About
AI automation. Built properly.
I'm Bart Porcincula. Porsync is my personal lab — AI systems built end to end as experiments, to find out what actually holds up in production: lead acquisition, agent orchestration, AI visibility, and voice agents. Everything here runs live.
The Builder
I'm a senior software engineer with a background in enterprise-grade delivery. That same discipline goes into every system here — built to ship and to maintain, not to demo. The work is grounded in two beliefs:
- ▲The hard part of AI automation is not the model. It's the surrounding systems — scraping, qualification, routing, branded delivery, audit trails, identity, and compliance. That's where the real engineering lives.
- ▲Everything here is built on standard, well-documented tools any web developer can maintain — no proprietary runtimes, no black boxes. The goal is systems that work in production and make sense to anyone who reads the code.
Built on standard, well-documented tools any web developer can maintain — so every build here makes sense to anyone who reads it, with no vendor lock-in and no black boxes.
What I Build
- 01
Lead Acquisition Engine
Finds and pre-qualifies prospects automatically — sourcing, scoring, and CRM hand-off, running daily.
- 02
Agent Operations Platform
Orchestrate AI agents that handle routine sales, marketing, and operations tasks end-to-end, with a dashboard for visibility.
- 03
AI Visibility Engine (AEO / WebMCP)
Gets a business found, cited, and acted on by AI systems like ChatGPT, Perplexity, and Claude.
- 04
AI Voice Receptionist (inbound + outbound)
Answers, books, and qualifies calls 24/7 — inbound reception and outbound campaigns.
- 05
Bespoke Experiments
Some systems started as a specific problem someone brought me — the ones that don't fit a standard shape are usually the interesting kind.
How I Work
I build these to learn what actually works — not necessarily for profit. Each system starts as a process worth automating, gets designed before it gets wired, and ships with monitoring and audit trails from day one.
Each build is a self-contained system — no ongoing platform dependency, standard tools, full documentation. Then I write it up: what worked, what broke, and the real numbers.
Remote, worldwide, async-friendly. I publish the work — the systems speak for themselves. If one of them maps to a problem you have, I'm happy to talk.