ReflectEd: Evaluating Reflection-Driven Learning in an AI-Assisted System
This addresses the challenge of maintaining collaboration readiness in time-constrained workflows, though it is incremental as it builds on existing reflection and AI-assisted system concepts.
The study tackled the problem of sustaining engagement and reducing task drift between collaborative checkpoints by developing ReflectEd, an AI-assisted system for reflection-driven learning, finding that deeper reflection configurations increased actionability and planning but were harder to sustain, with partner-visible reflections improving coordination.
In collaborative settings, sustaining momentum and engagement between checkpoints (e.g., meetings) can be challenging, often leading to task drift and reduced preparedness. To address this gap, we developed ReflectEd, an AI-assisted system that supports between-checkpoint reflection through theory-driven prompts with progressively structured levels and mechanism-based scaffolding. We evaluated ReflectEd in a mixed-method study comparing two reflection configurations: a regular reflection workflow and a deeper reflection workflow that included an additional transformative reflection activity. Across conditions, participants reported steady engagement early in the week. In the deeper configuration, later reflections tended to exhibit higher actionability and richer forward-looking planning, while also being harder to sustain and more effortful during periods of active work. Partner-visible reflections were frequently described as supporting coordination by surfacing differences in focus and facilitating accountability. Overall, the findings characterize trade-offs between reflection depth, feasibility, and perceived preparedness for subsequent checkpoints. We discuss implications for the design of AI-assisted systems that support collaboration readiness and reflection-oriented regulation in time-constrained collaborative workflows.