A field-ready prototype with longitudinal measures, logging boundaries, and a deployment stop plan.
HUMAN · Masterclass
Novel Interfaces and Longitudinal Evaluation
Test what remains after the novelty wears off.
Evaluate voice, multimodal, ambient, proactive, embodied, and adaptive systems over time and in context.
Field protocol, repeated-use data, novelty analysis, incident threshold, and evidence-limited recommendation.
Longitudinal Field-Study Dashboard and Stop Plan
Class requirement: create or sign in to your Alternate Clouds account, deploy the Longitudinal Field-Study Dashboard and Stop Plan template, and submit its live URL before the class is marked complete.
Create your Alternate Clouds account ↗Use only work you own or are authorized to use.
Every submission needs a source-and-license manifest covering text, code, images, audio, video, fonts, datasets, models, weights, and AI reference inputs. Attribution alone is not permission. Questionable material stays private or is replaced before deployment or showcase.
Ask about rights clearance01Beyond the chat box+
Choose voice, multimodal, ambient, proactive, or embodied interaction only when the context earns it.
Compare two interface forms against the same human need.
02Novelty and adaptation+
Separate first-use delight from learning, reliance, fatigue, workarounds, and changed behavior.
Define what must be measured after one day, one week, and one month.
03Evaluation that matches the risk+
Combine task success, trust calibration, correction, workload, equity, safety, and operational outcomes.
Build a metric set with success, guardrail, and stop thresholds.
04Field deployment and governance+
Plan consent, logging, monitoring, incidents, model change, study exit, and result communication.
Run a bounded field pilot or simulation and publish what remains unproven.
The complete course adds the teaching deck, Alternate Clouds lab, source-bounded guide, review rubric, and instructor feedback.
Find a class