Spreadsheet cleanup
Every company runs on spreadsheets that three systems export differently. Cleaning them is mechanical, repetitive, and exactly what an agent should do, as long as every change is listed rather than applied invisibly.
The job on one screen
| Runs when | A file is dropped in the intake folder. |
|---|---|
| Reads | The file, the target schema, and the rules for dates, currencies, and names. |
| Decides | What each column is, how to normalize it, and which rows cannot be saved. |
| Produces | A clean file, a change log, and a rejects file with reasons. |
| Stops when | Clean file written. The rejects always go to a person. |
| Tools it needs | File parser, schema definition, storage. |
| Autonomy to start at | Approve. It does the work and stops before the irreversible step. |
Optional: load a real model
Run it
The fields it pulls
Required fields are never guessed. If one is missing the run stops and a person gets the document, which is the difference between an extraction agent and a wrong database row.
| Field | Required | How it is found |
|---|---|---|
| Supplier | yes | ^\s*([A-Za-z][\w&.\- ]+?)\s*[;,] |
| Date | yes | (\d{1,2}/\d{1,2}/\d{4}|\d{4}-\d{2}-\d{2}) |
| Amount | yes | ([A-Z]{3}\s?[\d,]+\.?\d{0,2}) |
| Terms | optional | \b(net-?\d+)\b |
| Reference | optional | \b([A-Z]{2}-?\d{3,})\b |
Where this one goes wrong
Ambiguous dates
03/04/2026 is two different dates depending on the country of the person who typed it. Never guess: require the source's format or reject the row.
Silent rounding
Currency conversion inside a cleanup step introduces errors nobody can trace. Keep the original column.
Fuzzy name merging
Acme Ltd and Acme Limited are probably the same. Probably is not good enough for a payment run.
How you would know it is working
| Measure | Why that one |
|---|---|
| Rows requiring manual fixing | The number to drive down, and the honest measure of the rules. |
| Silent corrections | Should be zero. Every change is in the log or it did not happen. |
| Rejects that were actually fine | Too many and your rules are stricter than reality. |
Earning more rope
| Assist | Produce the clean file next to the original for comparison. |
| Approve | Write the clean file into the pipeline with the change log attached. Right level. |
| Auto | Fully automatic for a source whose format you control, never for one that arrives by email. |
Related: Document extraction · CRM hygiene · Invoice matching · all agent jobs · Agent Lab home
Free from AI School - no signup, everything runs in your browser.