Augova
Augova is an AI automation company based in Richmond Hill, Ontario, which I co-founded in August 2026 and co-lead as co-president. We build practical AI that plugs into how a small or mid-sized business already runs: the phone line, the document pile, and the manual steps between a booking and a paid invoice. We focus on the Greater Toronto Area, where a missed call or a slow follow-up is often a customer lost to the business down the street.
What we build
Voice agents
An AI receptionist that picks up on the first ring, 24/7, and holds a real conversation in five languages. It books appointments live on the call, hands off to a person when it should, and syncs a transcript, a summary, and lead fields to the CRM after every call.
Document intelligence
Incoming files are read, classified, and filed on arrival. Staff can ask questions of their contracts, case files, and records and get answers with citations back to the source, plus summaries and recurring reports built from the same data.
Process automation
Scheduling, invoicing, ticketing, and follow-ups that run off real events instead of reminders, connected through native CRM connectors and webhook and API workflows for everything else.
Custom AI
For workflows nothing off the shelf fits: agentic pipelines and models trained on a client's own legal, medical, or field data, built into web and mobile products from data ingestion to interface.
Who it's for
Businesses where the phone, the paperwork, or the follow-up is the bottleneck: dental, medical, and physiotherapy clinics, law and accounting firms, trades and home services, salons and med spas, real estate, auto repair, veterinary clinics, and restaurants.
My role
As a co-founder and co-president I lead business development: learning how each business actually runs and translating that workflow into a tailored AI solution. I also oversee how we contract and deliver, from service agreements and service-level commitments to the proof period we offer every new client.
Stack & Tools
Other Projects
Real-Time Obstacle Detection Dataset
Second-author benchmark paper submitted for publication in 2026: 24,326 images, 25 classes, six nano-scale YOLO detectors compared under one protocol. 83,000+ Hugging Face downloads.
Prosecuto
Built at NVIDIA Spark Hack Toronto on GB10 hardware. Owned the local-inference path — on-device llama-server and vLLM NVFP4 instead of a hosted API.
Undercut
Live used-car deal finder that flags mathematically underpriced GTA listings. Built the visualization layer and led the migration to a modular architecture.
SyncAgent
Multi-agent orchestrator that runs Claude Code, Gemini CLI, and Codex CLI on one task, coordinated through markdown files on disk. Python, zero dependencies.
Custom Quadcopter Build
End-to-end embedded build — PCB design in Altium, ArduPilot firmware, DJI flight controller integration, and full PID tuning.
ATF Robotics Cup
National championship-winning autonomous robot against a 5,000+ participant field. Lead software and systems engineer across firmware, PCBs, and competition strategy.
FIRA RoboWorldCup
2nd place nationally and a World Finals qualification. Technical operations manager, troubleshooting firmware live under competition conditions.