An AI colleague for your accounting practice: repeat questions and documents
An accounting practice gets the same questions every month from different people: where do I submit this, what do you still need, has my return been filed. Nova absorbs those repeat questions, reminds clients of missing documents and files things in the right place. What it does not do is assess — that is your profession.
Published on
The problem in this sector
Filing peak: clients email 4× a week "is my filing in yet?" No time to call everyone.
| Aspect | For this sector |
|---|---|
| Channels | E-mail · WhatsApp |
| Own knowledge | Each client gets their own files and statuses, strictly separated |
| Volume per day | 600 messages (100/hour) |
| Expected outcome | Client sees the status right away, instead of waiting 2 days. Accountant calls only on real questions. |
That table is an example configuration, not a measured average. We do not yet have clients in production, so there are no field figures to show — and invented figures are worse than none. What it shows is the setup we would propose for this type of business, with the volumes that go with it.
Where the limit sits
Here a constraint applies that other sectors do not have: the statutory tax retention obligation. The Dutch Tax Administration states that the retention period only begins once a record's current value lapses — not on the invoice date. An AI that clears out on the basis of age is therefore structurally wrong. Nova does not clear anything from the administration; it processes messages, and those have their own, shorter retention.
Concretely, these are the things Nova does not do on its own here:
- Giving tax advice or classifying an entry; it flags what is missing, you determine what it is.
- Deleting documents from the administration — the retention period hangs on current value, not age.
- Filing or approving a tax return, not even when everything appears complete.
That limit does not live in a setting someone can flip by accident; it is established up front. That is the difference between a system you know the behaviour of and one you find out about afterwards.
The general rules on automated decision-making and transparency are set out in AI and the GDPR for SMEs and the AI Act for SMEs.
How it starts
It starts with a fifteen-minute intake call where we look at which work recurs in your case and lends itself to being taken over. We then analyse your existing communication from the past 90 days, so Nova learns your tone rather than a generic one. A shadow week follows in which it prepares drafts for you to review — only once that is right does it start sending on its own.
That shadow week is not a formality. It is the moment where it becomes visible which work the AI genuinely handles and which work should stay with a human — and that differs more per business than per sector.