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

Built an end-to-end system coordinating autonomous agents for generation, fact-verification, quality and geography gates, image matching and publishing. The platform runs on Supabase and Postgres with Deno edge functions and pg_cron scheduling, using evaluation gates as release conditions and self-healing that auto-unpublishes on gate failure.

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

Built a router across Anthropic, OpenAI and Google that keeps generation running through any single-vendor outage. Each task is routed to the lowest-cost model that clears its quality bar, under a per-day spend guardrail.

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

Built a bespoke CRM and lead engine end to end, including enrichment, sequencing and tracking, with human approval in the loop for consequential actions.

Outcome A private investor tool shaped around the team’s actual fundraising process.

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.