The burden of proof is ours, not yours
No standard-setter has yet blessed AI-generated accounting entries. So scepticism is the correct default — if a system can't produce evidence, your only honest position is to treat everything it posted as unsupported. This page exists so you don't have to.
From inside Xero, you cannot tell which entries a human looked at
Xero records the user on every entry written through its API as System Generated. An entry a finance lead reviewed line by line and an entry posted unattended at three in the morning look completely identical.
That isn't a flaw in Xero — it was never designed to record who exercised what judgment. But it does mean any tool that posts automatically has to supply that layer itself. Otherwise it is weakening your evidence, not helping you.
Five things, per transaction, immutable
Inputs at transaction grain
A pointer to the specific file — an image or a PDF, with its content hash — not a summary of a batch. You can click from the trial balance back to the document itself.
Model and prompt version
Generative output is not reproducible, so "we used AI" is not evidence. We record which vendor, which model ID, which prompt version, which region, and how long it took.
Output, confidence and basis
Per-field confidence — not one overall score — plus the basis for the coding, e.g. "47 prior entries for this supplier, all consistent".
Reviewer, timestamp, changes
Who approved, when, what they were shown, and which fields they changed. A rubber-stamp approval shows as "no changes" rather than being hidden.
Immutable version history
Each decision record's hash includes the previous record's hash. Retroactive edits break the chain — no separate logging system needed to detect them.
The AI-posted entry list
At year end you can pull every unattended entry for the period, with its confidence, the gate conditions it satisfied, and the sampling record. That list is your basis for deciding whether to accept the workflow at all.
Automated does not mean unsupervised
- A two-condition gate. To post unattended an entry must satisfy model confidence and a set of checks that don't depend on the model at all — amount limit, supplier history depth, duplicate detection, period lock, policy checks. Any single failure routes it to a person.
- Permanent sampling. 10% of auto-posted entries are reviewed on an ongoing basis and the result written into the evidence log. If the sampled error rate exceeds the threshold, the gate tightens automatically. Not a one-off acceptance test — a continuing control.
- Period lock checked before writing. Xero exposes lock dates but provides no API to set them, so we maintain one locally and check it before every write — preventing any tool from quietly posting into a closed period.
- No edit function. Posted entries cannot be modified. Errors are reversed and re-posted, with both entries and the reason retained.
- Segregation of duties. Whoever submits cannot approve; whoever approves cannot change the policy thresholds. Enforced in code, not in a handbook.
What we do not do
Scalebook does not audit, does not express an opinion, and does not assess materiality for you. It also does not claim its output is accurate — it claims that every output carries enough information for you to judge its reliability yourself. That distinction matters to us.
What would you need
to accept a machine-posted entry?
The five items above are ours. We've read the discussion and looked at what others do, but no practising auditor has reviewed this and told us whether it is sufficient. That is the single biggest unknown in this product, and it matters more than any technical question.
We're looking for a few auditors practising in Hong Kong to look at the evidence structure and tell us directly: what's missing, what's insufficient, what's unnecessary. This is cheap to fix now and expensive to fix in a year.
Nothing to sign, and this isn't a sales conversation. If your conclusion is "I wouldn't accept this format", that is the most valuable sentence we could hear today.
We reply personally. No newsletter, no drip sequence — your address is used to talk to you about this and nothing else.