Everything I have built.

A multi-agent assistant that acts across your inbox, calendar, contacts, music and home devices from a single conversation.

A serverless engine that turns a Google Form and a chosen persona into coherent, human-plausible survey responses at scale.

A fact-checker that scores how likely a claim is to be a hoax, and shows the entire reasoning chain behind the number.

When should a robot tutor teach, rest, or push harder? Formalised as a 1,440-state Markov Decision Process and solved with deep reinforcement learning.