Task Track

Identifying the Opportunity

Market Viability: I began by assessing existing goal-setting apps to understand the current market and identify user pain points and unmet needs. This helped validate whether there was genuine demand for a new AI-driven solution.

Heuristic Analysis: By reviewing popular goal-setting apps, I identified shared features and typical user flows, helping me determine common design patterns and opportunities for differentiation.

Research Insights

1. Literature Review: Most people fail to achieve their goals due to a lack of structured planning. Without a well-defined step-by-step approach, motivation and follow-through drop significantly.

2. User Research: Focused on college students (18–23) at California State University, Long Beach. A key insight emerged: they struggled with structuring their goals, resulting in procrastination and low motivation. They wanted a tool that:

• Guides them in creating well-defined goals and tasks.

• Reduces mental effort by breaking down goals into manageable steps.

Defining the Challenge

Design a goal-setting app that leverages generative AI to automate goal structuring, task creation, and management.

Approach & Experimentation

Prompt Engineering: Tested various structured prompts with large language models to yield consistent, coherent goal breakdowns.

Prompt Example:

“I am a college student and would like to achieve {goal_description}, I estimate this will take {HR:MIN} to complete, and I want to finish by {Date/Time}.”

The AI response provided a list of tasks and timelines.

Observed that more detailed goals produced more relevant and tailored task breakdowns.

Design & User Flows

User Flow Diagram: Created a streamlined flow to keep the app intuitive, focusing on minimal steps from goal creation to task management.

Wireframes & Visual Design:

Opted for a bold black-and-yellow palette to draw attention to key actions and important information.

Incorporated familiar features from top apps—monthly and weekly views—to align with user expectations and enhance adoption.

Usability Testing

1. AI Capability Test:

Result: Tasks generated were somewhat generic but still usable. Users indicated a desire for more personalization and ongoing learning from the AI to adapt tasks to individual schedules and preferences.

2. Design & Usability Test:

Result: Users found the interface clean, straightforward, and easy to navigate. They wanted insight into how tasks were generated and suggested gamification features to make the experience more engaging.

Lessons Learned

Potential for AI: Generative AI can streamline goal creation and management, but must evolve to offer deeper personalization and context.

User Intent Matters: AI cannot fully compensate for vague or poorly defined goals; users must still articulate clear intentions.

Delight & Engagement: As user flows simplify, the role of design in creating an engaging, delightful experience becomes even more critical.