LexReviewer – Because "Chat with PDF" is broken for legal workflows
LangGraph agent adapts search strategy per query, but LLMs still hallucinate in contracts.

Specialized legal models topping retrieval benchmarks when general LLMs hallucinate.
Legal tech developers, AI engineers in law firms
Harvey AI · CaseText · Lexis+ AI
We make legal AI models. We recently released two state-of-the-art legal information retrieval models, Kanon 2 Embedder and Kanon 2 Reranker. Together, they rank first on Legal RAG Bench and the Massive Legal Embedding Benchmark (MLEB).
We also recently released Kanon 2 Enricher, an entirely new type of AI model capable of transforming lengthy, unstructured legal documents into highly structured knowledge graphs. We had the pleasure of having Harvey, KPMG Law, Alvarez & Marsal, Clifford Chance, Clyde & Co, Carey Olsen, Smokeball, and Moonlit be part of the closed beta for that model.
We're proud supporters of open source and maintain popular legal and AI datasets and libraries like the Open Australian Legal Corpus and the semchunk semantic chunking algorithm, together downloaded over one million times a month.
Our core mission is to solve every common data- and AI-related pain point of the legal tech industry. Uniquely, we're focused primarily on serving the legal tech industry rather than lawyers per se.
We, therefore, view folks like Harvey and Legora as customers instead of competitors.
In the few months since we've been around, we've witnessed massive growth in usage of our models by other new legal tech startups. We think our industry is only going to get bigger, particularly as more accessible legal services make their way into the hands of end consumers and enterprises instead of law firms.
We see ourselves as best placed to serve the needs of our industry given our strong experience and expertise in AI and law. I previously led all national-level AI projects at the Australian Attorney-General's Department as a senior data scientist while also holding an honors degree in law. My brother, in turn, is skilled in economics, data science, and AI.
We're currently working on scaling up our team to meet the growing demand we're seeing as well as help build out the next stage of our roadmap, which includes a first-of-a-kind knowledge graph of laws, decisions, and contracts from around the world, as well as the first legal reasoning model.
If you align with our mission and would like to partner with us or be part of our team, you can reach out at [email protected].
LangGraph agent adapts search strategy per query, but LLMs still hallucinate in contracts.
Legal RAG benchmark revealing embedding quality > LLM choice by 19-point margin.
Turns routine startup paperwork into instant PDFs or Markdown — YC-style SAFEs, NDAs, privacy policies and a few other templates generated in ~30 seconds with unlimited regenerations. Smart UX choices (no-signup preview, clear pricing, PDF + Markdown export) make it frictionless, but it's essentially an AI-templating layer limited to six doc types, so expect to send anything non-standard to a lawyer.
58-task-head model that extracts + links entities + maps doc hierarchy—no hallucinations like LLMs.
There are real engineering moves here: 33k+ pages ingested, 1024-dim BGE-M3 embeddings served locally for privacy/latency, FAISS for millisecond retrieval and a clever 'triple‑AI' failover chain (Gemini → Llama via OpenRouter → Groq) to keep demos responsive. The frontend leans into Apple-style glassmorphism with Framer Motion interactions, so it actually feels like a thought-through product rather than a hack — biggest caveat is reliance on proprietary LLMs and infrastructure complexity for anyone wanting to reproduce it.
Voice AI for websites when Voiceflow, Vapi, and Bland AI already exist.