Cultivating user trust designing AI education platform
December 2023 — March 2024
SmartPrep is an EduTech platform focused on transforming secondary education through AI-driven tools for language education.
Product Designer working with product manager and 5 software engineers.
As the first design hire, I led user research to uncover user pain-points, built human-AI experiences from 0-1 to boost user retention, and established a design system for efficient handoff with cross-functional teams.
Impact
+27%
-21%
$1.2M
User problem
Teachers struggle to offer personalized support to students due to inefficient workflow.
Teachers have little time for personalized suppport
Teachers are flooded with assignments to be graded
Business Goal
Low retention rate among trial users with our MVP chatbot.
Solution
An efficient and trustworthy education platfrom that supports teachers with personalized coaching.
Generate assignment with AI to help you save more time.
Teachers can generate entire assignments or specific questions using AI that aligns with their syllabus and learning objectives
2.1 Assignment Creation
2.2 Question Card Interaction
AI facilitated grading and student assignment analysis
Teachers can access information like AI grading suggestions, question breakdowns, common misconceptions, and more.
2.3 Assignment Insights
AI facilitated grading and student assignment analysis
Teachers can access information like AI grading suggestions, question breakdowns, common misconceptions, and more.
2.4 Student Insights
So, how did I get here? It all started with...
Context
Before I joined, due to time constrain, the team launched the product as an AI Chatbot.
2.1 Assignment Creation
Research — Data Analysis
96% of trial user dropped off before acting on AI generated insights.
4.1 User engagement Map
Where… did we lost our users?
Mapping user retention across key touch points in the user journey to identify where we experienced the highest drop-off rate.
Research — Quanlitative
Teachers are hesitant to rely on AI as there is too much uncertainty around the technology in education scenarios.
Why… did we lost our users?
Mapping user retention across key touch points in the user journey to identify where we experienced the highest drop-off rate.
Iteration 1: User flow & Information architecture
Teachers have a complex role and prefer products that support the entire workflow.
However, that chatbot only covers limited workflow
Expanding product coverage
Users were accustomed to using different platforms for assignments. Hence, we expanded our product to mimic their familiar workflow.
Unresolved Problems
Low user trust is the root cause of product abandonment, reducing product retention.
Therefore, I tried enhancing the credibility of AI interaction to further reduce uncertainty and build trust.
User's trust emerges from repetitive reliability indicator, but the question is how ...?
To explore ways to strengthen trust between users and AI products, I delved into HCI research on AI interactions scenarios that demands high level of user trust, and examined the concept of reliability indicators that justifies trustworthiness.
Design principles for AI interactions
AI in education should provide familiarity and transparency for teachers
Familiar Interactions
I delved into HCI research on AI interactions scenarios that demands high level of user trust, and examined the concept of reliability indicators that justifies trustworthiness.
Transparent Experiences
Clearly entail how AI makes decisions and where AI is implemented, providing users with understandable explanations and insights into the processes.
Iteration 2: AI Interactions in Assignment Creation
Helping teachers feel more comfortable with AI via using familiar prompt inputs.
Ensure clarity in potential AI interactions to empower users with autonomy and eliminate uncertainty.
Iteration 2: AI Interactions in Assignment Grading & Analysis
Helping teachers feel more comfortable with AI via using familiar prompt inputs.
Transparency in students’ interactions with AI fosters trust between platforms and teachers.
Iteration 2: AI Interactions in Student Insight Analysis
Transparency with evidence and explanation to calibrate trust in the moment.
Transparency with confidence level indicator to be honest with our users.
Retrospectives
Designing for Implementation Means Designing with Engineers in Mind
In a fast-paced startup environment, I learned that collaborating closely with engineers is crucial. From mapping out all edge cases to providing clear annotations and structured handoffs, making life easier for engineers means more of my designs get pushed out to users. Seeing my Figma work come to life is incredibly rewarding.
Navigating Ambiguity in Emerging Tech with Academic Research
Designing for AI comes with a lot of ambiguity due to the lack of established design patterns. Instead of relying on intuition alone, I found that academic research in HCI, especially on human-AI interaction, provided valuable guidance in shaping the cognitive models of AI interactions.
Prioritizing Designs that Drive Business Growth
At an early-stage startup, I had to prioritize designs that would have the most impact on business growth. Engaging closely with the business side, I realized that launching a functional version—even with minor design flaws—can be crucial for meeting client timelines, generating revenue, and gathering data to improve the product.