# Project export: Ted.AI

This document was generated by HackStack to give an AI agent context about a hackathon project. Sections are labeled with their provenance; content marked as truncated was cut to keep this document small.

## Project metadata

- Hackathon: Cal Hacks 12.0
- Tagline: A multimodal AI companion that fuses emotion sensing, language understanding, and real-time biofeedback to support children’s mental wellness.
- Devpost: https://devpost.com/software/ted-ai-x8537t
- GitHub: not linked
- Video: https://www.youtube.com/embed/3bj86ky1eAc?enablejsapi=1&hl=en_US&rel=0&start=&version=3&wmode=transparent
- Result: winner (LiveKit: Most Creative Project; Cal Hacks: 2nd Overall)
- Team: contributor stats unavailable

## Devpost submission (written by the team)

### Inspiration

Every day, millions of children grow up battling unseen struggles — anxiety, ADHD, loneliness, and emotional overwhelm — in a world moving too fast to listen. We wanted to create something that not only hears them but feels with them. A companion that bridges empathy and intelligence to help them regulate emotions and feel understood.

### What it does

Ted.AI is an emotionally intelligent teddy bear powered by multimodal AI. It senses hugs, movement, and heart rate using embedded sensors and responds with empathy through a conversational LLM. It guides children through breathing exercises, focus routines, and calming interactions while analyzing tone, language, and gestures to adapt its responses in real time. A connected dashboard visualizes emotional states, sentiment trends, and simulated brain-region activations for parents, educators, and clinicians.

### How we built it

Ted.AI integrates: Hardware: ESP32 microcontroller, HW-502 pulse sensor, capacitive touch sensors, and MPU6050 accelerometer. Software: OpenAI Whisper for speech-to-text, RoBERTa for emotion detection, and GPT-powered dialogue through LangChain orchestration. Data Pipeline: Real-time sensor fusion via MQTT, edge inference using TensorFlow Lite Micro, and backend storage with Flask, MongoDB, and InfluxDB. Dashboard: Built with React, Flask, and D3.js to visualize emotion timelines and neural activation maps.

### Challenges we ran into

Synchronizing real-time audio, motion, and biosensor inputs required complex sensor fusion and filtering. Integrating emotion classification with low-latency on-device inference was another major challenge. We also spent time designing dialogue flows that felt emotionally natural rather than robotic, balancing empathy with accuracy.

### Accomplishments we're proud of

We successfully built a fully functional prototype that detects emotion through physical and verbal cues, reacts in real time, and displays a live dashboard of emotional analytics. The seamless blend of hardware sensing, multimodal AI, and affective computing exceeded our expectations in both complexity and impact.

### What we learned

We learned how to merge disciplines — embedded systems, AI, psychology, and human-centered design — to create technology that genuinely connects with people. Building Ted.AI taught us the importance of empathy in engineering and how emotional design can make AI feel human.

### What's next

We plan to integrate EEG-based emotional tracking, cloud-based analytics for therapists, and reinforcement learning for adaptive empathy. Our vision is to expand Ted.AI into classrooms and therapy settings to support children worldwide through emotionally aware technology.

## README (from the GitHub repository)

No README available.

## Detected evidence (automated analysis)

No repository was indexed for this project. Claimed technologies below could not be checked against code.
- AWS (technology) — claimed on Devpost, not found in the code
- Docker (technology) — claimed on Devpost, not found in the code
- Firebase (technology) — claimed on Devpost, not found in the code
- Flask (technology) — claimed on Devpost, not found in the code
- Google Gemini (technology) — claimed on Devpost, not found in the code
- OpenAI (technology) — claimed on Devpost, not found in the code
- Python (language) — claimed on Devpost, not found in the code
- React (technology) — claimed on Devpost, not found in the code

## Codebase structure

No repository index available.

## Key source files

No repository index available; no source files included.