Dummy Run

AI plays your users and tries your app before your customers do.

A fictional user with a real role signs in to your preview and reports what broke, with the screenshot to prove it.

frictionmajormeasuredconfirmed
On a phone the Submit button sits under the keyboard
Step 6 of run 2026-10-17-sam-author-006, screenshot step-06.png. Seen again in run 007.

How a run works

Amber marks the two stages where a model acts. Green marks what people read.

  1. CastPersonas with a role, a device and goals
  2. RunA real browser on your preview
  3. ReportSteps, screenshots and logs
  4. ReviewEvery claim checked against evidence
  5. BoardConfirmed findings only

What you get back

Everything below is drawn from the example cast for Inkwell, a fictional publishing app.

Samsam-author
Role
Author
Device
Phone, 390 by 844
Goals
Submit a draft. Reply to review comments
May
write draftsreply to reviews
May not
approveschedule
A persona is a fictional user with a role, a device and permissions.
sam-author / reply-to-review2026-10-17-sam-author-006
  1. 1click Submit4.5 s
  2. 2select Title2.5 s
  3. 3select Comment2.9 s
  4. 4click Approve3.1 s
  5. 5click Schedule2.2 s
  6. 6visit /draftsfinding
  7. 7type Comment3.4 s
  8. 8click Submit2.7 s
  9. 11finishcompleted
Step 6, screenshot step-06.pngSubmit button under the keyboard
A run is one persona working through one scenario, step by step.
permissionmajorcodeconfirmed
A contributor can open the rates table for all writers
Step 7 of run 2026-10-17-lin-contributor-008. The reviewer traced the route to app/policies/rate_policy.rb and confirmed it.
A finding carries its evidence tag, its step and the reviewer's verdict.

The results board

FindingKindSeverityPersonaRunsVerdict
A contributor can open the rates table for all writerspermissionmajorlin-contributor1confirmed
On a phone the Submit button sits under the keyboardfrictionmajorsam-author2confirmed
Scheduling an issue for a past date returns a server errorbugmajorada-editor1confirmed
The draft title field has no accessible nameaccessibilityminorsam-author1pending
The payment status "settled" is unclear to a contributorquestioninfolin-contributor3pending
Confirmed findings only, as static HTML and JSON you host yourself. A person decides what becomes a ticket.

Every run in Grafana

Each run is one OpenTelemetry trace. Four dashboards read the traces, metrics and logs, and the Grafana page shows them in full.

The overview dashboard
The overview dashboard
The personas dashboard
The personas dashboard
The findings dashboard
The findings dashboard
The run dashboard
The run dashboard

I am

Dummy Run is pre-release and nothing installs yet. The reference has the plan, the architecture and the run record format.