AI contract drafting and review platform for legal teams
Spellbook is a Microsoft Word-integrated AI platform for contract work, adopted by 4,000+ in-house legal teams and law firms. The stack—OpenAI, Anthropic, React, Node.js, MongoDB, AWS—reflects a consumer-grade product philosophy (frontend-first, serverless infrastructure). Active hiring is skewed heavily toward sales (11 roles) and marketing (3) relative to engineering (5), signaling a shift from product-market fit to revenue acceleration. Security investment (penetration tests, threat modeling, bug bounties) is front-and-center, critical for a product handling sensitive legal documents.
Spellbook helps legal teams automate contract drafting, review, and analysis within their existing Microsoft Word workflows. The product suite includes contract review with compliance checks and redline suggestions, a query interface for extracting answers from contracts with citations, real-time market-data comparison tools, an AI agent for multi-document drafting (Spellbook Associate), and intake automation (Spellbook Greenlight). Customers range from in-house legal departments at mid-market and enterprise companies to law firms. The company is based in Toronto and operates across Canada, the United States, and Australia.
Spellbook runs on OpenAI and Anthropic LLMs, React and TypeScript on the frontend, Node.js and Express for backend services, MongoDB for data storage, and AWS (including CDK, Glue, Athena) for infrastructure. Data pipelines use dbt, Snowflake, and Dagster; observability via Datadog and Looker.
Current initiatives include lead generation and outbound sales motions, training and automation playbooks for legal teams, new product features, security hardening (penetration tests, threat modeling), and expansion playbooks. The company is also focused on moving from early traction to category leadership and improving brand visibility.
Other companies in the same industry, closest in size
Spellbook's technology stack, projects, and hiring signals are inferred from public hiring and company data — career pages, public listings, and company web presence — then clustered and de-duplicated. Figures are estimates that refresh over time. Read our full methodology →
This is not an official vendor or customer list. It is a technology-adoption signal inferred from public data, intended for B2B research.