Skip to content

Platform

Nothing ships until a number can be trusted.

Every figure your team sees has already been checked, cross-referenced against the rest of the document, and traced back to exactly where it came from. If a number cannot be backed up, it does not reach a reviewer’s desk.

The work is split on purpose.

Reading a document and drafting language is one kind of task. Arithmetic is another. We keep them separate: every number is computed the same way, every time, and checked against the rest of the document before your team ever sees it. That separation is not a policy layered on afterwards — it is how the system is built.

What gets checked before a number reaches you

Arithmetic consistency, cross-document agreement, matching labels and periods, correct signs, consistent units — the kinds of error that slip past a simple check because, taken on its own, every individual figure looks correct.

  1. 01AI

    Extract

    A vision-language model reads the document and returns labelled fields, each with a page reference. It transcribes. It does not calculate.

  2. 02Deterministic code

    Validate

    Does the arithmetic hold. Do the derived figures agree with the underlying records they claim to summarise. Are the labels consistent across every table. Failures are raised here, before a human reads a draft.

  3. 03Deterministic code

    Compute

    Every total, ratio and variance is computed in typed code from validated inputs. Same inputs, same outputs, every time, with or without a model provider.

  4. 04AI

    Narrate

    The model writes commentary from figures that already exist. Its output is checked against the computed set; any figure that does not match a computed value is rejected before the draft is shown.

  5. 05Human

    Approve

    A named user approves. The approval records who, when, which draft and which engine version. Until then, nothing leaves the platform.

Nothing leaves without a name attached

Every release — a reconciliation, a statement review, or any workstream we add after them — passes through approval by someone on your team before it goes anywhere. That approval records who signed off, when, on which draft, and what produced it, written to a record that cannot be edited afterwards.

No new category of authority to grant

Sign-off sits with an authority you have already granted to a named role, rather than a new kind of machine authority you would need to define. Whoever could already approve a reconciliation break or a statement analysis before this platform existed is the same person who approves it now.

It keeps working when a provider doesn’t

Reconciliation, computation and every check keep running with no AI provider reachable, because none of them depend on one. Only reading and drafting queue until service is restored. The platform gets slower. It does not get less accurate.

What it will not do

Stated as plainly as what it will do, because it is the more useful list to anyone signing off on this.