Product tour

Six screens. Three minutes. One fictional company.

This is the route we take in a working session, in order, on real screens from the OgMart reference world. OgMart is fictional and labeled as such on every image.

Book a working session Read the demo guide

1 · The queue

Every item, ranked by value at stake.

The first thing to judge is whether the ordering is defensible. Could you hand this to a team lead and have them work it top-down? Each row carries its pressure, the money at stake and its band.

The OgMart payments domain as a ranked list of entities, each with its value pressure, value at stake and value band, ordered by pressure — The queue: every entity ranked, with the money at stake beside it, so a team can work it top-down.

2 · One item, in depth

What to do, what it costs, and why.

Ranked candidate actions with their economics, the drivers behind the conclusion, the trajectory against the events that triggered it, and, here, a notice that the evidence is conflicting so autonomous action is held.

3 · A priced decision

Acting against not acting.

The forward path with and without the action, and the net value of acting. The product says plainly when an action costs more than it saves. That is the point of pricing it.

Impact analysis for an OgMart entity: the forward path with and without the action, and the net value of acting — Impact analysis prices the action against doing nothing, and says plainly when acting costs more than it saves.

4 · Counterfactual

The same item, run forward twice.

Once ignored, once acted on early. The comparison replaces a post-incident argument with a measurement, and it is projected, not realized, which the screen says.

Counterfactual theater: two forward projections of one OgMart entity, one with no action and one with early action, with the dollars at stake in each — Counterfactual: the same entity run forward twice, once ignored and once acted on early.

5 · The model comparison

Look for the models that lose.

Each model against the dashed baseline, measured on data it never trained on. Below the line, the model adds information. Above it, it does not, and it is shown anyway.

Prediction error by model on data the model never trained on, with a dashed baseline line: models that beat the baseline fall below it and those that do not rise above it — Models are judged against a baseline on data they never trained on. The ones that lose are shown, not hidden.

6 · The audit trail

Every blocked and held action, with its reason.

Guard rails that blocked actions, and the items whose conflicting evidence holds autonomous action, recorded with the acting user and the time.

The audit log: a compliance snapshot and the guard rails that blocked actions, including entities whose conflicting evidence holds autonomous action — Every blocked and held action is recorded with its reason, including actions held because the evidence conflicts.

Now see it on your domain

The tour is OgMart. The session is yours: your items, your events, your time frame.

Book a working session Download the evaluation checklist