Our Story
Legal AI that reads your documents and knows the law. Research, contract review, compliance, and drafting for in-house and corporate legal teams.
Built for in-house counsel
Most legal AI is built by AI engineers who learned a bit of law, or by AmLaw partners building for AmLaw rates. The in-house counsel running a in-house legal team at a growth-stage company got stuck choosing between $500-a-seat tools designed for partner-track BigLaw workflows or generic ChatGPT with no grounding. Vaquill AI was founded by a lawyer (Arshita) who watched that gap widen and an engineer (Priyansh) who built the verification stack the in-house buyer actually demands.
Vaquill AI does the full job: contract review and redlining, compliance research across the complete US Code, CFR, and all 52 state and territory statute codes, AI research across 8M+ US federal and state court opinions, drafting, document comparison, due-diligence matrices, and matter management. Every answer is grounded in real authority and runs through a 4-layer citation-verification pipeline that flags anything it cannot confirm, so you know exactly what to check before it reaches your contract, advisory, or board memo.
We serve in-house legal teams first: solo GCs, in-house legal departments, and growing corporate legal teams. The product also works for solo practitioners and small firms across every practice area from transactional to litigation. Our confidentiality setup (PII anonymization before any document reaches an LLM, zero-data-retention with OpenAI and Anthropic, US data residency, no training on customer data) was built for the 2026 procurement bar, where the question shifted from “can this make us efficient” to “can this withstand scrutiny if challenged.”
Join us as we build the modern legal AI platform for in-house and corporate legal teams.
Meet Our Founders
The team building Vaquill AI, legal AI for in-house and corporate legal teams
Arshita Anand
Co-founder & CEO · Lawyer
Arshita is a lawyer who spent her early career embedded in the workflows in-house and solo legal teams actually run: contract triage, compliance gap-checks, memos to non-lawyer stakeholders, research under deadline. She came up through legal aid cells, moot courts, and clinical work, the side of the profession where you learn fast because no one else is going to clear the queue for you.
What she saw at every turn: the lean teams doing the most work were buying the worst tools. AmLaw firms had Westlaw, Lexis, and seven-figure annual budgets. The lean in-house team got quoted $500 a seat for software designed for partners or told to make do with ChatGPT. She built Vaquill AI for the lawyer on the other side of that quote.
“This is the tool I wished I had as a young lawyer. Cited authority, contract review that actually understands the playbook, compliance across 11 frameworks in one pass, all at a price an in-house team can swipe a card for.”
Priyansh Khodiyar
Co-Founder & CTO · Engineer
Priyansh built and runs the technical stack behind Vaquill AI: 3.5M+ sections of US primary law indexed across the complete US Code, the CFR, and all 52 state and territory codes, plus retrieval over 8M+ federal and state court opinions. He shipped the 4-layer citation verification pipeline (exact text match, citation check, meaning analysis, AI cross-check) that catches fabricated cases and misquoted holdings before they reach a client memo.
He owns the confidentiality setup in-house buyers grill on the first call: PII anonymization before any document reaches an LLM, zero-data-retention agreements with OpenAI and Anthropic, US data residency on AWS, AES-256 at rest, TLS 1.3 in transit, no training on customer data, DPA on request. The stack is built for the 2026 procurement question: “can this withstand scrutiny if challenged?”
Priyansh treats legal AI as an accuracy and trust problem first, a UX problem second. The site, the docs, the public statutes API, and every retrieval-grounded answer in the product run on infrastructure he architected.