CAPABILITY · AI

AI as a system layer

The model is not the product. It is a layer inside a system.

I work with LLMs, agents, self-hosted models (vLLM, Qwen, LLaMA), APIs and knowledge systems. The order is always the same: data, context, model, reasoning, decision, automation. Prompt engineering and RAG exist where the domain has first been structured.

01

Models in the right place

Self-hosted when control and cost matter. APIs when the problem justifies them.

02

Agents with limits

An agent is useful if it has a task, a context and a point where it stops.

03

Knowledge before the prompt

Retrieval over normalised data. A prompt does not repair a messy domain.

The architecture

  1. 01 Data
  2. 02 Context
  3. 03 Model
  4. 04 Reasoning
  5. 05 Decision
  6. 06 Automation

Have something that needs to become real?

Tell me the starting point: a problem, an idea, a process or a brand. You don’t need a perfect brief — just know what needs to change.

WhatsApp