Selected work

Case studies first. Each covers the problem, the system, the decisions, what broke and what came of it.

Featured

Three case studies, one per kind of work: Ownership, Systems, Applied AI.

01 · Ownership · August 2026 to present

An AI voice front desk for dental clinics

Took an AI receptionist for dental clinics from AI-scaffolded code to production, with three voice providers and per-practice tenant isolation.

Read the case study →

The path of one booking, from the call to the practice's own scheduling system.

02 · Systems · 2025 to 2026

A social and market signal intelligence backend

Built a client backend alone: it ingests Telegram, Discord and X, summarises with AI, searches semantically and raises alerts.

Read the case study →

One message, from a platform to an alert in Discord.

03 · Applied AI · 2026 to present

AI agents working inside a live ERP

Built an agent platform over an ERP: it began as expense-claim automation and became multi-company procurement and inventory intelligence.

Read the case study →

How a document reaches the ERP through an agent, and how the dashboard reads the result.

More systems

Four more case studies.

Open source

Code you can read.

Smaller builds

One line each. Work under NDA is described by function.

Research

Peer-reviewed, Springer, 2025.

Circuits, Systems, and Signal Processing (Springer), 44(8), 5852 to 5875, 2025

Evaluation of a low-cost single-lead ECG module for vascular ageing prediction and studying smoking-induced changes in ECG

My part: Data collection, the signal-processing and feature pipeline, and model training and evaluation.

DOI 10.1007/s00034-025-03048-2 · arXiv preprint · How the study was built

One recording, from capture to evaluation. I did not build the capture hardware. I collected data and built everything after it.