A controlled escalation in which an ONOXIA bot conversation is taken over by a human support agent, with full message history and visitor context transferred to the agent's portal session.
A request-time decision that picks the inference provider best suited for the visitor's language pair — Mistral AI in Paris for European languages (GDPR-compliant), Qwen for Chinese and other Asia-Pacific languages, Gemini Flash as a global fallback.
A per-site bundle that defines who the bot is, how it speaks, which tools it may call, and what it must refuse. Personas sit between the visitor's question and the LLM, shaping the system prompt and tool registry for every conversation on that site.
A pattern that retrieves passages from a private knowledge base before an LLM generates an answer, so responses cite your own documents instead of fabricating facts.
A server-side technique where each visitor's IP address is hashed with SHA-256 before any storage, so ONOXIA can identify abuse patterns and rate-limit without retaining personally identifiable IP data.
A chat widget loaded inside a Shadow DOM root so its styles and DOM are isolated from the host page, guaranteeing no CSS conflicts and no script collisions regardless of the host CMS or theme.
A pricing model that consumes the oldest token package first. Each ONOXIA plan ships a monthly token budget; one-time add-on packages are layered on top and depleted in first-in-first-out order, so the never-expiring add-ons are only touched when the monthly budget runs out.