Cortiqa Publications

Articles & Research

In-depth perspectives on sovereign model architectures, low-latency edge inference, and agentic workflows.

Understanding Context in Conversational AI: Inside Sonre

Why traditional chat interfaces lose context over multi-turn dialogues, and how Sonre maintains persistent semantic threads.

Bringing self-healing AI coding workflows and autonomous agentic task execution directly into your local development terminal.

How we engineered a 297M parameter sovereign Small Language Model (SLM) from scratch in India, featuring 8:1 GQA and Parallel SwiGLU Attention.