Sovereign inference — zero external LLM calls
If your answer depends on an OpenAI round-trip, you are not sovereign.
The one-line audit
grep -r 'openai\|anthropic\|gemini' our production tree. Zero hits. No third party sees the citizen's medical query. No third party rate-limits the ministry.
Why sovereignty is the healthcare deal-breaker
A Nepal Ministry of Health cannot legally send patient-adjacent queries to a US-hosted frontier lab. Full stop. If your architecture cannot answer without that round-trip, you cannot bid on the contract.
The commercial consequence
Sovereignty is not a marketing bullet — it is a licence to operate inside government, healthcare, defence, and finance. The vendors that build for it inherit those verticals.
Why we use different words
Where the industry says LLM, we say CLLM. Where it says vector database, we say NEXUS. Where it says Chain-of-Thought, we say PRISM proof-tree. Where it says RAG, we say LATTICE. Where it says trillion-token dataset, we say Smart Router Dataset. Different words because different architecture. Read the whitepaper.