Corpus Law AI

Built by lawyers and engineers who understand both worlds.

Preceda is India's most intelligent legal AI agent — the flagship product of Corpus Law AI. We started with Indian law because it is where the gap between what technology can do and what practitioners actually have is the widest.

The team

Our Chief Legal Officer has spent 35 years before the Delhi High Court and the Supreme Court of India — constitutional, commercial, criminal. He has litigated the matters that set precedent, and every product decision at Preceda runs through that experience.

Our CEO has built platforms and led engineering teams for S&P 500 companies and institutional investment firms managing over $100 billion in assets. Our CTO engineered high-frequency options pricing and real-time market data systems at trading firms in Hong Kong and New York.

The problem

Legal research in India has long relied on databases that prioritize volume over accuracy. Citations are often unverified. Case names are garbled from OCR artifacts. Metadata is incomplete or wrong. Lawyers spend hours cross-checking references that should be trustworthy out of the box.

The tools available from Western legal tech companies are priced for large firms and built for systems that do not map to Indian legal practice. Indian platforms prioritize volume over accuracy. There has been no AI agent that understands Indian courts deeply enough to draft court-ready documents, profile judges, and verify citations — until now.

What we built

Preceda is India's most intelligent legal AI agent. The corpus covers Indian case law comprehensively — Supreme Court, every High Court, and key tribunals — with a verified citation graph where every reference is checked against the actual corpus, classified by treatment, and scored for authority. Canada, US, and UK case law is included for cross-border citation tracing.

The AI matter agent drafts court-ready legal documents with 29 specialized tools — searching Indian case law, verifying authorities, checking limitation periods, computing court fees, analyzing judge patterns, and producing bail applications, writs, appeals, and legal notices grounded in verified Indian law.

Intelligence profiles for over 30,000 Indian advocates and 22,000 judges provide win rates, bail grant rates, citation authority scores, and disposition speed — derived entirely from case data, not self-reported.

The technology

We built the first retrieval-optimized embedding model for Indian law — trained on 637,000+ citation-graph-derived pairs across 13 Indian citation formats. The model runs locally via ONNX at zero marginal cost, with no API dependency.

Citation resolution uses deterministic patterns across 40+ jurisdiction-specific formats, not language model guessing. Treatment classification covers 366,000+ edges — followed, distinguished, overruled, applied. PageRank authority scoring ensures landmark decisions surface above semantically similar but obscure orders.

The entire system is built for legal accuracy at scale: verified citations, deduplicated corpora, repealed law detection, and OCR artifact correction across 3.5 million cases.

Corpus Law AI

Preceda is our first product — and we believe it is the most intelligent legal AI agent available in India today. The citation graph and intelligence layer we have built are the foundation for a platform where accuracy is not optional and hallucination is malpractice.