TAI: You Learning Agent
TAI: You Learning Agent
TAI: You Learning Agent
03
TAI
UX Design
UX Design
AI Product
AI Product
Intro
I worked with the Teaching Assistant Intelligence (TAI) team, a cross-functional research and product group at UC Berkeley’s Vive Center, focused on creating AI-powered tools to transform how students learn in large STEM classes. On this project, I collaborated with two other UI/UX designers, two product managers, and a team of five to ten engineers. I was responsible for the redefining the new user flow for the up-coming version, refine key features such as note, knowledge base, and file/video chat functions.
I worked with the Teaching Assistant Intelligence (TAI) team, a cross-functional research and product group at UC Berkeley’s Vive Center, focused on creating AI-powered tools to transform how students learn in large STEM classes. On this project, I collaborated with two other UI/UX designers, two product managers, and a team of five to ten engineers. I was responsible for the redefining the new user flow for the up-coming version, refine key features such as note, knowledge base, and file/video chat functions.
I worked with the Teaching Assistant Intelligence (TAI) team, a cross-functional research and product group at UC Berkeley’s Vive Center, focused on creating AI-powered tools to transform how students learn in large STEM classes. On this project, I collaborated with two other UI/UX designers, two product managers, and a team of five to ten engineers. I was responsible for the redefining the new user flow for the up-coming version, refine key features such as note, knowledge base, and file/video chat functions.
demo video
MVP
Personalized, course-specific teaching assistant that supports students throughout their learning process
Personalized, course-specific teaching assistant that supports students throughout their learning process
Personalized, course-specific teaching assistant that supports students throughout their learning process
Lecture recordings are automatically broken down into meaningful segments, each paired with its transcript. Students can skim through the chaptered timeline or click on transcript sections to jump to specific moments, making long videos searchable and digestible.
Lecture recordings are automatically broken down into meaningful segments, each paired with its transcript. Students can skim through the chaptered timeline or click on transcript sections to jump to specific moments, making long videos searchable and digestible.
Lecture recordings are automatically broken down into meaningful segments, each paired with its transcript. Students can skim through the chaptered timeline or click on transcript sections to jump to specific moments, making long videos searchable and digestible.
The Problem
Large STEM classes at Berkeley face three major pain points:
Why start with micropipette?
❌ Limited personalized attention: Office hours are overcrowded and intimidating.
🧩 Fragmented learning materials: Lecture slides, past exams, labs, and readings are scattered across different platforms, making it hard to study systematically.
🤖 Generic AI isn’t enough: Tools like ChatGPT can’t provide course-specific, reliable answers — leading to frustration or misinformation.
👉 This leads to students relying on guesswork, overloading TAs with repetitive questions, and missing deep conceptual understanding
❌ Limited personalized attention: Office hours are overcrowded and intimidating.
🧩 Fragmented learning materials: Lecture slides, past exams, labs, and readings are scattered across different platforms, making it hard to study systematically.
🤖 Generic AI isn’t enough: Tools like ChatGPT can’t provide course-specific, reliable answers — leading to frustration or misinformation.
👉 This leads to students relying on guesswork, overloading TAs with repetitive questions, and missing deep conceptual understanding
❌ Limited personalized attention: Office hours are overcrowded and intimidating.
🧩 Fragmented learning materials: Lecture slides, past exams, labs, and readings are scattered across different platforms, making it hard to study systematically.
🤖 Generic AI isn’t enough: Tools like ChatGPT can’t provide course-specific, reliable answers — leading to frustration or misinformation.
👉 This leads to students relying on guesswork, overloading TAs with repetitive questions, and missing deep conceptual understanding
From local "ChatGPT" to End-to-end Intelligent Learning Agent
From local "ChatGPT" to End-to-end Intelligent Learning Agent
From local "ChatGPT" to End-to-end Intelligent Learning Agent
Students can start directly from the course landing page to ask questions in natural language. Instead of relying on generic LLM responses, the assistant anchors every answer to instructor-provided materials, ensuring accuracy and academic integrity. When students ask a question, the system retrieves relevant sections from the course’s slides, notes, or problem sets, and shows linked references, allowing students to trace exactly where the information came from. This creates trust and transparency, especially in technical courses where precision matters.
Students can start directly from the course landing page to ask questions in natural language. Instead of relying on generic LLM responses, the assistant anchors every answer to instructor-provided materials, ensuring accuracy and academic integrity. When students ask a question, the system retrieves relevant sections from the course’s slides, notes, or problem sets, and shows linked references, allowing students to trace exactly where the information came from. This creates trust and transparency, especially in technical courses where precision matters.
Students can start directly from the course landing page to ask questions in natural language. Instead of relying on generic LLM responses, the assistant anchors every answer to instructor-provided materials, ensuring accuracy and academic integrity. When students ask a question, the system retrieves relevant sections from the course’s slides, notes, or problem sets, and shows linked references, allowing students to trace exactly where the information came from. This creates trust and transparency, especially in technical courses where precision matters.
Academic Research
Effective learning methods for students with learning disabilities.
Expert Interview
The problem with traditional learning method for lab experiment.
Contextual Inquiry
First-hand observation of student's experience with lab experiments.
Different students find different modes of instruction useful, and the preferred mode may be dependent on experience
???
Following the experiment video required students to switch attention back and forth between multiple areas during steps.
Most errors occurred from forgetting steps or improper use of the equipment.
Immediate feedback is crucial to error reduction and learning.
Academic Research
Effective learning methods for students with learning disabilities.
Expert Interview
The problem with traditional learning method for lab experiment.
Contextual Inquiry
First-hand observation of student's experience with lab experiments.
Different students find different modes of instruction useful, and the preferred mode may be dependent on experience
???
Following the experiment video required students to switch attention back and forth between multiple areas during steps.
Most errors occurred from forgetting steps or improper use of the equipment.
Immediate feedback is crucial to error reduction and learning.
Academic Research
Effective learning methods for students with learning disabilities.
Expert Interview
The problem with traditional learning method for lab experiment.
Contextual Inquiry
First-hand observation of student's experience with lab experiments.
Different students find different modes of instruction useful, and the preferred mode may be dependent on experience
???
Following the experiment video required students to switch attention back and forth between multiple areas during steps.
Most errors occurred from forgetting steps or improper use of the equipment.
Immediate feedback is crucial to error reduction and learning.
Leap Motion
shareable, portable, & cost-effective, precise, open space
lack haptic feedback
Physical Interactive gadget
haptic feedback, shareable
expensive, not adaptable
VR
immersive
isolating, expensive
Wall Projection
open space, collaboration
expensive, hard to set up
Leap Motion Sensor
Leap Motion Sensor
Leap Motion
shareable, portable, & cost-effective, precise, open space
lack haptic feedback
Physical Interactive gadget
haptic feedback, shareable
expensive, not adaptable
VR
immersive
isolating, expensive
Wall Projection
open space, collaboration
expensive, hard to set up
Leap Motion
shareable, portable, & cost-effective, precise, open space
lack haptic feedback
Physical Interactive gadget
haptic feedback, shareable
expensive, not adaptable
VR
immersive
isolating, expensive
Wall Projection
open space, collaboration
expensive, hard to set up
Pressed
Released
Second Stop
First Stop
The first stop expels enough air from the pipette for an accurate measurement in the next step.
Release the plunger draws up the accurate measurement amount of liquid.
The second stop is meant to expel excess liquid from the tip.
1
Release
2
3
How did early user testing revealed this issue?
Our Approach
Key Motion 1: Pressing
Key Motion 2: Turning
“There’s a little bit of hesitation before you reach the first stop [but] I wouldn’t say I feel [the pressure] at this point..."
First Stop
Second Stop
Released
“Easy to press down”
“Harder to press down”
price
immersion
accessibility
concept learning
engagement
hands-on practice
Motion Lab
price
immersion
accessibility
concept learning
engagement
hands-on practice
price
immersion
accessibility
concept learning
engagement
hands-on practice
Labster
price
immersion
accessibility
concept learning
engagement
hands-on practice
Gizmos
price
immersion
accessibility
concept learning
engagement
hands-on practice
HoloLab Champions
price
immersion
accessibility
concept learning
engagement
hands-on practice
AR Science Lab
Users successfully transfer conceptual learning from digital to real micropipette.
Users utilize gestural learning to help them remember experiment steps.
Users successfully transfer conceptual learning from digital to real micropipette.
Users utilize gestural learning to help them remember experiment steps.
Users would benefit from better communication of realistic interaction.
Reflection