Geist
Book a demo
Process mining

The process as it runs, next to the process as modeled

Import an event log, and Blueprint draws the paths cases took. Conformance shows where cases leave the model, and the variant explorer shows what each path costs in time.

Book a demoRequest access
The event log draws the process as it actually ran.Conformance checks every case against the reference model.Overlay one variant to see where it leaves the model.Compare two variants side by side.Rework loops are marked in the trace, with the time they cost.
Ask for the dashboard you need, in your own words.Wisp picks a template and binds it to your event log.Every tile reads the same event log.Wisp answers only from the histogram's own evidence.
Discovery, conformance, variants

Every case checked against the model

The process graph shows each path with its case count. Conformance replays every case on the BPMN model and reports fitness. A variant overlaid on the model marks matched steps, inserted activities and steps out of order.

  • Sort variants by cases, coverage, duration or rework
  • Open a variant as a BPMN model, or compare two side by side
  • Variants with unusual durations are flagged
The event log draws the process as it actually ran.Conformance checks every case against the reference model.Overlay one variant to see where it leaves the model.Compare two variants side by side.Rework loops are marked in the trace, with the time they cost.
Dashboards

Charts on the log you mine

Cycle-time distributions, throughput and bottlenecks come from the same event log. Ask Wisp, the AI in Geist, to build a dashboard, then ask it to explain a chart.

How analytics works
Ask for the dashboard you need, in your own words.Wisp picks a template and binds it to your event log.Every tile reads the same event log.Wisp answers only from the histogram's own evidence.
AI actions

Measured findings, ready to act on

Run optimization reads the same log and lists bottlenecks, automation candidates and handover friction with the measured times. What to change stays your call.

How AI actions work
AI actions open on the process in front of you.Run optimization reads the active event log, not just the diagram.Each finding names the step, its measured time and what to check first.The report changes nothing in the model. What to act on is your call.
How it works

From an event log to the variants that cost time

  1. Step 1

    Import

    Upload an event log as CSV or XES. Data quality lists missing values and import issues first.

  2. Step 2

    Discover

    The process graph shows how cases ran. Set a date range to look at one period.

  3. Step 3

    Check

    Conformance replays each case on your BPMN model and marks where cases leave it.

  4. Step 4

    Compare

    The variant explorer ranks the paths and marks rework. Open a variant as a model, or compare two.

FAQ

Questions about process mining

What does an event log need?

One row per event with a case ID, an activity name and a timestamp. CSV and XES files work, and you can export the log again as CSV or XES.

What does fitness mean?

How well the recorded cases run through the model. Blueprint counts fitting, partly fitting and non-fitting cases, and reports token fitness separately.

Which BPMN elements does conformance cover?

Sequence flows, exclusive and parallel gateways, and loops. Where a model uses elements the replay does not support, the check falls back to comparing activity sequences and says so.

Can I open a variant as a BPMN model?

Yes. Open any variant in the modeler, or select two and compare them side by side.

Who sees individual cases?

Slow-case samples in the variant explorer follow your organization's privacy scope.

Related capabilities

Next step

Mine one of your processes

Send an event log export, and we run discovery and conformance on it with you.