Skip to content

002_AGENTS.MCP

Put AI into your product. Not just on the roadmap.

Chatbots that know your docs. Agents that do the boring work. AI features your users actually use. Prototyped in days, production-ready in weeks.

This is for you if… 👇

  • ✓"We should do something with AI" has been on the agenda for months
  • ✓Your team copies, pastes and summarises all day
  • ✓You ran a pilot, and nobody uses it
  • ✓You want AI in your product, but your team is busy

Let’s be honest

Building an impressive AI demo takes an afternoon.

Getting it to work on Monday morning, with real users, messy data and a CFO asking about token costs? That’s the actual job.

That’s the part I love. ❤️

What I build

✅ AI features inside your product: smart search, assistants, summaries, generation.

✅ AI agents that read emails, tickets or documents and put the results where they belong.

✅ MCP servers that give AI assistants safe, typed access to your systems.

✅ Automations in n8n your team can see and change themselves.

How it works

Day 1: We pick one use case. Not ten.

Week 1: You click through a first working version on your real data.

Weeks 2–6: Weekly iterations. Then honest numbers, and a clear decision: scale it, hand it over, or kill it cheaply.

Proof

Voice agents and AI portraits for a telco’s flagship stores. An MCP-powered concierge. A live AI art installation.

Different problems. Same approach: ship early, learn fast.

Proof, not promises

LLM & Agents Telco brand (via agency) · 2026

Generative AI Experience Hub for Flagship Stores

From Electron prototype to multi-store web app with voice agents & generative portraits.

LLM & Agents Mobility R&D project · 2026

MCP-Powered Mobility Concierge

A typed MCP server + n8n agent on Gemini that compares car, bike & walking routes from plain language.

Questions? Answered.

How fast is "fast"?

+

A first working AI prototype usually exists within days. A full sprint with real users and honest numbers takes 4–6 weeks.

What is MCP (Model Context Protocol)?

+

An open standard that lets AI assistants use your tools and data through one interface. Build one MCP server for your system, and Claude, ChatGPT or n8n can all use it.

Which AI models do you use?

+

Whatever fits: Anthropic Claude, OpenAI, Google Gemini or open-weight models hosted in the EU. Model-agnostic, so switching stays cheap.

Is this GDPR-compliant?

+

It's part of the architecture from day one: EU hosting or self-hosted models where needed, data minimisation, no training on your data. I work alongside your DPO.

Also on the menu

042_NEXT_STEP.SH

Got something to build? Let's ship it. Fast.

30 minutes. No sales script. You tell me what you want to build. I tell you honestly how fast we can get there, and what it takes.

Prefer to chat first? Send me a DM on LinkedIn or email me.