Ultra PatternsAI interface patterns with receiptsULTRA project

Metric · Cognitive load

View

Mental effort

5 min per participantPart of the ten-minute kit. All nine metrics

What it tells you

How hard people had to think to use the AI feature. In the KU Leuven review, the size and structure of an explanation were found to influence it.

How, in 5 minutes

Two items adapted from the NASA Task Load Index (NASA-TLX), mental demand and frustration, on a 1 to 7 scale after the task, plus time on task from the logs.

Benchmark

No benchmark yet. Run the kit and send us yours.

Plan your test explains how to choose metrics and how many participants you need.

Questionnaire items

  1. How mentally demanding was the task? (1 to 7)
  2. How frustrated did you feel during the task? (1 to 7)

Answer on a 1 to 7 scale from strongly disagree to strongly agree unless the item states its own scale. The ULTRA team wrote or adapted these items for the kits and has not checked their reliability, so report them as ULTRA kit items and name any questionnaire they were adapted from.

Log events

task_started {task}task_completed {task, duration_ms}

Pairs with

Urgency labels for prioritisationWhy is this urgentMatch recipe

Research side · the property behind this metric

Property

Cognitive load (Subjective system aspects). The cognitive effort the user has to do to achieve the task. Donoso-Guzmán et al. 2025, Table 9

References

  1. Hart and Staveland 1988, NASA-TLX.
  2. Donoso-Guzmán et al. 2025: five of the reviewed studies used the standardised NASA-TLX.

Editors

Practice: Thomas Van den Bossche · v0.1