Spellbook
Spellbook drafts, reviews, and rewrites contract language inside documents.
Overview
- Transparency
- 4 / 10
- Trust
- 96 / 100
Trains on your data
- Free
- No
- Paid
- No
- Opt-out
- Not captured
Incidents
00
Assessed SEP 21, 2026 · Checked by hand SEP 21, 2026
Spellbook confirms SOC 2, GDPR, HIPAA, provider zero data retention and Canada and US hosting; the published subprocessor list and termination deletion clause were verified.
Trust breakdown
96 / 100
Overall trust score
Data and privacy
Trains on your data
No training on user data
Storage regions
Sub-processors
Data retention
Spellbook has negotiated agreements with both OpenAI and Anthropic for zero data retention (ZDR).
Deletion: Upon termination of this Agreement, Recipient will, upon request, return or destroy Discloser's Confidential Information in its possession or control.
Powered by
Spellbook primarily uses third-party LLMs from Anthropic and OpenAI. They have explicitly stated they abandoned fine-tuning their own models and instead focus on the 'harness' around the foundation models.
Integrations and access
Integrations
Available on
Pricing
Enterprise
Custom
Pricing is not publicly available and is structured around the number of team members on your license. Customers are routed to a demo for personalized pricing. Third-party estimates for a Spellbook seat currently range from about $20 per user per month at the low end to over $500 per month at the high end. A 7-day free trial is available.
Prices as listed on SEP 21, 2026; check the vendor's page.
Moat and openness
Moat
- Proprietary Model
- Proprietary Data
- Network Effects
- Switching Costmoderate
- Unique UX
- Distributionmoderate
Spellbook's moat is primarily built on its specialized 'harness' engineering for legal workflows and strong integrations, rather than proprietary models or data. While its established customer base and tailored UX for legal professionals offer some switching costs, the reliance on third-party LLMs and lack of proprietary data limit its long-term defensibility against competitors with similar integration capabilities or superior underlying models.
Openness
- Open model weights
- Published research
- Open source contributions
- Transparency reports
- Public safety evals
Spellbook emphasizes transparency in its AI recommendations and audit trails for contract changes, allowing users to understand the reasoning behind suggestions and track all edits. However, the company does not appear to open-source its code or publish research. While it provides a trust center detailing data security protocols and LLM commitments, it lacks broader transparency reports or public safety evaluations. Pricing transparency is also noted as an area for improvement.
Timeline
- 2026-03Spellbook secured $40 million USD in debt financing from RBCx to finance acquisitions of other contract-focused legal AI companies. The company also partnered with the Canadian Bar Association (CBA) to become its exclusive provider of AI-powered contract drafting and review tools.
- 2024-01Spellbook completed a Later Stage VC (Series A) funding round.
- 2023-05Spellbook secured $10.9M in financing from Moxxie Ventures, Thomson Reuters Ventures, Inovia Capital, The LegalTech Fund, Bling Capital & others. The company also announced its rebranding from Rally to Spellbook, with plans to merge the Rally platform with Spellbook to create new AI features.
- 2022-09Spellbook launched the first generative AI tool for lawyers, preceding the public release of OpenAI's ChatGPT.
Company
Spellbook
- Founded
- 2018
- HQ
- Toronto, Ontario, Canada
- Site
- spellbook.legal
Popularity
Not disclosed
monthly visits
Notable customers
Spellbook is a leading AI-native platform in the legal technology landscape, specializing in contract drafting, review, and redlining, with strong integration into Microsoft Word and a global customer base.
Value and ROI
What it should move: It shortens contract reviews, first drafts, and redlines.
Best fit
It fits teams with repeated agreement types and established clause positions.
The catch
Suggested language can miss commercial context or conflict with the playbook. Control document access, clause approval, and final legal review.
- NEAR Foundation: Uses Spellbook to draft, review, understand and rewrite partnership agreements.[1]
- CunninghamLegal: Uses Spellbook for clause drafting, agreement review and client explanations.[2]
In our stacks for