Automation Engineer

I build systems that self-improve

Multi-LLM automations and AI Agents under ML.

Your manual processes become machines.

My zones of genius

Everything I build answers one question:
does it scale on its own?

"A well-designed system manages itself. Real leverage isn't effort, it's architecture."

geoany, Automation Engineer

I specialize in designing multi-LLM automation pipelines orchestrated via n8n, covering every use case and process, deploying autonomous AI agents capable of self-improving over time without human intervention.

What I've built.

Systems in production, not prototypes.

Ideas.xyz

SEO/GEO-optimized article production pipeline orchestrated via n8n to generate structured profiles of founders, startups and tools. (Zero human intervention)

→ ~$0.80 / profile · ~4 min / profile · 24/7

Ideas.xyz company database showing SEO-optimized startup profiles generated by n8n multi-LLM pipeline at $0.80 per article
Ideas.xyz founder profile page with structured JSON-LD data generated by autonomous n8n pipeline orchestrating GPT-4 and Claude

Restaurant Automation

Complete automation system for restaurant managers. Workflows eliminating most admin work: reservations, invoices, emails, Google reviews, regulatory/subsidy monitoring

→ −80% administrative tasks

BTC ↔ USDT AI Trading

Bot with calculated multi-indicators (RSI, Bollinger, F&G, whale activity...) for buy/sell/hold decisions. System with daily/weekly/monthly review to self-improve long term. Outperforms in bear: +5.59% vs market.

→ 1 decision / 3h · 0 human intervention · 24/7

BTC/USDT AI trading bot n8n workflow showing RSI, Bollinger Bands, Fear & Greed index nodes with self-improving daily and weekly review cycles

AI Agent for Content (WiP)

Vocal / Idea New YT video Intl. scraping Auto adapt to user AI Agent Questions if needed + sourced scraping V1 generated Auto angle testing ragebait, voice... User feedback Auto publish X LinkedIn Substack Medium ...

Philosophy

"I become a shareholder, not an employee of my processes."

Frequently asked questions

What is a multi-LLM automation pipeline? +

A multi-LLM automation pipeline is an n8n workflow that routes different subtasks to different AI models based on each model's strengths. GPT-4 handles unstructured document parsing while Claude manages data validation. This approach achieves 30-50% better accuracy than single-model systems.

What is n8n workflow automation? +

n8n is an open-source workflow automation platform with 400+ integrations and native AI capabilities. Unlike Zapier or Make.com, n8n can be self-hosted for full data sovereignty and supports custom code nodes. Geoany builds production n8n systems running 24/7 without human intervention.

What is an autonomous AI agent? +

An autonomous AI agent is a software system that independently plans, executes and adapts multi-step tasks using large language models as its reasoning engine. Unlike chatbots, autonomous agents use tools, access APIs and complete complex workflows without human intervention. Geoany builds these using n8n with multi-model fallback chains.

How much does automation cost? +

n8n automation projects typically range from 2,000 to 15,000 euros depending on workflow complexity and integrations. n8n is open-source and free to self-host, making it significantly more cost-effective than Zapier or Make.com for high-volume automation.

Glossary

Multi-LLM Pipeline
An automated workflow that routes different subtasks to different language models (GPT-4, Claude, Gemini) based on each model's strengths, cost and latency. Orchestrated via n8n with automatic fallback chains for reliability.
Autonomous AI Agent
A software system that independently plans and executes complex tasks using a large language model as its reasoning engine. Can call APIs, process data and make decisions without human supervision. Operates 24/7 in production.
GEO (Generative Engine Optimization)
The practice of optimizing web content to be cited by generative AI engines (ChatGPT, Perplexity, Gemini). Unlike traditional SEO, GEO optimizes for LLM citability through semantic structuring, structured data and extractable factual content.

Get in
touch.

@geoany