TAI: You Learning Agent

TAI: You Learning Agent

TAI: You Learning Agent

03
TAI
UX Design
UX Design
AI Product
AI Product
{ SCROLL }
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.

product 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

The Problem

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.

When a course PDF is uploaded, the assistant automatically parses its structure—detecting sections, headings, and key concepts. These are presented as a sidebar table of contents and overview bullets inside the chat, giving students multiple ways to navigate. Students can jump directly to relevant sections or ask file-based questions, and the model responds with precise, section-grounded answers.

When a course PDF is uploaded, the assistant automatically parses its structure—detecting sections, headings, and key concepts. These are presented as a sidebar table of contents and overview bullets inside the chat, giving students multiple ways to navigate. Students can jump directly to relevant sections or ask file-based questions, and the model responds with precise, section-grounded answers.

When a course PDF is uploaded, the assistant automatically parses its structure—detecting sections, headings, and key concepts. These are presented as a sidebar table of contents and overview bullets inside the chat, giving students multiple ways to navigate. Students can jump directly to relevant sections or ask file-based questions, and the model responds with precise, section-grounded answers.

Explore

Purchase

Configuration

Analytics



❌ 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

Large STEM classes at Berkeley face three major pain points:

Auto-Loading Purchased Devices

Automatically imports purchased devices into the portal so users can begin configuring them even before physical delivery.

Wasted Time on Waiting

Dealers had to wait until the physical devices arrived to begin the provisioning process, which prolonged the wait time for customers to receive their service.

Step-by-Step Guided Setup Wizard

Introduces a wizard to guide users through the setup process in the correct sequence.


Uncertainty on Setup Process

Uncertainty about where to start in the provisioning portal, but not following an optimal setup sequence can lead to additional manual work.

Optimized Workflow Logic

Create template users to apply pre-configured settings to multiple devices, saving time on recurring setups.

  • Use cloning features to replicate configurations from an existing user or device, ensuring consistency across teams.

  • Batch configure multiple devices at once, reducing repetitive manual steps while retaining flexibility for unique needs.


Tedious Manual Work

The previous provisioning process required users to manually configure each device one by one, a time-consuming and error-prone approach.