Legora vs Spellbook: how they compare in 2026

The models are the product. The workspace is AI native rather than a document system with a model attached, and every surface the vendor sells, review, drafting, research and workflows, is a generative capability. Remove the models and nothing remains 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.

Grounding is claimed in vendor material, which describes reliable and verifiable answers and cells linked to their source. Searched the vendor site, blog, newsroom and trust center on 29 Aug 2026 and located no published accuracy measurement, no evaluation framework, no hallucination rate and no description of the retrieval method. Third party directories describe a citation verification capability, which is not vendor material and does not move this axis.

Grounding is real and documented with the method described, short of published figures. The vendor states its architecture explicitly and unusually: it does not fine tune, it connects general purpose models to proprietary market data and requires them to fetch and cite rather than rely on learned patterns, on the stated 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 aimed at its own users. Not located as of 29 Aug 2026: any accuracy figure, hallucination rate, test set or evaluation for its own product. Worth noting the CEO has publicly questioned third party benchmarking studies of legal AI tools while the company publishes no measurement of its own.

Human oversight is asserted as a governing principle in vendor material and is covered in the abstract by an ISO 42001 certification of the AI management system. What is not published is the mechanism: where the review point sits, what an agentic workflow does on its own, at what threshold it stops, and what a supervising lawyer must approve. Searched the vendor site, blog and trust center on 29 Aug 2026. Oversight appears as a stated principle rather than a described control.

A real written commitment that the models work alongside a supervising lawyer, with a genuine review surface, short of the full control structure. Associate is described as the first AI agent that can work through multi document legal matters with your oversight, which states the oversight position in the product's own headline claim. The delivery model is itself the review mechanism: output arrives as tracked redlines inside a Word document the lawyer accepts or rejects clause by clause, which is a more concrete control point than most of this market publishes. Not located as of 29 Aug 2026: what the agent decides on its own within a matter, the threshold at which it stops, and what happens after an output is wrong.

Named customers appear in vendor material, including a published Grant Thornton UK forensic investigations story, and the vendor states more than 1,000 customers across 50 plus markets. Additional named users including Cleary Gottlieb, Goodwin, Linklaters, White and Case, Dentons and Barclays appear in vendor recruiting material. Not located as of 29 Aug 2026: dated outcome figures with a method a reader could assess, which is what separates this from an A.

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 as of 29 Aug 2026: a dated case study carrying figures with a method a reader can assess.

Substantive published commitments, and unusually for this market they sit in openly published contract documents rather than only on a trust page: general terms and conditions in EU and US versions, a data processing agreement, and a security measures annex covering least privilege access, personnel confidentiality obligations, authorization controls and retention on customer instruction. The security page states the vendor will not use customer data to train or fine tune models. Two gaps hold this off an A. Attorney client privilege and work product handling is not addressed directly in located material, and matter level segregation between users is not documented.

Substantive published commitments, 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. That is a stronger and more specific statement than most of this market publishes. Encryption, SSO through Microsoft Entra with enforced MFA, and audit controls are stated. Two gaps hold this off an A. Attorney client privilege and work product handling is not addressed directly in located material. Segregation between users or matters inside a customer is not documented, and for a firm facing product the applicable standard under the amended band is matter level walls.

The intended audience is unambiguously lawyers, firms and in house teams, and vendor material describes the product as working with lawyers rather than replacing them. Searched the vendor site, the published acceptable use policy, the general terms and the blog on 29 Aug 2026 and located no published position on the advice line, no treatment of competence and supervision duties, and no statement of jurisdiction limits.

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 was not located, 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.

Holds an ISO 42001 certification covering 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 named as the operating principles. That is a published governance framework with real substance and independent validation, which is rare in this market. Not located as of 29 Aug 2026: a named internal owner of AI governance, published pre release testing results for model behaviour, or any disclosure about uneven output across matter types, parties or populations.

A published governance framework with real substance and independent validation, short of testing results or a named owner. The vendor commissioned and publishes an independent legal opinion from CMS Law on its classification under the EU AI Act, states 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. Commissioning an outside law firm to classify your own AI system and then publishing the letter is a governance artifact rather than a principles page, and no other vendor on this index has published one. Not located as of 29 Aug 2026: a named internal owner of model governance, published pre release testing results for model behaviour, or any disclosure about uneven output across matter types, parties or populations.

The published security measures annex covers access on a least privilege and role based model, centrally stored logs traceable to unique usernames with security logs retained at least 12 months, data integrity signing, personnel background checks and confidentiality agreements, and retention set by customer instruction. The published data processing agreement commits the vendor to assist with the customer's own breach notification obligations, so incident practice is addressed. ISO 27001:2022 is audited yearly. Not located as of 29 Aug 2026: a current named subprocessor list, which is the remaining element of the A bar.

Substantive published policy covering most of the ground, short of the full set. Published and specific: zero data retention at the model layer with both providers named and the mechanism described, a complete third party 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, access control through Microsoft Entra so a customer enforces its own authentication and MFA policy, breach notification addressed through implemented HIPAA Breach Notification rule controls with signed business associate agreements downloadable, and a published vulnerability disclosure policy. What holds this off an A is deletion, which the A band requires alongside the rest: searched the security page and FAQ, the published terms of service, the privacy policy and the trust portal entry point on 29 Aug 2026 and located no stated retention period for the vendor's own storage of documents, prompts and outputs, no customer control over that window, and no deletion commitment. This record's own prompt-and-output-retention signal row records the same gap.

A real published position, which is uncommon here. General terms and conditions are published openly in EU and US versions and carry numbered liability clauses, aggregate caps that apply across the subscriber and its affiliates, a separate cap of 100,000 Euro on beta features, and a carve out concept the terms call an Enhanced Claim. A buyer can read the allocation of loss before entering a sales process. Not located as of 29 Aug 2026: indemnity scope for third party claims arising from output, any warranty on output, and any insurance position, so the full picture is short of an A.

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, which is more than several vendors on this index manage, and the refund policy is an unusual published commercial commitment. But searched those documents, the security page and the trust portal entry point on 29 Aug 2026 and located no indemnity running 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.

Real and named integrations: an iManage technology partnership working through iManage APIs with an announced expansion, SharePoint, Box, a Microsoft Word add in for drafting and redlining, Outlook, EDGAR, and import from virtual data rooms and contract lifecycle systems. The vendor is explicit that it integrates with document management systems rather than replacing them. Not located as of 29 Aug 2026: implementer level documentation describing what each integration moves, in which direction, and what an administrator must configure, which is what the A bar asks for.

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 as of 29 Aug 2026: 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.

The claim is made and the detail is not published. Vendor material states flexible storage options matched to data sensitivity, and separate EU and US contract documents indicate region specific arrangements, with the technical team in Sweden operating under GDPR. Searched the vendor site, the security pages and the published legal documents on 29 Aug 2026 and located no list of available regions, no tenancy model, and no statement of where processing happens as distinct 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 centres 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 was located as of 29 Aug 2026. 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.

Three current independent certifications, ISO 27001:2022 audited yearly, SOC 2 Type II, and ISO 42001 for AI management, with a public trust center at security.legora.com carrying a resources section and a data flow diagram, plus security whitepapers and a security measures annex published openly with no gate at all. The open publication of the security annex is full credit rather than a request flow. The certifying auditor is not named in located material, which is the one thing a peer in this category does publish.

Certification is real and stated with an open route to the evidence, short of 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, which is a materially better pattern than most of this market and is why this is not a C. The trust portal is at a stable URL and carries downloadable documents including business associate agreements and the EU AI Act opinion letter. Under the three tier test this is a self serve request flow rather than a sales gate. What was not located as of 29 Aug 2026 is the audit coverage period, the scope, or the name of the auditing firm.

Vendor material refers to how it implements, supervises and evolves AI without identifying what sits underneath. Searched the vendor site, the trust center, the published general terms, the data processing agreement and the security measures annex on 29 Aug 2026 and located no named model provider, no subprocessor list and no commitment to notify customers when the supply chain changes. Third party sources describe a multi model approach running on Microsoft Azure, which is not vendor material and does not move this axis.

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, names OpenAI and Anthropic as the providers, states the zero data retention agreements negotiated with each and what that means technically, names AWS as the primary cloud provider, states processing locations as Canada and the US, and publishes a complete third party subprocessor list at a stable trust portal URL. Naming the specific model versions in marketing copy is rare and is what a customer inheriting the dependency actually needs. Short of the very top only in that no explicit commitment to notify customers before the model supply chain changes was located, though the subprocessor list is the mechanism through which such a change would surface.

Searched the vendor home page, product pages, newsroom and legal pages on 29 Aug 2026. No pricing page, no published rate, no stated unit of charge and no published tier structure located. The only commercial entry point is a demo request, which is sales gated and earns no credit. Several independent third party pricing analyses state the same, and one reports a consumption based tier that was not located on the vendor site. Third party per seat estimates are not vendor published and do not move this axis. Note that the vendor does publish its general terms openly, which is transparency of terms rather than of price and is graded on the liability axis instead.

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, itemises what each includes, states that pricing is structured around the number of team members on a licence, and confirms a 7 day free trial with extended trials available for larger organisations. 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. Checked the pricing page, the home page and the footer on 29 Aug 2026.

Segment coverage is described with substance: large law firms, in house legal departments, and professional services including a published forensic investigations customer story, spanning more than 1,000 customers across 50 plus markets with multi jurisdiction and cross border work as a stated strength. Practice coverage spans review and diligence, research, drafting and investigations. Not located as of 29 Aug 2026: any statement of the boundaries, meaning which firm sizes or practice areas the product is not built for.

Segment and practice coverage is described with substance, short of the boundaries. Two buyer segments carry 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 80 plus countries. Practice focus is stated clearly and repeatedly as transactional and commercial legal work rather than claimed broadly, which is a real self limit. Short of an A because litigation appears as an option in the signup form while nothing on the site describes litigation support, and because no statement of which practice areas or firm sizes the product is not built for was located.

The vendor home page and security page both state that customer data is not used to train or fine tune any AI models. The vendor publishes its general terms and conditions and its data processing agreement openly, and a training prohibition was searched for in those documents on 29 Aug 2026 and not located, so the commitment as recorded rests on the security and marketing pages rather than on a located contract term. The full agreement text was not read end to end.

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.

REGRADED 29 Aug 2026 after the value set was amended; previously recorded at disclosed without a period, following an earlier correction that established the customer control exists. Rechecked against the source document. Section 17 of the published security measures annex, dated 31 Jan 2025, states that during the term of the data processing agreement personal data is subject to the retention requirements the subscriber instructs from time to time, and that after termination or expiry clause 11 of that agreement governs. Retention is therefore customer instructed and the commitment sits in a contract document rather than a policy page, which is the contractual form of control this value describes and is enforceable in a way a policy page is not. Recorded at customer controlled rather than the top value because no retention period is published and no zero retention setting was located. Also confirmed on the same document and worth factoring in as a retention floor: subscriber environments are logically separated at all times, and full production backups are taken every four hours.

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. What was not located as of 29 Aug 2026, after checking the security page, the published terms of service, the privacy policy and the trust portal entry point, is any statement of how long the vendor itself retains prompts, documents and outputs in its own systems, whether a customer controls that window, or whether deletion is available. Recorded at the middle value because retention is acknowledged and answered for one layer without a period for the other.

Searched the vendor site, the iManage partnership announcement, the security page, the published security measures annex and the trust center on 29 Aug 2026. No vendor material was located addressing whether retrieval enforces document management system permissions at query time per user, or how ethical walls and matter level segregation are handled. The security annex documents least privilege access for vendor personnel, which is a different question. A partner case study describes per query authentication, which is not vendor material.

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.

Searched the published EU and US general terms and conditions, the data processing agreement, the security measures annex and the acceptable use policy on 29 Aug 2026. No clause addressing government or law enforcement requests for customer data was located, and no transparency report was located. This records a search that did not surface the clause rather than a reading of the full agreements end to end.

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.

Research coverage is described by jurisdiction, reported at twelve, and the vendor announced the acquisition of Qura, a Stockholm legal database covering case law, legislation and regulation, which it is extending to larger markets. What is not identified is the corpus itself: which publishers or public sources the law comes from, the licence or public domain basis for each, and the update lag. Searched the vendor site, newsroom and product pages on 29 Aug 2026.

The corpus here is contract market data rather than primary law, which is the right shape for a transactional product and reads differently against a signal written for case law. 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 fetching 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.

Searched the vendor site, product pages, newsroom and blog on 29 Aug 2026. No vendor material was located addressing whether authority returned by the product carries a treatment signal, whether subsequent history is checked, or whether any commercial citator is licensed. A third party directory describes a citation verification capability, which is not vendor material and was not treated as evidence.

Searched the site, the Ask and Compare feature pages, the learning hub and the help centre 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 licence was located. Noted for context: this is a transactional contract product whose grounding corpus is contract market data rather than case law, so a citator is largely outside its design. The absence is recorded as found, and a reader should weigh it against what the product is for.

Searched the vendor site, blog, newsroom and trust center on 29 Aug 2026. No published material was located describing what the product does when it cannot ground an answer, whether an explicit no answer path exists, or whether any confidence or grounding signal is exposed to the user.

Searched the site, the feature pages, the learning hub and the help centre entry point on 29 Aug 2026. No published material describes what the product does when it cannot ground an answer, and no explicit no answer path or confidence signal exposed to the user was located. The vendor publishes a clear architectural position that models should fetch and cite rather than rely on learned patterns, which is about how an answer is grounded rather than what happens when nothing supports one.

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, and it is bounded by what that database covers.

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.

Searched the vendor site, blog, newsroom and resource pages on 29 Aug 2026. No engagement with any named ethics opinion was located, including ABA Formal Opinion 512 and state or national bar guidance. The vendor publishes substantial governance and certification material, which addresses its own AI management system rather than the professional responsibility obligations its buyers are bound by.

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 candour to the court and the obligation to verify AI output, and 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. Searched the site, the learning hub, the blog and the guides and reports index on 29 Aug 2026 and located no engagement with a named ethics opinion, including ABA Formal Opinion 512, any state bar guidance, or any Canadian law society guidance.

Vendor material is framed around speed and volume, describing analysis of thousands of documents in minutes and teams moving faster. Searched the vendor site, blog and legal pages on 29 Aug 2026 and located no per matter record of AI assisted work intended for fee purposes, and no published guidance on billing, fee or client disclosure treatment.

Savings are claimed with nothing published on the client's side of the equation, and unusually the framing runs the other way. A published customer quote from a named partner states the product probably helps him bill an extra hour a day, and the pricing page is headed on boosting profitability, alongside a published return on investment calculator and repeated ten times faster drafting claims. Searched the site, the pricing page, the customer stories and the learning hub on 29 Aug 2026 and located no per matter record of AI assisted work intended for fee purposes, and no guidance on billing, fee or client disclosure treatment. A published claim about billing more hours, in a market where ethics guidance is direct that a lawyer bills for time actually spent, is the sharpest version of this signal on the index so far.

Read against the artifacts this signal turns on, the picture is mixed and the value understates one half of it. Openly published with no gate and forwardable to a client today: general terms and conditions in EU and US versions, a data processing agreement, a security measures annex and an acceptable use policy. Not located as of 29 Aug 2026: a current subprocessor list, any statement of which model providers see client content, and any client facing consent or notification pack. The trust center carries a resources section that routes document access through a request.

A firm can assemble most of what a client AI clause asks for without a sales conversation. Published through a trust portal at a stable URL: a complete third party subprocessor list with processing locations, 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. Short of the top value because the material is a self serve portal rather than a client facing consent or notification pack the firm could forward as assembled, and no such pack was located as of 29 Aug 2026.

Searched the vendor site, product pages and published legal documents on 29 Aug 2026. Partner material describes citations being preserved when work is exported to Word, and the security annex documents security logging traceable to unique usernames, which is an infrastructure control rather than a record of AI assisted work. No per document record covering model used, sources retrieved and human verification was located.

Searched the site, the feature pages, the security page and the help centre 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.