves the building waits for approval.
- 04AssessChecks its output against your rules before settling credits.
The tools it used
Read off the recording of the run, not off a feature list.
- Import the bank statement
- Categorise the transactions
- Flag the anomalies
- Save the result
The result
Result being recorded
This scenario is ready, but its real run has not been recorded yet. Until it has, there is nothing to show here: we would rather print one honest line than a fake result.
What to look for
612 movements imported — the row the portal exported twice stays one — with twelve salaries, twelve rents and forty-eight receipts, as the year's months require. The notes say three currencies live in the file, so no overall total is a real number.