AdaptEd
Conversational learning

Lectures that
talk back.

AdaptEd turns static teaching into a real-time conversation with an AI lecturer. The slides change as you ask. The pace bends to you. Not 
A note from the team
"Instead of students adapting to the system, our AI lecturer adapts to students."
02
Demo reel — 02:14

The original cut, recorded the morning after we won.

Stack — Next.js · FastAPI · Gemini 1.5 Pro · Retell AI
Awards — Google Gemini 1st · Fetch.ai Agentified
Built in — 36 hours, Pauley Pavilion
03
Three things at once

Listens, draws, watches.

Three loops running in parallel. Each one was a different sponsor's sandbox. Together they made the lecturer feel alive.

Retell AI · Custom LLM URL

Responsive AI

Real-time voice with end-of-turn detection. The lecturer can be interrupted at any point — it loses the thread gracefully and picks back up.

Gemini 1.5 Pro · multi-source RAG

Dynamic content

Slides and whiteboard regenerate in response to verbal cues. Wikipedia, YouTube transcripts, and image search feed the same context window.

Hume · Intel Developer Cloud

Emotion detection

A side channel watches attention and confusion. The lecturer pauses, slows down, or backtracks based on what it sees on your face.

04
Origin

Built in 36 hours under the rafters of Pauley Pavilion.

AdaptEd shipped at LA Hacks 2024 — UCLA's annual hackathon, the largest collegiate one in Southern California. April 19–21, 704 participants across 142 teams, sponsored by Google, Intel, Fetch.ai, MongoDB, Auth0 and a dozen others.

Out of those 142 teams, the original four — Bill Zhang, Spike O'Carroll, Jay Wu, and Jasmine Wu — took first in the Google Gemini Challenge and also won Fetch.ai's Agentified Winners prize. Their thesis: of 16 million U.S. university students, half fall behind on static, one-sided lectures while fewer than three percent have access to quality tutoring programs. So they built a lecturer that talks back.

This page is a frontend showcase of that build — the original FastAPI backend is preserved in this repo as a historical artifact. The voice loop in the demo here is mocked client-side via the Web Speech API, but everything you see in the demo reel above is real footage from the night of.

Spec sheet
EventLA Hacks 2024
DatesApr 19–21, 2024
VenuePauley Pavilion, UCLA
Hackers704
Teams142
AwardsGoogle · Fetch.ai
Team size4
Build time36 hrs
Sleep≈ 4 hrs
Originally branded "TeachMe" during the build, renamed to AdaptEd for submission.