About

A practical AI cooking system, not a recipe content farm.

My Royal Chef AI combines browser-native inference with cloud models so common cooking questions feel immediate and complex ones still go deep. The product is built for utility, speed, and low-friction decision making in the kitchen.

Platform

What this is.

Core idea

Context-aware cooking help.

It is not a static recipe search page. It understands ingredients, constraints, time, and skill level so the answer changes with the situation.

Built by

Aporia Systems

Created by Yunus Emre Vurgun and Yusuf Ceylan. The focus is practical software with clear systems thinking, not decorative product noise.

Common cooking questions are handled by the local knowledge base for instant responses, while complex requests route to cloud LLMs with deeper culinary reasoning.

Architecture

How a request moves through the system.

1. Input

Text, audio, or image

The interface accepts the form of input that fits the moment.

2. Knowledge layer

Local KB match

Familiar, high-confidence questions resolve instantly from the structured knowledge base without cloud latency.

3. Cloud routing

LLM processing

Complex requests route to Meta Llama 3.1 70B for deep recipe generation, planning, or reasoning.

4. Specialized models

Multimodal fallback

Audio transcribes via Whisper, images analyzed via Llama 3.2 Vision, and complex recipes via Llama 3.1 70B with automatic fallback models.

5. Context shaping

Mode-aware prompting

The request is framed differently for recipes, shopping, planning, and general guidance.

6. Persistence

History and saved recipes

Useful outputs are stored for continuity, personalization, and follow-up work.

Principles

Product rules that shape the interface.

Speed first

Simple tasks should feel immediate. If a question can be answered locally, it should not wait on the network.

Multimodal by default

Typing, speaking, and image input are part of the same workflow instead of separate tools.

No content bloat

No forced reading, no engagement bait, and no extra narrative before the useful answer.

Transparent AI boundaries

The system should make it clear when an answer is instant and local versus slower and cloud-dependent.

Team

Who is building it.

Systems

Yunus Emre Vurgun

Architecture, machine learning integration, infrastructure, networking, and security.

Backend and data

Yusuf Ceylan

Data pipelines, analysis systems, and backend development with a strong operational mindset.

Contact

Need to reach the team?

Use the contact page for product questions, feedback, and partnership inquiries.