Skip to main content
The Run tab shows how your agent did on every scenario.
Three plays, not one
Agents vary, so each scenario runs three times to tell a real problem from a lucky draw.
A real-feeling world
A realistic user and a fully wired digital twin, not scripted inputs.
Ready to ship
The difference between a demo that worked once and an agent you can rely on.
The Run tab of the report

The Run tab: each scenario's three attempts, and how many checks failed.

​
Read the grid

Each row is a scenario, and each square is one attempt: green passed, red failed.

​
See what happened

Select any red square to open that conversation. It opens at the turn where things went wrong, with What broke at the top: the exact words a check objected to, and why.

​
Compare with earlier runs

Each run is kept. Pick an earlier one to see whether a change made things better or worse. For every label in this tab, see Run results.