AI Transparency

AI is used to extract structured facts from documents, build timelines, cluster witness statements, surface potential contradictions, draft motions, and assemble reports. Each of these steps is a starting point for professional review — never a final product.

Analyses are anchored to the documents you upload. Findings are presented alongside citations back to the source text so that a reviewer can verify each claim. When a finding cannot be grounded in the corpus, it is suppressed or gated rather than surfaced as fact.

• AI models can make mistakes, miss context, or produce plausible-sounding but incorrect statements.
• Automated analysis is not a substitute for professional legal judgment.
• Users must verify all output against source documents and applicable law before relying on it.
• The system aims to avoid fabricating evidence or citations — if you encounter one, please report it.

You can configure API keys for AI providers you already use (OpenAI, Anthropic, Google, Groq, OpenRouter). When a personal key is active, requests for your workspace are routed directly to that provider under that provider's terms.

Nyrava does not use your case content to train general-purpose models. When third-party providers process a request, their contractual data-handling terms apply to that request.

Every output — timelines, motions, findings, reports — must be reviewed by a qualified legal professional before use in an actual matter. Nyrava is a tool for professionals, not a replacement for them.