I design and ship AI agents and automation systems — n8n, Make.com, Zapier & GoHighLevel — that qualify leads, answer customers, and move data without a human touching it.
Four areas I keep coming back to — because they're where automation moves the needle most for a business.
Multi-agent systems that handle email, calendar, support, and lead qualification — built on Claude, GPT-5, and Gemini, with real memory across turns, not scripted chat.
End-to-end systems in n8n, Make.com, and Zapier that connect CRMs, inboxes, and marketing tools — so leads get followed up in seconds, not hours.
Agency-grade GHL builds — pipelines, snapshots, white-label setups, and AI chatbots wired directly into the CRM your team already runs on.
Document and site content turned into a searchable, AI-answerable knowledge base using vector embeddings — for support bots that actually know your business.
This is a simplified simulation of my real Gmail & Calendar Assistant — one goal in, the agent plans and executes the steps.
"Find tomorrow's available meeting slots and email John."
This is a simplified simulation of my real RAG Chatbot & Knowledge Base project — documents in, grounded answers out.
"What's your refund policy?"
"Refunds are available within 30 days of purchase, provided the item is unused and in its original packaging. Contact support with your order number to start a return."
Powered by RAG — answer traced back to source documentsEvery system I build follows the same layered logic — a request comes in, an AI agent reasons over it, automation carries out the steps, and the result lands somewhere your team can see it.
Something happens — a form fill, a message, a missed call.
A form submission, inbound message, missed call, or scheduled trigger fires a webhook, passing a structured payload into the pipeline.
AI reads the request and figures out what to do next.
Claude, GPT-5, or Gemini processes the payload — using function calling and structured outputs to classify, qualify, or decide the next action.
The right steps happen automatically, in the right order.
n8n, Make.com, or Zapier orchestrates branching logic, retries, and routing across connected nodes.
The AI talks to the other apps your business already uses.
REST APIs and webhooks pass authenticated requests between the AI layer and connected tools.
The record gets saved and moved to the right stage.
GoHighLevel or HubSpot's API updates the contact record, sets the pipeline stage, and triggers the next touchpoint.
Information is stored so it can be found again later.
PostgreSQL or a vector store (Pinecone) persists structured data or embeddings for retrieval.
The task gets done — no one had to do it by hand.
The pipeline resolves to a logged, auditable outcome — timestamped, with a status a human can check.
The same lead, handled two different ways.
Two things separate a real system from a demo — knowing when to ask a human, and knowing what to do when something breaks.
For anything with real stakes — money, a customer message, a record change — the system pauses for a human instead of guessing.
Good automation doesn't only handle the happy path. It knows what to do — and who to tell — when something goes wrong.
A sample of production automation systems and AI agents — full portfolio and source available on GitHub.
Multi-agent assistant that handles email and calendar actions from text or voice, with contact lookup and memory.
Syncs documents into Pinecone as embeddings, then answers questions with memory-enabled semantic search.
Answers service questions, qualifies leads, and detects booking intent — with human handoff for edge cases.
Not a list of adjectives — here's what you're actually getting.
I start with the operational bottleneck, not the tool — so the system I build actually fixes what's slowing you down, not just something automatable.
A BSc in Computer Science & Engineering behind the automation work — I understand APIs, data, and logic, not just how to drag nodes in a no-code builder.
I combine AI agents with deterministic workflow automation — using AI for judgment calls, and plain automation for everything that doesn't need it.
Discovery, design, build, test, and handover — I can take a process from "this is broken" to "this runs itself" without handing it off midway.
I'm open to remote/hybrid roles, and to automation projects for agencies and founders.