Legora vs Spellbook: how they compare in 2026
These two are often shortlisted together and they are not really the same purchase. Spellbook lives inside Microsoft Word, which for transactional drafting is the deepest integration available rather than a connector alongside the work. Legora is a separate collaborative workspace the matter team moves into. Spellbook is stronger on what decides a confidentiality review. It names OpenAI and Anthropic as its model providers and describes zero data retention precisely enough that a reader can see the mechanism, while Legora names its providers in a subprocessor list without saying which serves which feature. Spellbook also explains why its architecture reduces hallucination rather than only claiming it does. Legora's counter is contractual openness, with its terms, data processing agreement and security annex published, and a working surface built for teams rather than individuals.
At a glance
All 15 axes, side by side
The same grid applied to every vendor in the index, graded from public sources. Hover a grade to see what the letter means on that axis.
AI Centrality
How much of the product is actually AI. Whether the machine learning is the mechanism the buyer is paying for or a feature layered onto conventional software, and whether the vendor is specific about which is which.
Everything Legora sells is generative. The Agent plans and executes legal work across the platform's tools, Tabular Review extracts answers from each document into a grid, research answers questions across jurisdictions, and drafting runs in Word, Outlook and the built in editor. An orchestration layer handles tool routing, memory, model selection and guardrails beneath them. Without the models there is no product left to sell.
The models are the product. Review, Draft, Ask, Compare and the Associate agent are all generative capabilities delivered through a Word add in that exists to carry them. The company pivoted its whole business to generative AI in 2022, rebranding from Rally to Spellbook. Remove the models and there is no product, only an empty add in.
Citation Accuracy and Hallucination Disclosure
Whether the vendor publishes measured accuracy on citations and assertions, grounds output to primary sources, and says plainly what its system does when it does not know. Legal has a documented public record of fabricated citations reaching filed briefs, so an untested claim of accuracy is not evidence.
Each cell in Tabular Review expands to its reasoning and the source documents behind it, and Portal answers carry links back to the exact source. Legal research works several sources in parallel, ranks them by authority and checks each finding against primary law before the answer returns. The rebuilt research layer announced on 14 September 2026 runs on an ontology of the law that maps how authorities rank and relate, including amendments and temporal validity. Its AI native citator follows a standard set and audited by former publisher attorney editors. Legora says it has cataloged more than 50 ways AI fails at legal research without publishing the list. The layer is in limited beta, and no accuracy figure, evaluation framework or hallucination rate is published.
Grounding is real and documented, with the method described, and no figures are published. The vendor states its architecture explicitly. It does not fine tune; it connects general purpose models to proprietary market data and requires them to retrieve and cite rather than rely on learned patterns, reasoning that putting documents into a model's long term memory encourages hallucination. Compare benchmarks a clause against a stated corpus of more than 2,300 contract types and explains why differences matter, and Ask is published as producing answers with citations. The vendor also publishes educational material on hallucination risk for its users. Not located: any accuracy figure, hallucination rate, test set or evaluation for its own product. The CEO has publicly questioned outside benchmarking studies of legal AI tools while the company publishes no measurement of its own.
Autonomy and Oversight Model
What the system decides on its own, what a lawyer must approve, and whether the vendor documents where the review point sits. A tool that drafts under review and a tool that files without one are different products and different risks.
The Agent proposes a plan before it acts, carries out the work across documents, data sources and tools, checks whether it met the goal, and delivers work product into the project workspace for the lawyer's review and approval. It can also act without being asked, watching email, documents and projects and starting work when something needs attention. Tabular Review adds Mark as Reviewed, Lock Cells and Review Mode for team review, and full audit trails record every tool call, file access and agent action. ISO 42001 covers the AI management system, with human oversight named as a principle. No threshold at which the Agent stops for a person, and no route after a wrong output, is described.
A real written commitment has the models work alongside a supervising lawyer, with a working review surface and no full control structure. Associate is described as the first AI agent that can work through legal matters across several documents with the user's oversight, which puts the oversight position in the product's own headline claim. The delivery model is itself the review mechanism: output arrives as tracked redlines in a Word document that the lawyer accepts or rejects clause by clause, a concrete control point. Not located: what the agent decides on its own within a matter, the threshold at which it stops, and what happens after an output is wrong.
Operational and Outcome Evidence
Named, dated evidence that the product works in production at real firms or legal departments. Case studies with figures and identified customers count. Unattributed testimonials and launch announcements do not.
Legora counts more than 1,800 teams in over 50 markets and 100,000 lawyers on the platform. Named customers include White & Case, Crowell, Accor, Dentons Europe, Trowers & Hamlins and Grant Thornton UK, whose forensic investigations team has a published story. The customers page reports that users see a 25 percent improvement in work quality, that experienced users save 80 percent of non billable hours weekly, and that firms bill $6.4 million more per 100 lawyers a year. None of those figures carries a date, sample or method. An in house study with the analyst Ari Kaplan drew on conversations with 30 customers in nine countries.
Real deployment evidence with substance, short of the full A bar. Multiple named customer stories are published with individually attributed detail, including Dropbox with a named associate general counsel on video, Panasonic on saving three weeks building an RFP process, KMSC Law with a named partner, Alturas Capital Partners, Elevare Law and Westaway with a named managing partner. The logo wall names large enterprises including eBay, Fender, Crocs, Franklin Templeton, Hapag Lloyd, Valentino and DirecTV, and the vendor states more than 4,500 legal teams across 80 plus countries. Figures appear but attach loosely: a named partner states Spellbook helps him bill an extra hour a day, and Panasonic's three weeks is a stated saving. Not located: a dated case study carrying figures with a method a reader can assess.
Privilege and Confidentiality Posture
How client confidences are handled: attorney client privilege and work product treatment, segregation of one client matter from another, whether client data trains any model, and what the vendor commits to in writing rather than in marketing.
The general terms bar Legora from using a subscriber's confidential information to train or fine tune AI models and require the same of its subcontractors. The terms, the data processing agreement and the security measures annex are published in versions for the EU and the United States, and the annex covers least privilege access, personnel confidentiality, authorization controls and retention on customer instruction. Ethical walls and role based access are stated to keep confidential information from crossing matters or projects, on access control built on the Zanzibar authorization model, and engineers reach customer data only with the customer's written approval. Privilege and work product handling are not addressed.
Substantive published commitments stop short of the full picture. Zero data retention agreements are stated as negotiated with both named model providers, OpenAI and Anthropic, with the mechanism described precisely: customer data in requests and responses is not persisted and exists only in memory to process a request. Encryption, SSO through Microsoft Entra with enforced MFA, and audit controls are stated. Two gaps remain. Attorney client privilege and work product handling are not addressed directly in located material. Segregation between users or matters inside a customer is not documented, so for a product used by firms no walls at matter level are described.
UPL and Professional Responsibility Posture
Whether the vendor is clear that it supplies a tool rather than legal advice, who its audience is, and how it addresses unauthorized practice of law, competence and supervision duties, and jurisdiction limits. ABA Formal Opinion 512 is the reference point. Where the advice line is not the duty a product raises, the axis is read through the nearest professional duty it does raise: judicial conduct rules and the reviewing duty for products sold only to courts, and the duty to bill for time actually spent for products that draft time entries.
Legora sells to lawyers, firms and in house teams and describes the product as working with lawyers rather than replacing them, with the Agent's output delivered for a lawyer's review and approval. No position on the advice line, no treatment of competence and supervision duties and no jurisdiction limit appears in the acceptable use policy, the general terms or the product pages.
The audience is unambiguous, transactional lawyers at firms and in house teams, with a signup form that asks a prospect to confirm they are a legal professional and offers no path for non lawyers. The vendor publishes educational material engaging with a lawyer's duty of competence and the obligation to verify AI output. What is not published, after checking the site, the solutions pages, the published terms of service and the learning hub on 29 Aug 2026, is a published position on the advice line, on supervision duties as distinct from competence, or on jurisdiction limits, despite the product being sold in more than 80 countries.
AI Governance and Bias Disclosure
Published governance over model behavior: who owns it inside the vendor, what is tested before release, and what is disclosed about disparate output across matter types, parties, or populations.
Legora holds ISO 42001 for its AI management system, independently audited with ongoing surveillance, and publishes what the certification covers: how AI is designed, deployed, supervised and monitored, with human oversight and structured governance as the operating principles. No internal owner of AI governance is named, no results of testing on model behavior before release are published, and nothing covers uneven output across matter types, parties or populations.
A published governance document has real substance and outside validation, without testing results or a named owner. The vendor commissioned an independent legal opinion from CMS Law on its classification under the EU AI Act, states that it was assessed as low risk, and makes the full opinion letter downloadable from its trust portal along with the controls implemented for that classification. An outside law firm's classification of the vendor's AI system, published in full, is a governance document rather than a principles page. Not located: a named internal owner of model governance, published results of testing model behavior before release, or any disclosure about uneven output across matter types, parties or populations.
AI Safety and Data Stewardship
Retention, deletion, access control, and what happens to prompts and documents after they are processed. Whether the vendor states its subprocessors and its incident practice, or leaves the buyer to assume.
The security measures annex sets least privilege and role based access, and centrally stored logs traceable to unique usernames, with security logs kept at least 12 months. It adds data integrity signing, background checks and confidentiality agreements for staff, and retention as the customer instructs. Subscriber environments are logically separated and full production backups run every four hours. The data processing agreement has Legora report a personal data breach within 36 hours and delete or return personal data at the subscriber's choice when it ends. The subprocessor list, last updated 6 July 2026, names each provider with its purpose, data and residency, and a new subprocessor comes with 30 days to object. Penetration tests cover the full platform twice a year.
Substantive published policy covers most of the ground, and deletion is the gap. Published and specific: zero data retention at the model layer, with both providers named and the mechanism described; a complete subprocessor list with processing locations in the trust portal; AWS named as primary cloud provider; storage and processing locations stated as Canada and the US; and access control through Microsoft Entra, so a customer enforces its own authentication and MFA policy. Breach notification is addressed through implemented HIPAA Breach Notification rule controls, with signed business associate agreements downloadable, and a vulnerability disclosure policy is published. The security page and FAQ, the terms of service, the privacy policy and the trust portal entry point were searched. They showed no retention period for the vendor's own storage of documents, prompts and outputs, no customer control over that window, and no deletion commitment.
AI Liability and Recourse
What the vendor stands behind contractually when its output is wrong. Indemnities, caps, carve outs, insurance, and whether any of it is published or only reachable through a negotiated agreement.
General terms and conditions are published openly in an EU version and a version for the United States. They carry numbered liability clauses, aggregate caps that apply across the subscriber and its affiliates, a separate cap of €100,000 on beta features, and a carve out the terms call an Enhanced Claim. No indemnity for third party claims arising from output, warranty on output or insurance position is stated.
Liability is addressed only through published terms a buyer can read in advance, without a position on the exposure the product creates. Terms of service, a privacy policy and a refund policy are all published openly, and the refund policy is a published commercial commitment. Those documents, the security page and the trust portal entry point, searched, showed no indemnity to the customer for third party claims arising from output, no warranty on output, no stated liability cap figure and no insurance position. The vendor will sign a business associate agreement for protected health information, which is a regulatory undertaking rather than recourse for wrong output.
Practice Systems Integration Depth
How deeply the product reaches into the systems legal work already lives in: document management such as iManage and NetDocuments, Word and Outlook, contract lifecycle management, matter management, e-billing, and court filing systems.
Legora integrates with document management systems rather than replacing them. An iManage technology partnership works through iManage APIs, and SharePoint, Box, virtual data rooms and contract lifecycle systems feed documents in. Add ins bring the Agent and playbooks into Word and Outlook, EDGAR sits among the research sources, and MCP connectors and third party legal services feed the Agent's context. A plugin released on 17 September 2026 brings Legora's grounded answers into ChatGPT Enterprise. What each connection moves, in which direction and what an administrator configures is not documented.
Real integrations exist and are documented, short of depth. The product is delivered as a Microsoft Word add in and also runs in Google Docs, which is the deepest possible integration into the surface where transactional drafting actually happens rather than a connector alongside it. A dedicated integrations page is published, and the ACM product describes contracts arriving from email, Slack and Salesforce. Authentication integrates with Microsoft Entra. Not located: legal specific document management connectors such as iManage or NetDocuments, and per integration documentation describing what moves in which direction and what an administrator configures.
Deployment Model and Data Residency
Where the software runs and where the data sits. Multi tenant cloud, single tenant, private deployment, on premises, and whether region of residence is a published option or an enterprise conversation.
Legora runs separate arrangements for the EU, the United States and Asia Pacific. Its subprocessor list sets out hosting and AI model providers by region, Microsoft, AWS and Google among them, with EU customers' data held in the EU and EEA. Storage is tiered to data sensitivity, technical teams in the EU and the United States support local clients, and subscriber environments are logically separated. No customer selection of region inside a tier is described, and where processing happens is not separated from where data is stored.
Deployment model is stated clearly with partial residency detail. The vendor publishes that AWS is the primary cloud provider and that customer data is stored and processed in data centers in Canada and the US, with a full list of subprocessors and their locations in the trust portal. That is a real residency statement naming both jurisdictions. What is missing is customer choice and tenancy: no selectable region, no single tenant or private deployment option, and no statement of the tenancy model is published. For a vendor selling into more than 80 countries, the absence of an EU or UK processing option is a live buyer question the site does not address.
Security Certifications and Trust Center
Independent attestation a buyer can pull without a sales call: SOC 2, ISO 27001, penetration test summaries, a trust center with current reports and named scope rather than a badge image.
ISO 27001:2022 with a yearly audit, SOC 2 Type II and ISO 42001 for the AI management system are all current. The trust center at security.legora.com carries a resources section and a data flow diagram, and the security whitepapers and security measures annex are published without a gate. Penetration tests run twice a year under an assume breach method. The certifying auditor is not named.
Certification is real and stated with an open route to the evidence, without published scope. SOC 2 Type II and HIPAA are both named, and the badges on the home page link directly to named, dated resources in the trust portal rather than sitting as decorative images. The trust portal is at a stable URL and carries downloadable documents, including business associate agreements and the EU AI Act opinion letter. It works as a self serve request flow rather than a sales gate. Not located: the audit coverage period, the scope or the name of the auditing firm.
Model Supply Chain Disclosure
Which models sit underneath, whose they are, where they run, and whether the vendor commits to telling customers when that changes. A legal buyer inherits every dependency it cannot see.
The subprocessor list names Microsoft, AWS and Google for hosting, infrastructure and AI models and OpenAI for AI models, with DeepL for optional translation and Linkup Labs for web results, each with its residency. New subprocessors are announced by updating the list, with 30 days for the subscriber to object. An orchestration layer handles model selection across tasks. No model or model version is named, and nothing states which provider serves which feature.
The models underneath are named, their providers identified, where they run is stated, and the commercial terms binding them are disclosed. The vendor names GPT-5 and Claude Opus as the models powering the product on its own home page, and names OpenAI and Anthropic as the providers. It states the zero data retention agreements negotiated with each and what they mean technically, names AWS as the primary cloud provider, states processing locations as Canada and the US, and publishes a complete subprocessor list at a stable trust portal URL. Naming the specific model versions in marketing copy is what a customer inheriting the dependency needs. No explicit commitment to notify customers before the model supply chain changes is published, though the subprocessor list is where such a change would surface.
Commercial Transparency
Whether a buyer can learn what this costs without entering a sales process: published rates, the unit being charged, what sits behind an enterprise tier, and what implementation adds.
No pricing page, rate, unit of charge or tier structure is published, and the commercial route is a demo request. The general terms are published openly, so contract terms can be read before a sales conversation even though price cannot.
Pricing is gated behind a demo request while tier names and feature splits are published, so the shape is visible and the number is not. The pricing page publishes two named tiers, Law Firms and In House Teams, itemizes what each includes, states that pricing is structured around the number of team members on a license, and confirms a 7 day free trial with extended trials available for larger organizations. Free access for academic institutions is published. So a buyer learns the unit of charge and the packaging without a sales call. No figure appears at any tier, and the only route to one is a demo booking.
Firm and Practice Coverage
Who the product is actually built for. AmLaw, midlaw, small firm and solo, in house departments, government and courts, and which practice areas are supported rather than merely claimed.
Legora serves large law firms, small and mid sized firms, in house legal departments, the public sector and professional services, with solution pages for M&A, litigation, banking, insurance, private equity and tax. Multi jurisdiction and cross border work are stated strengths, with research sources across Europe and federal and state law in the United States. No firm size or practice area is named as outside its scope.
Segment and practice coverage is described with substance, without the boundaries. Two buyer segments have dedicated pages, law firms and in house legal, and six industries have their own: energy, healthcare, financial services, technology, manufacturing, and retail and consumer goods. Firm size is addressed in the trial form, from 1 to 10 through 200 plus, and the vendor states more than 4,500 teams across more than 80 countries. Practice focus is stated clearly and repeatedly as transactional and commercial legal work rather than claimed broadly, which is a real self limit. Litigation appears as an option in the signup form while nothing on the site describes litigation support, and no statement is published of which practice areas or firm sizes the product is not built for.
The 12 legal signals, side by side
Recorded rather than graded. These are the questions a practitioner has to answer before a tool touches a client matter, and the answers are taken from public material only.
Client Data in Training
Can material a lawyer puts into this product be used to train a model?
Under the heading Feedback, Usage Data and no training, Legora's general terms bar it from using a subscriber's confidential information to train or fine tune AI models and bar its subcontractors from doing so. Legora may use usage data to develop and improve the services, and shares it outside the company only when aggregated and anonymized. The home page and security page repeat the commitment as zero AI training on customer data.
The vendor states plainly that zero data retention means its model providers never learn from, train on or store customer data, and the security FAQ describes the mechanism: agreements negotiated with OpenAI and Anthropic under which customer data in requests and responses is not persisted and exists only in memory to process a request. The commitment as located covers the model providers specifically and sits on a public security page and pricing page rather than in a term of the published customer agreement, which was searched on 29 Aug 2026.
No separate statement was located as to whether the vendor itself trains on customer content, as distinct from its providers.
Prompt and Output Retention
How long does the product keep what a lawyer typed, and can that be set to zero?
Section 17 of the security measures annex, dated 31 January 2025, keeps personal data under whatever retention the subscriber instructs during the data processing agreement, and clause 11 of that agreement governs return or deletion after it ends. No default retention period or zero retention setting is published. Backups of the full production environment run every four hours, and each subscriber's environment stays logically separate.
At the model provider layer the answer is specific and zero: data in requests and responses is not persisted and exists only in memory. That is a real published retention position for the part of the pipeline buyers ask about most. The security page, the terms of service, the privacy policy and the trust portal entry point, checked on 29 Aug 2026, say nothing about how long the vendor itself keeps prompts, documents and outputs in its own systems, whether a customer controls that window, or whether deletion is available. Retention is answered for one layer and given no period for the other.
Ethical Walls and Matter Segregation
Does retrieval respect the firm’s ethical walls, or can the model read across them?
Ethical walls and role based access control keep confidential information from crossing matters or projects, and full audit trails record every tool call, file access and agent action. Access control is built on the Zanzibar authorization model. How a wall is set up, and whether retrieval applies document management permissions per user at query time, is not described.
Searched the security page, the integrations page, the published terms of service and the trust portal entry point on 29 Aug 2026. No vendor material addresses ethical walls or segregation between users or matters. Authentication runs through Microsoft Entra, so a firm enforces its own identity policy at sign in, but that governs who can open the add in rather than what the product may retrieve per user. No legal document management integration was located whose permissions retrieval could inherit at query time. For a product sold to law firms this is the applicable standard and it is not addressed.
Third Party Request and Subpoena Notice
If someone subpoenas the vendor for a firm’s data, does the firm hear about it first?
Legora's general terms let a party disclose confidential information when law or an order of an authority, regulator or court compels it. The compelled party gives the other notice of the proceeding where the law allows and cooperates in seeking confidential treatment. The data processing agreement adds notice of any communication with a data protection authority about Legora's processing. No transparency report is published.
Searched the published terms of service, the privacy policy, the security page and FAQ, and the trust portal entry point on 29 Aug 2026. No clause committing to notify a customer of a government or law enforcement request for their data was located, and no transparency report was located. This records a search across the published documents that did not surface the clause rather than a reading of every document end to end.
Primary Law Corpus Provenance
Where does the law in this product come from, and does the vendor have the right to use it?
Legora names the sources behind its research. Federal law and all 50 states in the United States are hosted on Legora, beside SEC EDGAR. European sources include France's Cour de cassation, Germany's federal statutes, Sweden's court portal, Lovdata, Retsinformation, Finland's legal database and Portugal's official gazette, and content partnerships bring in publishers. The Qura acquisition adds a Swedish database of case law, legislation and regulation. No license basis or update lag is stated for any source.
The data here is contract market data rather than primary law, which suits a transactional product. Coverage is quantified: Compare benchmarks a clause against a stated more than 2,300 contract types and thousands of similar agreements, and the vendor describes the architecture as retrieving from proprietary market data sources and citing them. What is not published is where that market data comes from, on what rights basis it was assembled, or how current it is.
Searched the Compare feature page, the clause index, the state of contracts report page and the security pages on 29 Aug 2026.
Good Law Verification
Does the product tell you when the authority it just cited has been overruled?
Legora is building its own AI native citator on an ontology of the law, announced on 14 September 2026. The ontology captures the hierarchy of authority, how sources relate and temporal validity, so an amended rule or an overruled case is recognized as such, and former publisher attorney editors set and audit the standard. The technology comes from the Qura and Wexler acquisitions. The citator is in limited beta, with general availability planned for the fourth quarter of 2026, and no coverage figure or error rate is published.
Searched the site, the Ask and Compare feature pages, the learning hub and the help center entry point on 29 Aug 2026. No material was located addressing whether authority returned carries a treatment signal or whether subsequent history is checked, and no commercial citator license was located. This is a transactional contract product whose grounding data is contract market data rather than case law, so a citator is largely outside its design. The absence is recorded as found and should be read against what the product is for.
Refusal and Uncertainty Behavior
What does the product do when the answer is not in the corpus?
The Agent checks whether it met the goal and loops back to adjust, and research ranks sources by authority before answering. No explicit no answer path, abstention behavior or confidence value shown to the user is described.
Searched the site, the feature pages, the learning hub and the help center entry point on 29 Aug 2026. No published material describes what the product does when it cannot ground an answer, and no explicit path for declining to answer or confidence signal shown to the user was located. The vendor publishes a clear architectural position that models should retrieve and cite rather than rely on learned patterns. That concerns how an answer is grounded, not what happens when nothing supports one.
Fabricated Citation Record
Does a public court record exist addressing fabricated or hallucinated legal citations in output from this product?
The AI Hallucination Cases database maintained by Damien Charlotin, which records court decisions worldwide that address hallucinated AI content and the tool involved where known, has no entry naming Legora or Leya. Legora's research checks findings against primary law, and its Tabular Review links every answer to the document it came from.
No court order, opinion or disciplinary record naming this product has been located as of 29 Aug 2026. Instrument searched: the AI Hallucination Cases database maintained by Damien Charlotin, which tracks court decisions worldwide involving AI generated hallucinated content and records the AI tool implicated where it is known. Also checked published 2026 sanctions summaries and secondary sanctions trackers. The entries located name filers, and in some rows other products, rather than this one.
This is a statement about the public record on the date shown and not a clearance. Note that this vendor publishes its own editorial content about AI hallucination sanctions, which surfaces in searches for its name and is not a record about the product. Note also that the product is transactional rather than litigation facing, so its output is less likely to reach a court filing in the first place.
Bar Guidance Alignment
Has the vendor engaged in public with the ethics opinions its buyers are bound by?
Legora publishes material on its own AI governance and ISO 42001 certification, and none of it engages ABA Formal Opinion 512, a state bar opinion or national bar guidance on lawyers' use of AI.
Public materials refer to professional responsibility in general terms without naming guidance. The vendor publishes substantial educational content on hallucination risk that engages with a lawyer's duty of competence and candor to the court and the obligation to verify AI output. It is named exclusive AI partner of the Canadian Bar Association, which is a relationship with a bar association rather than engagement with its guidance.
The site, the learning hub, the blog and the guides and reports index, searched on 29 Aug 2026, showed no engagement with a named ethics opinion, including ABA Formal Opinion 512, any state bar guidance, or any Canadian law society guidance.
Billing and Fee Posture
Does the vendor address what happens to the bill when the work takes an hour instead of six?
Legora sells to law firms and in house teams, and its customers page reports 80 percent of non billable hours saved weekly by experienced users and $6.4 million in additional billing per 100 lawyers a year. The small and mid sized firm page pitches more matters handled without more headcount. No record of AI assisted work by matter for fee purposes, and no billing or client disclosure guidance, is offered.
Savings are claimed with nothing published on the client's side, and the framing runs the other way. A published customer quote from a named partner says the product probably helps him bill an extra hour a day. The pricing page is headed on boosting profitability, alongside a published return on investment calculator and repeated claims of drafting ten times faster. The site, the pricing page, the customer stories and the learning hub, searched on 29 Aug 2026, showed no record of AI assisted work for each matter intended for fee purposes and no guidance on billing, fees or disclosure to clients.
Ethics guidance is direct that a lawyer bills for time actually spent, and here the vendor publishes a claim about billing more hours.
Outside Counsel Guideline Readiness
Can a firm get this vendor through a client’s AI clause without a bespoke negotiation?
Legora publishes its subprocessor list by region, last updated 6 July 2026, naming Microsoft, AWS, Google and OpenAI as AI model and hosting providers with their purpose, data categories and residency, and offers email updates. Its general terms, data processing agreement, security measures annex and acceptable use policy are published without a gate. No client facing consent or notice pack is offered, and trust center documents come through a request.
A firm can assemble most of what a client AI clause asks for without a sales conversation. A trust portal at a stable URL publishes a complete subprocessor list with processing locations, the named model providers with the zero data retention terms binding them, a dated SOC 2 Type II resource, a HIPAA resource, signed business associate agreements from vendors handling protected health information, and an independent EU AI Act classification opinion from CMS Law.
The material is a self serve portal rather than a consent or notification pack a firm could forward to its client as assembled, and no such pack was located as of 29 Aug 2026.
Court Disclosure Support
If a judge’s standing order requires an AI disclosure, can the product produce one?
Full audit trails record every tool call, file access and agent action, Tabular Review cells link to their source documents, and Portal answers cite the exact source. No export for each document records the model used and the human verification, and no court disclosure template is offered.
Searched the site, the feature pages, the security page and the help center entry point on 29 Aug 2026. The vendor states audit controls exist and Ask is published as returning answers with citations, but no per document export covering model used, sources retrieved and human verification together was located, and no disclosure or certification support material was located. Noted for context: this is a transactional drafting product whose output is contracts rather than court filings, so a judicial AI disclosure order is less likely to reach it. Recorded as found.
The questions both sides leave open
Derived from the records above rather than written, so it cannot favor either vendor. Take these into both conversations and ask each side the same question.
- Refusal and Uncertainty Behavior
Which one fits
Choose Legora if
- Your work is document review and diligence across a matter team rather than clause level drafting by one lawyer. Tabular Review turns large document sets into a structured grid with every cell linked to its source, which is a different job from redlining in Word.
- You want the contract before the conversation. Legora publishes general terms in EU and US versions, a data processing agreement and a security measures annex openly, so they can be read before a sales process starts.
- Your matters are cross border and you want a vendor that states work across jurisdictions as a design strength rather than a supported case.
Choose Spellbook if
- Your lawyers draft in Word and will not move. Spellbook is delivered as a Word add in and also runs in Google Docs, so output arrives as tracked redlines in the document rather than in a separate application to copy from.
- You need to know which models touch your client data. Spellbook names OpenAI and Anthropic, states zero data retention agreements with both and describes the mechanism precisely. Legora names its providers only in a subprocessor list.
- You want the vendor's own explanation of why its architecture is less likely to hallucinate. Spellbook states that it does not fine tune, and requires models to fetch and cite rather than rely on learned patterns, on the stated reasoning that putting documents into long term memory encourages fabrication.
In summary
Legora
Legora is a collaborative AI workspace for law firms and in house legal teams, built around a shared surface where the matter team and the AI work together, with Tabular Review linking every review cell to its source. According to the AI Legal Index, its strongest feature for a buyer is contractual openness. General terms in EU and US versions, a data processing agreement and a security measures annex are published rather than gated, alongside an ISO 42001 certification and a stated base of more than 1,800 teams across more than 50 markets. It publishes no accuracy measurement and names its model providers only in its subprocessor list.
Spellbook
Spellbook is AI contract review and drafting for transactional lawyers, delivered primarily as a Microsoft Word add in and also working in Google Docs, with Review, Draft and Playbooks as core features. According to the AI Legal Index, its case rests on the model supply chain: it names OpenAI and Anthropic as providers and states zero data retention agreements with both, describing the mechanism precisely enough to verify. It publishes its architectural reasoning openly, stating that it does not fine tune and instead requires models to fetch and cite. It states more than 4,500 teams across 80 plus countries, and publishes tier names without a rate.
Questions buyers ask
Legora vs Spellbook: which should a firm choose?
They are not the same purchase. Spellbook is a drafting surface inside Microsoft Word and Google Docs, aimed at transactional lawyers redlining contracts. Legora is a separate collaborative workspace built for a matter team doing review and diligence together. Spellbook publishes more about its models and its pricing. From the AI Legal Index, based on each vendor's own published materials as of October 13, 2026. No vendor pays for placement.
Which one names the AI models it uses?
Spellbook does. It names OpenAI and Anthropic as its model providers and states negotiated zero data retention agreements with both, describing the mechanism precisely: customer data in requests and responses is not persisted and exists only in memory to process a request. Legora lists Microsoft, AWS, Google and OpenAI as model providers in its subprocessor list. From the AI Legal Index, based on each vendor's own published materials as of October 13, 2026. No vendor pays for placement.
Does Spellbook work inside Microsoft Word?
Yes, and that is the point of the product. Spellbook is delivered primarily as a Word add in and also runs in Google Docs, so review output arrives as tracked redlines in the document a lawyer is already working in. Legora also ships a Word add in for drafting and redlining, but its main surface is its own collaborative workspace rather than the document. From the AI Legal Index, based on each vendor's own published materials as of October 13, 2026. No vendor pays for placement.
Do either of them publish a price?
Partly. Spellbook publishes two named tiers, Law Firms and In House Teams, itemizes what each includes, states that pricing is structured around the number of team members on a license, and confirms a seven day free trial, but does not publish a rate. Legora publishes no pricing page, no rate, no unit of charge and no tier structure. Spellbook discloses more of its commercial structure, and neither publishes a figure. From the AI Legal Index, based on each vendor's own published materials as of October 13, 2026. No vendor pays for placement.
What do Legora and Spellbook both leave unpublished?
Neither publishes a position on liability or recourse when an output is wrong. Neither publishes a position on the advice line, on competence and supervision duties, or on jurisdiction limits, despite both selling to lawyers. Neither states which firm sizes or practice areas the product is not built for. From the AI Legal Index, based on each vendor's own published materials as of October 13, 2026. No vendor pays for placement.
Neither vendor paid for inclusion, placement or a grade, and neither reviewed this page before it published. Everything on it comes from public material on the dates shown. How the index grades.
These products overlap on contract work but are not built for the same unit of work, so a feature by feature reading will mislead. Spellbook is a drafting surface inside Word, and Legora is a review and collaboration workspace. Setting them side by side makes the disclosure gap visible, but the fit comes down to how your team works. Both tie output to its source: Legora links every Tabular Review cell to a document, and Spellbook requires models to fetch and cite. Legora's subprocessor list names its model providers but not the models or which feature each serves. Neither vendor reviewed this page.