AI capability

Ask your business a question

Not a chatbot bolted to a sidebar. A read-only interface to the business graph that answers in numbers, shows the transactions behind them, and declines when it cannot answer — which is the property that makes the other answers worth anything.

Rows
DeliverySalesG&A
New York$412K$286K$104K
Austin$238K$141K$62K
Remote$176K$88K$39K
Every dimension is on the journal line, so any combination is a query rather than a rebuild.
Read-only, alwaysScoped to your permissionsAnswers cite transactions

What it does

Six things, specifically.

Answer in plain language

Why did gross margin fall in the Austin office last quarter. Which vendors did we pay more than $50,000 to this year. What is our largest unbilled project.

Show its working

Every answer arrives with the transactions, accounts, and filters behind it. You can open the underlying records rather than take the number on trust.

Respect your permissions

It answers within the asker’s scope. A department head asking about company-wide payroll gets a refusal, not a redacted guess.

Compare and decompose

Period over period, entity against entity, budget against actual — with the movement broken into contributing parts rather than reported as a delta.

Hand off cleanly

Any answer becomes a saved view, a scheduled report, or an export. The conversation is a way to build a report, not a replacement for having one.

Say when it does not know

If the data does not support an answer — the dimension was never captured, the period is not closed — it says so instead of producing a confident approximation.

Why most ERP chat is disappointing

The common implementation puts a language model in front of a reporting API and lets it summarise. It demos well and disappoints in week two, for a specific reason: the model can reach the reports somebody already built, so it can only answer questions somebody already anticipated. Ask something slightly off that path and it either fails or, worse, produces a plausible number from the wrong report.

Because this one queries the business graph directly rather than a fixed report catalogue, the question does not have to have been anticipated. Margin by service line, by office, for clients acquired in the last eighteen months is a query rather than a feature request.

A copilot over a report catalogue can only answer questions somebody already thought of. That is not a language problem, it is a data-model problem.

Refusal is a feature

The failure mode that damages trust is not an unanswered question. It is a confidently wrong number that looks right, gets pasted into a board deck, and is contradicted three weeks later by the actual close.

So the copilot is tuned to decline rather than approximate. If a period is not closed, it says the figures are provisional. If a dimension was never captured, it explains that rather than deriving something adjacent. If the question is ambiguous, it asks which of two readings you meant. Every one of those is less impressive in a demo and more useful on a Tuesday.

Permissions are not a filter applied afterwards

Answers are computed within the asker’s scope in the data layer, not generated broadly and then redacted. That distinction matters: a system that computes a company-wide figure and then hides part of it has still leaked the aggregate, which is frequently the sensitive part.

Limits

Where it does not help.

Every capability page on this site carries one of these, because a feature described without its boundaries is a claim rather than a description.

It is not a forecast

It answers about what is recorded. Forward-looking questions route to the CFO agent, which models explicitly rather than extrapolating conversationally.

It cannot change anything

Read-only at every authority level. Asking it to post, adjust, or approve returns a refusal and a link to the thing that can, under proper controls.

It cannot invent dimensions

If payroll arrived as one lump entry with no department, no phrasing of the question produces department-level labour cost. It will tell you that is why.

Questions

What people ask.

Can it write to the ledger?
No, at any authority level. It is read-only by construction. Asking it to post or adjust returns a refusal with a link to the workflow that does that under proper controls.
Does it see data the asker cannot?
No. Queries carry the asker’s scope and are enforced in the data layer, so an out-of-scope question is refused rather than answered and redacted.
What if it gets an answer wrong?
Every answer carries the transactions behind it, so a wrong answer is checkable in seconds rather than discovered a month later. Where confidence is low it says so rather than presenting the figure flatly.
Does it work before we move our ledger?
Yes. It queries the business graph, which reads your existing accounting system, CRM, payroll, and the rest.
Can answers become reports?
Yes — save as a view, schedule it, or export it. Most customers use the conversation to discover the report they wanted and then pin it.

Ask it why margin moved.

Two periods of data and one real question is enough to judge whether the answers hold up.