Study Designer
grid_on20×16
100%
two-finger scroll = pan · pinch = zoom · drag dividers to resize
Select icons → Capture, set keys & mark ★ correct. Dial the ranges + pick directions — the formula expands. Push lands the set in the study.
Counts are per icon: each enabled direction adds that icon's own slice (a 4-dir icon = 4× a 1-dir icon). Congruency too — C or I = 1, both = 2. Clearing a row's directions mutes it (off the canvas + the count). After Capture, drag the anchors to your design positions (stop playback first).
A unified set of stimulus glyphs your games use. Pick a category (geometric shapes or Material icons), then tune style + size.
Count follows the generator's n-max (you need ≥ n-max distinct stimuli). Adjust it on the Generator panel.
The non-game screens of a session, stored on the game group (SC_SEQUENCE). Pick one, set its text + behaviour; the preview shows it. Background art reuses the tile palette.
Drive a synthetic participant through a served controller and watch it adapt — no recruiting required. Each trial is a real /ml/decide call, so this is also load against the gateway.
Model
Simulated participant
Accuracy falls off as the administered n passes ability; reaction time rises with load. A harness, not a model of a human.
Run
Arms run concurrently against the same controller, abilities spread across the n range this game group expands to. The spread is the finding.
Dimensions what each axis encodes
Every channel below is measured during the run. The mapping is saved with the instance, so a replay comes back on the same axes.
Bench
Saved runs draw as faint tracks behind the live one, so two controllers can be compared on the same axes.
Wire a participant state to an email. This records the rule on the study — it does not send: sending is nx-az-email's job, the one process holding a mail credential.
Published job
Anonymous by construction: a participant is a guid. No names, no addresses — mail is tracked as events against a guid.
Signup the link participants open
A study day is an appointment. On-time is required by default; relaxed lets a late session close an earlier day. Reschedule shifts a participant's remaining window instead of forgiving the miss.
—
People 0
The adaptive dispatch controllers served on this origin's /ml gateway. Pick one to inspect its parameters and drive a trial run through it.
Measures what the controller does, not what it claims: one /ml/decide probe per cell across recent accuracy × current level.
Selection
Interpolated @ Playhead
Keyframe
Click keyframe on timeline to select · Drag to move · Dbl-click to delete