Skip to main content
All work
Status: Led At Oracom Intelligence

Oracom AI platform: from call center to AI product

Principal architect and hands-on builder of an AI communication platform, from the first stack decision to launch-ready. Now leading the team that builds it.

  • TypeScript
  • Nuxt
  • Tailwind CSS
  • Node.js
  • NestJS
  • PostgreSQL
  • Agentic AI
  • RAG
  1. Step 1: A situation comes in
  2. Step 2: The matching flow, defined in the builder
  3. Step 3: The AI acts as the flow says
How the agent flow builder shapes the assistant's behaviour. Conceptual, no internals.

Context

When I joined Oracom GmbH in 2024 it was a call center. Since then it has grown into a company that builds AI communication products: voice and chat bots, smart assistants, and mail automation. That platform had to be built from zero.

My role

Principal architect and hands-on builder, from tech-stack decisions to production code. Since July 2026 I lead Oracom Intelligence, the company's IT department: I report to the CEO, set the roadmap with them, and own architecture, product decisions, and the team of five developers.

What I built and decided

  • Chose the tech stack and set the platform architecture.
  • Built an agent flow builder that defines how the AI handles specific situations, and later refactored it completely.
  • Refactored the delivery pipeline for on-site assistant devices.
  • Designed the document upload, embedding, and retrieval pipeline and coached a teammate to build it.
  • Leading the infrastructure rebuild toward zero downtime, autoscaling, and continuous delivery (in progress).

Outcome

The platform went from nothing to launch-ready and is now in the pre-sales phase. It has no customer usage numbers yet, so this page shows none.

What I'd do next

Finish the infrastructure rebuild so every release ships without downtime, then measure real usage once the first customers are live and let that data drive the roadmap.