Built for clients in Australia, Europe, and the US, and most of them are still running today, answering real customers at three in the morning. Agentic systems, voice agents, document systems, Claude Code, Codex, automations and creating anything that you can dream of.
One booking and dispatch scenario. ~2,000 inbound calls a month, six technicians, every failure path handled.
A full LIVE call end to end, from builds that are operational right now.
Lawyers and doctors upload their own files and ask questions about them. Every answer cites the exact page it came from. Runs on AWS with per-user access, a full audit log, and retention rules that keep HIPAA and GDPR happy.
A German-language phone line that answers the usual questions, checks real availability, then books the caller in with one of six technicians. Writes the calendar entry, sends the confirmation text, and handles a slot vanishing halfway through the call.
A recruiting platform that rings candidates on its own, works out who is worth talking to, and hands those ones to a human. Blank page to something people can sign up and use.
vonrel.com
A booking site for a farm stay in northern Poland, shipped in both Polish and English. Not everything is backend plumbing.
ranczonadstawem.com
A lead comes in, gets researched, then called and qualified by a voice agent. It moves through the CRM with the proposal and the follow-ups written as it goes.
Pulls files from S3, chunks and embeds them, and serves the right passages before the model answers. Built, deployed and tuned solo.
Custom agents, skills and commands wired into Claude Code so it knows the codebase and the business rules before I ask it anything. The same setup runs my accounting: Stripe, Wise and Gmail in, categorised ledger and quarterly tax reports out.
A coaching and progress-tracking app built full stack for my own students. Sprints, structure and live feedback while they build their own AI systems.
vaib-pods.vercel.appAgents that take and make real phone calls for sales, support, and bookings. I set up the phone lines underneath them too, which is usually where these projects come unstuck.
Taking a job someone does by hand every day and turning it into something that runs itself. I plan for what happens when it breaks, not just when it works.
Systems that answer questions from a company's own documents and get it right, with the answer traced back to the page it came from.
The bit most AI projects live or die on. Getting reliable output every time, testing it properly, and keeping it working as models change underneath you.
I work in Claude Code and Codex every day. It is the reason a project that used to take months now takes a couple of days.
Keeping European client data in Europe, and building on AWS to a standard US healthcare clients can sign off on.
I taught high school maths before any of this, and the same skill turns out to decide whether a technical project lands. I run weekly live sessions where people build real systems alongside me, I have trained over 300 paying students, and I speak at events like the AfricAI Automation Mastermind in Cape Town. In practice it means I can sit with someone non-technical and have them actually understand the trade-off, rather than just nod at it.
A weekly live session. Everyone builds the thing on screen with me, rather than watching.