I build production AI systems and the web platforms they run on.

Built a lead generation and nurturing platform with a built-in CRM, first deployed on a live 254-apartment, A$292M residential development. Agents find and score buyer, investor and B2B leads, run personalised outreach, and nurture each lead by email, SMS, Instagram, Facebook and WhatsApp. A voice agent returns calls, DocuSign and Square close the sale, and human approval gates consequential actions. A white-label edition for other developers runs on a separate database with fictional demo data.

Outcome In production: 12,150 contacts, 8,950+ emails, 501 calls transcribed and analysed, 29 second median first response and 35 sales.

Built a personal AI layer people can open on any device. It picks the right model for each task and keeps working if a provider fails, credits at least three independent publishers in every answer and keeps customer-owned memory. Its agent builder turns one sentence into a working agent with success tests; every run is scored and weak agents are improved automatically.

Outcome A portable, invite-only personal AI layer designed around dependable answers, continuity and user ownership.

Built a venture discovery engine that tracks live market signals, generates candidate businesses, stress tests each one adversarially and re-scores every idea as new evidence arrives, backed by a financial model, legal screen and investor memo.

Outcome A self correcting pipeline that caught inflated scores, including one that fell from 91 to 61 after re-scoring.

Built a multi-agent local news pipeline for city editions with fact-checking and quality gates as release conditions, AI disclosure, and automatic unpublishing when a gate fails.

Outcome A production publishing system designed to detect, contain and recover from quality failures autonomously.

Built !syncDev to triage issues across my platforms and route each fix to the most suitable AI agent or to me, with verification gates and automatic rollback.

Outcome 1,764 issues resolved and 1,257 merged pull requests in twelve weeks.

Built a network of city weather sites across 20+ cities (including Sydney, Melbourne, Brisbane, London, New York, Los Angeles, Tokyo, Singapore, Berlin and Dubai) on one shared template. Each shows live conditions, hourly and 7 day forecasts, UV, air quality and rain radar, an automated daily briefing, a what to do today activity rating driven by the conditions, and suburb level pages. Each site hands visitors to the matching city's live things to do guide, which ingests events continuously, checks each listing against its source and drops past events automatically. Weather data from Open-Meteo, air quality from CAMS.

Outcome A repeatable city template that turns daily weather traffic into local engagement and feeds the Daily Network news editions.

Built a routing layer that keeps generation running through any single-vendor outage, matches each task to a model that meets its quality bar, and caps daily spend.

Outcome More resilient AI operations with deliberate quality and cost control built into routing decisions.

Built and shipped many production sites using AI-assisted tooling with Lovable, React and TanStack front ends, Supabase and Postgres back ends, deployed on Cloudflare.

Outcome A pragmatic delivery practice that joins product thinking, application engineering and operations.

Diagnosed and resolved production database-saturation incidents, restored coordinator and watchdog loops, and documented root cause and prevention.

Outcome Systems returned to stable operation with clearer safeguards against recurrence.