★ 1st Place · Assistive Technology · 2026

CONNECTABLE

An AAC communication system that learns how you speak — and drafts the sentence before you finish tapping.

A personal Augmentative and Alternative Communication system for non-verbal users built around a 66-symbol board. A 3-layer AI cascade — bigram lookup, ChromaDB vector search, and a local LLM fallback — predicts what the user wants to say next, and retrains itself nightly from their own phrase history.

TimelineFeb 28 – Mar 2, 2026
RoleFull-Stack Developer
TypeHackathon Project
Outcome1st Place

The Challenge

Non-verbal users rely on AAC devices to communicate, but most commercial tools are static — they don't learn individual patterns, context, or preferences over time. Users must manually build every phrase from scratch, and generic suggestions rarely match their actual communication needs.

The Solution

ConnectAble combines a 66-symbol communication board with a personalized AI prediction system that learns nightly from the user's phrase history. A 3-layer cascade — bigram lookup, ChromaDB vector search, and LLM fallback — ensures fast, relevant suggestions that improve the more the system is used.

01

Symbol Communication Board

A 66-symbol grid organized into 5 categories (food, feelings, actions, places, people) lets users build sentences by tapping buttons. The top bar displays real-time AI phrase suggestions that update as each symbol is selected.

  • 66 symbols · 5 categories
  • Real-time suggestions
  • Accepted phrases feed learning
02

3-Layer AI Prediction Cascade

Phrase predictions run through a cascade designed for speed and accuracy. Layer 1 is an instant bigram lookup from a local vocabulary store. Layer 2 does semantic vector search over past phrases via ChromaDB. Layer 3 falls back to Ollama's phi3 LLM when the phrase database is sparse.

  • L1: Bigram lookup (instant)
  • L2: ChromaDB semantic search
  • L3: Ollama phi3 fallback
03

Nightly Learning Pipeline

Every night at 2 AM, the system retrains from logged phrase history — rebuilding the bigram map and re-embedding phrases into ChromaDB. The model improves continuously without user intervention.

  • Automated retraining at 2 AM
  • Bigram map rebuilt nightly
  • Embeddings stay fresh
04

Text-to-Speech

Supports two TTS modes: fully offline using pyttsx3 / macOS say, or high-quality streaming audio via ElevenLabs for users who need a more natural voice.

  • Offline TTS by default
  • ElevenLabs streaming option
  • Configurable per user
05

Agent Tab

A dedicated agent interface lets users send natural language messages that are classified into intents — make a call, order food, set a reminder, or general chat — and dispatched to tool handlers automatically.

  • Intent classification via phi3
  • Tool handlers for calls, food, reminders
  • General chat fallback
06

Private by Design

All phrase data is stored locally in an AES-256 encrypted SQLite database (SQLCipher). The LLM runs locally via Ollama. No user data leaves the device unless ElevenLabs TTS is explicitly enabled.

  • AES-256 encrypted SQLite
  • Local LLM inference
  • No cloud dependency by default

Frontend

React 18 · TypeScript · Vite · Tailwind CSS

Backend

FastAPI · SQLite + AES-256 · Python 3.11+

AI & ML

ChromaDB · sentence-transformers · Ollama phi3

TTS & APIs

pyttsx3 · ElevenLabs · 12 REST endpoints

66 AAC symbols across 5 categories
3 Prediction layers in the cascade
12 REST API endpoints
0 Cloud dependencies by default
01

Cascade Design for Latency

Putting the cheapest operation first (bigram lookup) and the most expensive last (LLM inference) keeps suggestions fast for common phrases while maintaining quality for novel inputs.

02

Privacy as a Feature

For assistive technology, communication history is highly sensitive. Designing for offline-first with local encryption made privacy a core feature rather than an afterthought.

03

Personalization Takes Time

The nightly training pipeline means the system improves gradually. Seeding the database with starter phrases was critical for useful predictions from day one.

04

Graceful Degradation

Building the frontend to work standalone with fallback data when the backend is offline ensured the communication board was always usable, even during development or connectivity issues.

Next project Linx