Spellbook vs LegalOn: how they compare in 2026
The real question here is whose playbook you want. LegalOn ships more than 135 playbooks written by its own attorneys covering around 10,000 legal issues, so a team without settled standards gets a position on day one. Spellbook expects you to bring yours and encodes it. That difference explains almost everything else. LegalOn publishes a 2026 benchmark of 3,282 pairwise reviews against eleven named models with the method described and the judge independently verified, and it backs deployments with named customers carrying figures. Spellbook counters on the supply chain, naming OpenAI and Anthropic and describing zero data retention precisely, where LegalOn names only its Azure OpenAI arrangement. Spellbook is the better fit for a law firm. LegalOn is built for the contracting function, lawyers or not.
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.
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.
Review reads a contract against each playbook guideline in turn and drafts redlines. Assistant answers questions about the open contract in Word or the browser, drafts fallback language and issues lists, and runs one click skills that extract terms, check definitions and summarize obligations. The Playbook Agent builds playbooks from a team's policies, templates and past redlines. The Intake Agent asks requesters follow up questions and routes a complete matter, classified by contract type, urgency, counterparty and deal value, and the Triage Agent screens low risk agreements against the playbook. Vault extracts key data, dates and obligations from the signed repository into a table a team can filter, and answers questions such as which contracts renew in the next 90 days. Translate pairs DeepL with LegalOn's own translation agent and sends back only the changes in the counterparty's language. All of it runs on models applied to playbook content that LegalOn's attorneys write.
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.
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.
Review grounds each issue in a playbook standard written by LegalOn's attorneys or by the customer, with the guidance and sample clauses behind it. Each guideline runs as its own check against the contract, about two dozen in parallel, rather than one pass over the whole document. The 2026 Contract Review Benchmark, released in June, set LegalOn against 11 general purpose AI systems across 3,282 pairwise reviews on 21 guidelines. An LLM judge, separate from the systems tested and blind to authorship, picked the more accurate, complete and useful review, and legal experts validated a sample of its outputs. LegalOn ranked first on all 21 provision types and finished a full review in 2.3 seconds. A downloadable report sets out four failure modes of general models on contract provisions.
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.
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.
Routine paper moves on its own and judgment stays with the user. The Triage Agent screens low risk agreements against the playbook, approves the standard ones and escalates the exceptions, and the Intake Agent follows up with requesters until intake is complete. Every agent returns output for review, with legal setting the guardrails and keeping final approval. Review ranks each issue low, medium or high with the playbook guidance behind it, and redlines land as tracked changes a user accepts or rejects. One click AI Revise in Word works through the same tracked changes. Who sets the line between standard and nonstandard paper, and what happens after a wrong approval, is not described.
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.
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.
Four customer stories pair a named company with figures. TriHealth, a Cincinnati health system whose legal team handles more than 1,500 contracts a year, cut review time by 75%. Its associate general counsel says clinical trial agreements that took hours now take about 20 minutes. Industrial Service Solutions saves its lead reviewer more than 15 hours a week and cut turnaround by 70%. Achievers, an HR technology company, reports NDA review time down 70% and $1,000 to $2,000 saved per third party contract. MCEA Holdings, a Japanese holding company, handles 50% more contracts without added headcount and resolves matters 20% faster. Each story names the speaker and role and sets out the starting point, such as a two week turnaround at Industrial Service Solutions and 15 to 20 minutes per NDA at Achievers. The site counts more than 9,000 customers.
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.
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.
Customer content stays the customer's property under section 7.2 of the subscription terms, with a license to LegalOn only to provide the service. Each customer account runs in a segregated environment with strict access controls, and data is encrypted at rest and in transit. Azure OpenAI processes content under terms that it is not used to train, retrain or improve the models and is not stored for any period, including for abuse monitoring. Section 7.3 lets LegalOn aggregate or deidentify customer content into analyses it owns and uses to improve the service, provided they cannot be linked to the customer. Section 2.2 states that LegalOn is not a law firm and that communications between LegalOn and the customer carry no attorney client privilege. Work product handling is not addressed.
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.
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.
Section 2.2 of the subscription terms says LegalOn is neither a law firm nor an attorney and is no substitute for an attorney's advice, and the website terms add that it gives no legal advice. Solution pages sell review to procurement, sales and contract management teams as well as lawyers, and the law firm page offers playbooks that adjust to each client's risk profile. Competence and supervision duties are not addressed, and international playbooks give guidance across 23 countries with no stated limit on where the product may be used.
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.
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.
The 2026 Contract Review Benchmark is LegalOn's published test of its own system. Pairwise reviews were judged by an LLM blind to authorship, and legal experts validated a sample of its decisions. Results are reported by provision type, with a report on four failure modes of general models, and a workflow survey of 500 legal professionals sits beside it. Attorneys on staff write the playbooks and keep them current as laws and standards change. An owner for model governance is not named.
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.
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.
Each customer account runs in a segregated environment with strict access controls, data is encrypted at rest and in transit, and LegalOn runs annual penetration tests, regular vulnerability scans and a patch management process. Contracting plans add enterprise single sign on, multifactor authentication and IP allow lists. The data processing addendum keeps a subprocessor list with functions and locations in the trust center, currently Google Cloud Platform, Auth0, Microsoft Azure for the OpenAI service and Datadog. A new subprocessor comes with prior written notice and ten days to object, and a personal data breach is reported to the customer without undue delay. Under section 9.2 of the subscription terms a customer can export content during the term, and LegalOn may delete it 30 days after the term ends. Trust center controls include data retention procedures, deletion of customer data on exit and tested continuity and disaster recovery plans.
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.
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.
Section 12 of the subscription terms caps each party's liability at the fees paid or payable in the 12 months before the claim. For a customer with no payment obligation, such as a trial, the cap is $1,000. Lost profits, lost data and consequential damages are excluded, and the cap does not limit the customer's own indemnity or payment duties. Against third party claims that use of the service infringes a United States patent, trademark or copyright or misappropriates a trade secret, LegalOn defends or settles and pays damages finally awarded. The indemnity does not reach the customer's negligence, abuse or misapplication of the service. The warranty promises that the service performs materially as documented, and the rest of the service is provided as is. The trust center holds a 2025 cyber insurance policy released on request, and California law governs the terms.
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.
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.
Word is the main working surface, with review, redlining, drafting, questions and one click AI Revise built on Word's tracked changes. Requests arrive from Slack, email and custom forms, with Microsoft Teams marked as coming soon, and SharePoint, Google Drive and Box connect for direct access to files. A public REST API covers three areas. The Contract and Files API moves contract files and data in and out, and the User Management API manages users, groups, workspaces and departments. The Matter API creates matters from a ticketing tool, form or CRM and keeps status, assignees and messages in sync. Access uses OAuth 2.0 client credentials and is scoped to the workspaces a user already holds. iManage and NetDocuments are not named.
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.
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.
Hosting runs in the United States on Amazon Web Services and Google Cloud Platform, with a segregated environment for each customer account. ISO 27017 certification covers the controls for multi tenant cloud operation. The data processing addendum brings in standard contractual clauses and the UK addendum for personal data moved from Europe, and the privacy policy says personal information may move to the United States or Japan. No single tenant, private or regional option is offered, and where Azure OpenAI processes model calls is not stated.
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.
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.
SOC 2 Type II, ISO/IEC 27001:2022 and ISO/IEC 27017:2015 certification are stated. The trust center holds the 2025 SOC 2 report in English and Japanese and the 2025 ISO 27001 and 27017 certificates. A 2025 cloud web penetration test, a network vulnerability assessment and security white paper v1.3 sit beside them, all released through a request for access. Badges on the integration and pricing pages name ISO 27007 and ISO 27011 where the security page names 27017.
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 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.
Microsoft's Azure OpenAI service is the named model provider for review and drafting, under terms that it does not train on or store customer data, including for abuse monitoring and debugging. Translation runs on DeepL alongside LegalOn's own translation agent. The subprocessor list places Microsoft Azure beside Google Cloud Platform, Auth0 and Datadog, and a new subprocessor comes with prior written notice. Review runs focused checks per guideline in parallel. Which models serve those checks, and where they run, is not stated.
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.
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.
Pricing is set in a sales conversation, and the pricing page lays out three plans without figures. Core Review, for solo attorneys and fractional general counsel, includes unlimited chat, review and redlining, 135 or more playbooks, a document repository, more than 100 templates and the Word add in. Contracting Suite adds custom playbooks, the Playbook Agent, Vault and Vault Projects, team training, dedicated support and enterprise sign on. Productivity Suite adds Matter Management with intake and triage agents, a matter dashboard and matter intelligence. Every plan includes unlimited usage and guided onboarding. Entity Management, Board, Translate, international playbooks and managed playbooks are further modules.
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.
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.
Buyer pages cover in house legal, legal operations, procurement, contract management, sales and law firms, and industry pages cover construction, financial services, business services, private markets, healthcare, manufacturing and software. Playbooks are specific to contract type and to whether the customer sends or receives the paper, and international playbooks cover common commercial contracts in 23 countries, from the United Kingdom to Singapore. Translation runs across 28 or more languages. The product covers contracting work from intake to signed agreements, plus entity and board records. Litigation and legal research are outside it.
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?
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.
Section 7.3 of LegalOn's subscription terms, last modified 1 June 2026, allows LegalOn and its affiliates to aggregate or deidentify customer content, alone or combined with data from other sources. The resulting analyses may be used for internal business purposes "including to improve the Services", and LegalOn owns them and may disclose them as long as they cannot reasonably be linked to the customer. The data processing addendum keeps the same right to use deidentified or aggregated customer data to improve LegalOn's systems after the contract ends.
No clause carves model training out of that use. At the model layer, Microsoft's Azure OpenAI service runs under protections that keep customer data out of training, retraining or improving its models.
Prompt and Output Retention
How long does the product keep what a lawyer typed, and can that be set to zero?
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.
Model calls through Azure OpenAI leave no customer data stored for any period, including for abuse monitoring and debugging. Contracts in Vault stay for the subscription term, a customer can export them, and LegalOn may delete them 30 days after the term ends. Personal data is kept as long as reasonably necessary, and no customer setting for retention during the term is described.
Ethical Walls and Matter Segregation
Does retrieval respect the firm’s ethical walls, or can the model read across them?
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.
Inside a customer, contracts are organized by workspace, project or department, and workspace access is set by user group, with changes cascading to every user in the group. API calls are scoped to the workspaces a user already holds. Each customer account runs in its own segregated environment. Walls at the level of a single matter are not described.
Third Party Request and Subpoena Notice
If someone subpoenas the vendor for a firm’s data, does the firm hear about it first?
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.
Section 8.2 of the subscription terms requires prior notice of a legally compelled disclosure where the law permits, and reasonable help if the customer contests it. Under the data processing addendum, LegalOn tells the customer of requests from regulators about personal data and does not answer them without approval. The privacy policy allows disclosure to law enforcement and authorities for legal compliance. No transparency report is offered.
Primary Law Corpus Provenance
Where does the law in this product come from, and does the vendor have the right to use it?
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.
Playbooks are written and maintained by LegalOn's attorneys for each contract type and negotiating position, more than 135 of them, and are kept current as laws and standards change. More than 100 attorney drafted templates sit beside them. The legal sources behind each standard are not named.
Good Law Verification
Does the product tell you when the authority it just cited has been overruled?
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.
Review tests contracts against playbook standards rather than case law, and the playbooks are kept current as laws change. No flag on cited cases or check of later history is part of the product.
Refusal and Uncertainty Behavior
What does the product do when the answer is not in the corpus?
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.
Review flags each issue with an importance of low, medium or high and supplies the playbook guidance and sample clauses behind it. No path is described for an issue the product cannot assess.
Fabricated Citation Record
Does a public court record exist addressing fabricated or hallucinated legal citations in output from this product?
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.
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 LegalOn. Its products review, draft and manage contracts for in house and contracting teams.
Bar Guidance Alignment
Has the vendor engaged in public with the ethics opinions 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 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.
The company's research covers AI adoption, a workflow survey of 500 legal professionals and its contract review benchmark. No public material engages ABA Formal Opinion 512, a state bar opinion or Japanese bar guidance.
Billing and Fee Posture
Does the vendor address what happens to the bill when the work takes an hour instead of six?
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.
LegalOn sells to in house legal, legal operations, procurement, contract management and sales teams, and to law firms. Its law firm page pitches taking on more clients by cutting manual review time by up to 85%. TriHealth, a Cincinnati health system, reports clinical trial agreements that once took hours now reviewed in about 20 minutes, a 75% reduction. No per matter record of AI assisted work for fee purposes and no guidance on billing, fee or client disclosure treatment is published.
Outside Counsel Guideline Readiness
Can a firm get this vendor through a client’s AI clause without a bespoke negotiation?
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.
The trust center keeps the subprocessor list that the data processing addendum points to, with Google Cloud Platform, Auth0, Microsoft Azure for the OpenAI service and Datadog. A new subprocessor is announced with ten days to object. The SOC 2 report, ISO certificates and security white paper are released on request, and no client facing disclosure template is offered.
Court Disclosure Support
If a judge’s standing order requires an AI disclosure, can the product produce one?
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.
Review ties each issue to the playbook standard behind it, and Matter Management keeps each request's history, status and cycle time. No record of AI use for a court filing is offered.
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.
- Good Law Verification
- Court Disclosure Support
Which one fits
Choose Spellbook if
- Lawyers are your users and Word is where they work. Spellbook delivers review and drafting as tracked redlines inside the document, and its signup asks a prospect to confirm they are a legal professional.
- You need to know which models see your client data. Spellbook names OpenAI and Anthropic and states negotiated zero data retention with both, describing the mechanism. LegalOn names its Azure OpenAI protections but discloses less of the wider chain.
- Your standards already exist and encoding them is the job. Playbooks in Spellbook are yours, which is the right shape when a firm's negotiating position is the asset rather than something to be supplied.
Choose LegalOn if
- You have no settled contract standards and need them supplied. More than 135 attorney written playbooks covering roughly 10,000 legal issues means a position on day one, rather than a system waiting for you to encode one.
- Measurement matters to your risk committee. LegalOn publishes a 2026 benchmark of 3,282 pairwise reviews across 21 precision critical guidelines against eleven named models, with the scoring method described and the judge independently verified.
- Your intake comes from everywhere. The intake agent ingests requests from email, Slack or a web form and routes them, with a described escalation rule that moves standard paper on and stops elsewhere.
In summary
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. According to the AI Legal Index, its case rests on the model supply chain: it names OpenAI and Anthropic as providers and states negotiated zero data retention agreements with both, describing the mechanism precisely enough for a buyer to verify. Its architectural position is published rather than implied. It does not fine tune, and instead requires models to fetch and cite, on the reasoning that long term memory encourages fabrication. It publishes named customer stories including Dropbox and Panasonic, and states more than 4,500 teams across 80 plus countries.
LegalOn
LegalOn is a contract review and legal workflow platform for in house legal, legal operations, procurement and contracting teams. It is built around attorney written playbooks rather than customer built ones, shipping more than 135 pre built playbooks covering around 10,000 legal issues. According to the AI Legal Index, its case rests on measurement: a published 2026 Contract Review Benchmark tests eleven named AI models across 3,282 pairwise reviews on 21 precision critical guidelines, with the methodology described and the scoring judge independently verified. It backs deployments with named customers and quantified results, and publishes dedicated pages for procurement, sales, contract management and legal operations. It publishes no rate of any kind.
Questions buyers ask
Spellbook vs LegalOn: which is better for contract review?
It depends on whether you have contract standards already. LegalOn supplies them, shipping more than 135 attorney written playbooks covering around 10,000 legal issues, which suits a team without a settled position. Spellbook encodes yours. Both are well documented, so the fit question decides it. From the AI Legal Index, based on each vendor's own published materials as of August 30, 2026. No vendor pays for placement.
Which one publishes accuracy figures?
LegalOn, and by a wide margin. It publishes a 2026 Contract Review Benchmark testing eleven named AI models against its own system across 3,282 pairwise reviews on 21 precision critical guidelines, with contracts broken into provision level checks and the scoring judge independently verified. Spellbook documents its grounding method clearly but publishes no accuracy figure. From the AI Legal Index, based on each vendor's own published materials as of August 30, 2026. No vendor pays for placement.
Is LegalOn only for lawyers?
No, and that is a real difference from Spellbook. LegalOn publishes dedicated pages for procurement, sales, contract management and legal operations alongside in house legal and law firms, and its own material states that AI contract review is not only for lawyers. Spellbook's signup asks prospects to confirm they are a legal professional and offers no path for non lawyers. A tool used by non lawyers raises professional responsibility questions that one used by an attorney does not. From the AI Legal Index, based on each vendor's own published materials as of August 30, 2026. No vendor pays for placement.
Do LegalOn or Spellbook train on customer data?
LegalOn's subscription terms let it aggregate or deidentify customer content and use the resulting analyses to improve the Services, and no clause carves model training out of that use. Its Azure OpenAI layer runs under protections that keep customer data out of Microsoft's models and store none of it, even for abuse monitoring. Spellbook names OpenAI and Anthropic and states negotiated zero data retention agreements with both, with data existing only in memory to process a request. From the AI Legal Index, based on each vendor's own published materials as of August 30, 2026. No vendor pays for placement.
What do LegalOn and Spellbook both leave unpublished?
Neither publishes a position on liability or recourse when a review misses something or gets it wrong. Neither publishes a position on the advice line, on competence and supervision duties, or on jurisdiction limits. Neither publishes a rate either. LegalOn has a pricing page in its navigation that carries no number, unit or tier, and Spellbook publishes tier names and a licensing basis without a figure. From the AI Legal Index, based on each vendor's own published materials as of August 30, 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.
The sharpest difference on this page is one neither vendor frames as a difference. LegalOn sells deliberately beyond lawyers, with dedicated pages for procurement, sales, contract management and legal operations, and its own material states that AI contract review is not only for lawyers. Spellbook's signup asks a prospect to confirm they are a legal professional and offers no path for anyone else. Neither publishes a position on the advice line or on supervision duties, but the exposure is not the same shape. A tool reviewing contracts for a procurement team raises questions a tool reviewing them for an attorney does not. Neither vendor reviewed this page and neither pays for inclusion.