Spellbookvs
Ironclad


Ironclad: Contract lifecycle management covering execution and obligations rather than drafting assistance in Word

Contract drafting and review assistant inside Microsoft Word
As of 31 August 2026, Spellbook's pricing is not published; the vendor quotes on request. A Word add-in that drafts and reviews commercial contracts using OpenAI and Anthropic models. Softwr lists it under Legal. Spellbook is made by Spellbook (Dialog Enterprises), available on Windows, macOS, Web.
Overview
Spellbook is a Microsoft Word add-in for transactional lawyers, also available for Google Docs. It suggests clause language while drafting, flags terms that are unusual or missing in an inbound agreement, compares draft terms against market standards, and answers plain language questions about the open document. It is built by Dialog Enterprises, a Canadian company formerly called Rally, and is aimed explicitly at commercial and transactional work rather than litigation. Living inside Word rather than in a separate platform is the real design decision. Transactional drafting happens in Word, and legal AI tools mostly fail on workflow rather than capability, because a lawyer under deadline will not export a document into another system. Unusually for this market, Spellbook names the models it runs on rather than referring vaguely to artificial intelligence: it cites OpenAI GPT-5 and Anthropic Claude models, and states it has negotiated zero data retention agreements with both providers. That is a materially better disclosure position than most competitors, and it gives a firm something concrete to assess against client confidentiality terms and outside counsel guidelines, which frequently restrict sending client material to external processors. On output quality there is nothing to assess. Spellbook publishes no accuracy percentage, no precision or recall figure and no benchmark of its own product. The often-quoted claim that it is ten times more accurate came from a funding announcement and was framed as product intent, with no methodology, dataset or baseline behind it. It did not take part in the Vals Legal AI Report, the main independent lawyer-baselined benchmark, and no third-party evaluation of it has been published. Pricing is not published either: it is per seat, but the rate is behind a demo request.
The honest half
Concrete and checkable, so you can decide whether any of them matter to you. This is the half of a review a vendor will not write about Spellbook.
Cross-shopped
Each pairing was judged by two reviewers asking whether a buyer would genuinely weigh the two against each other. The ones that failed were deleted rather than published.


Ironclad: Contract lifecycle management covering execution and obligations rather than drafting assistance in Word


Luminance: Contract analysis across large existing document sets rather than help while drafting a single agreement


Clio: Practice management with document automation, for firms whose problem is matter workflow rather than drafting language
Pricing
Taken from the vendor's own pricing page. Prices move, so check before you buy.
Spellbook
On request
Capabilities
Word add-in drafting
Clause suggestions and redlines inside the document being drafted
Contract review
Flags unusual or missing provisions in an inbound agreement
Benchmarks against market standards
Compares draft terms with common market positions
Question answering
Plain language questions answered about the open contract
Named model providers
Runs on OpenAI and Anthropic models under zero data retention agreements
Answered, with sources
Each answer names the page it came from, so you can check it rather than take our word for it.
No. It publishes no accuracy figure of its own, and no third-party evaluation has been published. It did not participate in the Vals Legal AI Report, the main independent lawyer-baselined benchmark. Evaluate it on your own agreements during the trial.
Spellbook names OpenAI GPT-5 and Anthropic Claude models, and states it has zero data retention agreements with both providers. Confirm the current terms and subprocessor list against your client confidentiality obligations before use.
Pricing is per seat but is not published. The vendor quotes it after a demo, so the seat rate cannot be compared with competitors in advance.
Keep looking
Machine learning contract analysis for review, negotiation and compliance
AI research and drafting platform for large law firms, sold on enterprise-only seat pricing with no self-service tier and reported contracts from roughly $50,000 to $360,000 a year
Legal research database sold per seat per practice area, with contract value set by firm size and content modules rather than a list price
Thomson Reuters legal research platform, priced per seat with tiers from Edge to Advantage and negotiated enterprise contracts above 10 attorneys
Document lifecycle and contract intelligence platform for law firms, built through a decade of acquisitions including Kira Systems, Workshare and Doxly
Practice management with a full legal general ledger and trust accounting built in
Configurable case management for plaintiff litigation, intake and mass tort firms
Cloud e-discovery priced by data volume, with review, legal hold and case preparation in one platform
Document and email management for law firms and professional services
Risk, compliance and business intake software for professional services firms
Legal case and matter management built natively on Salesforce
Legal practice management with billing and time tracking, tiered from matter basics to full legal accounting
Consent management and website privacy compliance priced per domain by monthly consent volume
Billing, trust and general ledger accounting for small and mid-sized US law firms
Document lifecycle and contract intelligence platform for law firms, built through a decade of acquisitions including Kira Systems, Workshare and Doxly
Softwr does not host reviews and shows no star rating for Spellbook, because a rating we did not collect is not ours to publish. What is here is the pricing and platform detail from the vendor’s own pages, limitations we could state concretely, and alternatives a reviewer confirmed people weigh against it. Tell us if any of it is wrong.
What people switch to, and what they give up
Every tier, and where the cost actually lands
Put it head to head with anything we hold
Its rating, and an embed for your own site
Legal research database sold per seat per practice area, with contract value set by firm size and content modules rather than a list price
quoteLegal CRM, client intake and marketing automation platform with a 3-user minimum that sets an effective entry floor of roughly $447 a month
Per user per month, with a 3-user minimum on the entry planDocument lifecycle and contract intelligence platform for law firms, built through a decade of acquisitions including Kira Systems, Workshare and Doxly
quoteThomson Reuters legal research platform, priced per seat with tiers from Edge to Advantage and negotiated enterprise contracts above 10 attorneys
quoteImmigration case management with automated USCIS and DOL form population from a single client intake questionnaire
Per user per monthLegal practice management with billing and time tracking, tiered from matter basics to full legal accounting
Per user per monthAI research and drafting platform for large law firms, sold on enterprise-only seat pricing with no self-service tier and reported contracts from roughly $50,000 to $360,000 a year
quoteConfigurable legal practice and accounting management platform sold as two separate products, priced per user with no published rate
Per user per month