2026 · taking projects
AI services and automation, built end to end — in weeks, not months.
I lead your project from idea to launch and beyond. To move at the speed of a whole team, I use my own fleet of AI agents: they take on research, code, tests and deployment, while architecture, decisions and quality stay with me.
“I don't assemble a team for each task — I already run a fleet of AI agents. So you get the speed of a team while dealing with one person who owns the result.”
What I do
From a single automation to a turnkey app. I own the task end to end — from framing and prototype to production deployment, testing and maintenance.
AI in your workflows
Process audit, finding automation points, a fast pilot on real data and an impact estimate before scaling.
Turnkey apps & services
Building a product from prototype to production: backend, interface, inference, monitoring and operations.
Agents & automation
AI agent pipelines for routine: document processing, support, reporting, research, quality control.
Integrations & RAG
Connecting LLMs to data and systems: knowledge bases, RAG, voice, documents, vision, internal API links.
My agent fleet
Not a “developer with ChatGPT”. I run a fleet of specialised agents: each covers its own area, while I keep the architecture, quality and deadlines.
How a project runs
A transparent rhythm with short iterations. You see working results in the first week — not a deck a month later. Every result goes through multi-stage testing, including complex real-world scenarios, and my personal review before launch.
Brief & goal
I unpack the task, success metric and constraints. Scope locked.
Prototype
A working prototype on your data — I test the hypothesis for real.
MVP
A service with the key scenario, interface and basic monitoring.
Production
Real-world scenario testing, my sign-off, deployment, documentation and handover.
Maintenance
Support, improvements and scaling driven by feedback.
Cases
A few projects I built with my agent fleet. The structure and metrics are a reference for your scenario.
Knowledge-base assistant
Search and answers across 12,000 internal documents with source links and hallucination control.
Ticket processing pipeline
Classification, enrichment and routing of inbound requests by a fleet of agents with no operator in the loop.
Voice assistant
A phone bot with speech recognition, scenarios and handover of complex dialogues to a live operator.
Stack
I pick tools for the task, but lean on a proven set for speed and reliability.
Let us talk about your project
Have an AI service idea or a process that is ready to automate?
Write to me directly — I answer myself, within a day. Describe the task in two sentences and I'll come back with a timeline estimate and an approach. The first prototype is usually ready 1–2 days after the brief.