LANVAR
← The shelf

LIA

Retired toy

An AI companion for people with severe memory loss — answering their questions from a guardian-curated knowledge base, no third party needed.

✳ Best Health Hack · NewHacks 2021 PythonML 2021
How it actually works
THE GUARDIAN guardian's portal adds today's facts KNOWLEDGE BASE facts stack up LIA answers, out loud she asks, it answers — no middleman THE PATIENT “who visited today?” one loop, all day: ask → recall → answer LISTENING… RECALLING… ANSWERING… Q → RECALL → A ? MAYA DID. MAYA DID.
FIG 1 · the loop, animated — she asks, LIA remembers, the guardian keeps the jar full
guardian's portal the facts of a life knowledge base who, what, where, when LIA answers from what the guardian recorded the patient asks “who visited today?” no third party needed dignity, restored ← the answer comes back straight to them NewHacks 2021 · Best Health Hack reborn three years later as NURO ↗
FIG 2 · the machinery — guardian’s knowledge → model → patient’s answers
The story

Inspired by a relative living with memory loss, and built with Abhigyan Praveen, Gianluca Piccirillo, and Matthew Cabral at the University of Toronto’s NewHacks 2021.

A guardian fills a portal with the facts of the patient’s life; a trained model answers the patient’s questions directly from that knowledge — who visited, what day it is, where things are — restoring a little independence and dignity without a human intermediary on call.

LIA won Best Health Hack, and the idea refused to die: three years later it was reborn as NURO, with real conversation recording and semantic memory. Every retired toy on this shelf is a seed.