Oscar Simone System Builder
IT EN Start a project

CAPABILITY · AI

AI as a system layer

A model becomes useful when it operates as a product layer within defined rules and boundaries.

I work with LLMs, agents, self-hosted models (vLLM, Qwen, LLaMA), APIs and knowledge systems. The sequence is always the same: data, context, model, reasoning, decision, automation. I use prompt engineering and RAG only after the domain has 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

Technologies

  • vLLM
  • Qwen
  • LLaMA
  • Python
  • FastAPI

Projects

Services built on this capability

Project / Start

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