A study comparing Sensible Agent with a conventional, voice-controlled AR assistant found that the proactive system reduced mental workload, even though it took longer to complete interactions.
The results were measured using the NASA Task Load Index (NASA-TLX) for cognitive load, the System Usability Scale (SUS) for usability, a 7-point Likert scale for user preference, and total interaction time.
On the NASA-TLX mental demand scale, Sensible Agent scored an average of 21.1 on a 100-point scale, compared with 65.0 for the baseline. The difference was statistically significant (π < .001). Perceived effort also fell significantly (π = .0039).
Usability scores were similar, with no statistically significant difference between the two systemsβ SUS results (π = .11). But participants preferred Sensible Agent overall, with an average rating of 6.0 versus 3.8 for the baseline on the 7-point scale (π = .0074).
The baseline system was faster. Interaction time, measured from the moment a prompt was triggered to the final system response to the user’s input, averaged 16.4s for the baseline and 28.5s for Sensible Agent. The source describes this as the expected trade-off of a two-step interaction flow, where the agent first proposes an action and the user then confirms it.
The findings suggest the proactive approach may be useful in social contexts where discretion and minimal user effort are important, even if it adds time to the interaction.
Source: research.google.
Companies can share verified announcements through Newz9’s international press release submission page.
