Gavel vs Spellbook: how they compare in 2026
Gavel Exec and Spellbook both help transactional lawyers draft and redline contracts inside Word, using playbooks and precedent to guide proposed changes. Gavel adds a separately priced document automation product, Workflows, for intake questionnaires, templates and client portals. Spellbook extends its drafting suite through Associate for work across several files, iManage access and Autonomous Contract Management for incoming agreements. That distinction matters when deciding what to buy beyond the Word assistant. Relativity acquired Gavel in June 2026 and plans to bring its Word drafting into RelativityOne. Gavel Workflows suits a firm building repeatable estate planning or family law documents. A legal department routing incoming commercial contracts may find Spellbook's intake and automatic approval rules closer to the task. Gavel Exec costs $160 per user monthly or $1,740 annually, including 1,000 monthly completions. Spellbook prices by team members but requires a quote. Both provide reviewable edits, yet Spellbook's contract management product can approve contracts that meet configured rules without sending each one to a lawyer. Neither product supplies a contractual guarantee that its proposed legal language will be correct.
Which one fits
Choose Gavel if
- Your firm needs intake questionnaires and repeatable Word or PDF documents, and Gavel Workflows builds them from templates and conditional rules.
- Your team wants to budget a Word review assistant before a sales call, and Gavel Exec lists $160 monthly and $1,740 annual seat prices.
- Your practice uses Clio matter data to prepare documents, and Gavel Workflows can populate intake fields and return completed files.
- Your lawyers want a web workspace as well as Word for contract work, and Gavel Exec supports both surfaces.
- Your estate planning or family law practice wants document automation with optional AI, which Gavel Workflows separates from Exec's generative review.
Choose Spellbook if
- Your firm keeps precedents in iManage and needs existing permissions respected, which Spellbook applies when selected files enter its working context.
- Your team reviews incoming commercial contracts and wants rule based automatic approvals, which Spellbook's contract management product supports alongside human escalation.
- Your lawyers work across several related documents and need shared reference material, which Spellbook Associate uses within its projects.
- Your team drafts in Google Docs as well as Word, and Spellbook supports both alongside its contract review tools.
- Your procurement process requires express privilege and work product protections in the agreement, which Spellbook includes with confidentiality duties for service providers.
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 for one of the two lines and optional for the other. Gavel Exec is built on AI: review, redlining against playbooks, drafting, market benchmarking and document chat are all model output. Gavel Workflows is rules based document automation with conditional logic, and the security page says its AI features, including AI onboarding for Workflows, are entirely optional and that many customers use the automation without enabling AI.
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.
Gavel Exec combines semantic retrieval with matching of text across customer precedents, matter files, EDGAR, government sources, and the open web. Its described analysis considers exact wording, conceptual similarity, and source verification. Answers and revisions include explanations intended to help a lawyer validate the result. That architecture provides a basis for tracing contract analysis, but the public claim that the product flags five times more issues than manual review has no reproducible sample or method. Market benchmarking also requires judgment about comparable agreements. Gavel does not publish a detailed failure analysis showing where extraction, clause interpretation, or proposed revisions become unreliable.
Ask can use selected iManage files and return citations to the team's own contracts. The legal data connection retrieves material from named open legal databases such as CanLII, CourtListener, Cornell Law, EUR Lex and regional legal information institutes, with links to the underlying authority; its page claims more than 1,000 databases while its tables list about 108. Their currency follows the source operator's updates. Spellbook's Humans Hallucinate Too study ran Review over 3,019 contracts filed with the SEC in a deliberately conservative mode, without a described human check of its findings. Spellbook publishes no reproducible accuracy evaluation for its own AI, no automatic subsequent treatment check and no abstention threshold. A citation makes an answer inspectable, but checking the quotation or legal proposition against it is still the reviewing lawyer's job.
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.
Proposed redlines and negotiation comments appear within Word, where the lawyer can review and revise them. Playbooks supply preferred positions, and explanations help a user assess why a change was suggested. Projects keep instructions and reference files together, while shared Workspaces support team use. The terms require users of experimental features to review and verify results and warn that those outputs may be incomplete or incorrect. These are identifiable review surfaces and responsibilities. The materials do not define a confidence based stopping rule, a required escalation route for an unsupported answer, or a recovery process after an erroneous revision has been accepted.
Review proposes changes in Word for the lawyer to inspect and approve, either individually or in a group. Playbooks encode the team's instructions, while Associate takes on work across several files with user oversight. Proposed edits can carry the reviewer's identity when accepted, and citation links let the reviewer inspect supporting material. Autonomous Contract Management, generally available since 7 October 2026, applies routing rules that can auto approve contracts, such as those under $50,000 that pass every playbook rule, while flagged items go to a person and every AI edit appears as a tracked change. The terms place responsibility for reliance and verification with the customer. No universal threshold is stated at which Associate must stop or escalate an unsupported conclusion, and no route is published for reversing an approval the system made on its own.
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.
Martin Algie of MIA Contract Lawyers describes using Gavel Exec for negotiation and redlining, with an attributed account of how it fits his work. Gavel also identifies more than 2,000 law firms and legal teams using its products. A separate Streeter Law Firm account describes preparing an estate plan in 30 minutes through Gavel Workflows. That outcome concerns rules based document automation and does not isolate an AI effect. The available examples establish recognizable users and practical use cases, but do not provide a dated, controlled before and after evaluation of Exec's accuracy, review completeness, or total professional effort.
Named customer accounts involve Dropbox, Panasonic, KMSC Law, Alturas Capital Partners and Elevare Law. Panasonic's account concerns saving three weeks while building an RFP process, while other testimonials describe drafting capacity and keeping work inside the legal team. Spellbook says more than 5,000 legal teams use it and claims 75 percent time saved on contract work without a method. These examples establish identifiable use rather than only a logo wall. A consistent dated measurement protocol, comparison baseline and workload definition do not accompany the range of savings claims, so the figures are specific customer accounts rather than a reproducible general result.
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.
Customer prompts and document content are not used for training, and AI providers, including OpenAI, operate under zero retention agreements, Gavel states. Customers have separate databases and file storage, with controls over whether Workflows data persists. The incorporated privacy policy nevertheless permits analysis of anonymized builder questions to improve questionnaire suggestions, while expressly excluding the answers. That narrower content permission requires attention alongside the general no training statement. Project access controls are asserted without a complete matter segregation model. The terms also distinguish the software relationship from privileged communications with a lawyer, leaving the firm responsible for protecting client confidences.
Spellbook's agreement expressly protects privileged information and work product and requires confidentiality for staff and service providers handling customer content. Its iManage integration preserves existing file permissions and ethical walls. Third party models cannot train on customer content and operate under zero retention commitments. Spellbook itself may use deidentified content for customer specific personalization and retain inputs and outputs temporarily for quality assurance, while the terms restrict those uses and access. These permissions are narrower than unrestricted cross customer training, but they are not an across the board ban on learning from client content. Application history also has no single stated in use retention deadline.
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.
Gavel's terms state that the company is not a law firm, supplies no legal advice, creates no attorney client relationship, and takes no share of legal fees. Users remain responsible for professional conduct requirements, including unauthorized practice, communications, and confidentiality. This distinction is relevant to Workflows, which lets firms offer client intake and paid legal services through their own interfaces. The lawyer must establish the client relationship and appropriate disclosures. Exec supplies suggestions for review, while experimental features carry an express verification responsibility. The materials do not map competence duties or legal coverage across each jurisdiction served.
Output counts as information rather than formal legal advice under Spellbook's terms, which place verification and appropriate lawyer review with the customer. The product is directed to law firms and legal departments, with review controls inside Word and oversight of Associate's work across files. The agreement also warns that non English use can produce unsatisfactory results. That is a concrete language limitation, but not a tested jurisdictional coverage matrix or a map of which regulated services the software can provide. Human acceptance of a redline remains part of contract work, and an answer from a cited public source is not a substitute for checking its legal application.
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.
Principles without a mechanism. The security page says the AI is built with legal professionals in mind, putting security, privacy and control first, and that AI is optional. The Gavel Exec information page says the product is trained by practicing deal lawyers. No owner, testing before release, evaluation or finding about uneven output is published.
Spellbook's terms describe internal AI risk and prohibited use policies, staff education and regular reassessment of ethical and legal requirements. Its security material also cites a CMS Law opinion classifying the product under the EU AI Act and identifying applicable controls. These are concrete governance arrangements beyond a general promise to act responsibly. The product supports verification through citations and user approval of edits, but those controls are separate from evaluating a model before release. The framework names no internal owner, no reproducible release test set and no results on uneven behavior across populations or matter types.
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.
Customers can decide whether Workflows data is stored and can delete stored information immediately. AI provider processing is described as transient under zero retention agreements, while the terms provide a seven day reactivation period after cancellation before account deletion, subject to legal exceptions. The privacy policy adds backup, audit, and dispute exceptions. Security measures include separate customer storage, encryption, two factor authentication, single sign on, and annual external testing. OpenAI is identified among AI providers, but no complete subprocessor register is published. The materials also do not give customers a specific incident notification timetable covering every class of content held by the service.
OpenAI and Anthropic process Spellbook requests under zero retention and no training commitments. Spellbook's own terms permit quality assurance copies of inputs and outputs for up to 90 days, restricted to authorized staff, and self service abuse monitoring for up to 30 days unless an investigation or law requires longer. Microsoft identity integration lets organizations enforce their authentication policies, and iManage access preserves source permissions. The agreement covers confidentiality, security incidents and deletion or return of customer material, while the processor register identifies downstream services. Outside those secondary uses, Spellbook gives no single fixed period for how long application history is kept.
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.
The August 19, 2025 terms disclaim warranties that output will be accurate, current, complete, or suitable for the user's needs. They place reliance on platform information at the user's risk and separately warn that beta and preview features can produce incomplete or incorrect results. Aggregate liability is limited to the greater of $100 or the fees paid for the relevant product during the preceding twelve months. The customer owes an indemnity for specified claims, while no reciprocal AI output indemnity is offered. These provisions allocate ordinary service risk without a warranty that generated legal language will be correct.
Specified intellectual property claims against the software are covered by an indemnity, alongside service warranties, while the accuracy of generated output and responsibility for customer reliance on it are disclaimed. The general limit is twelve months of fees, with exceptions including confidentiality, security, data incidents and indemnification duties. The agreement includes mutual protection for specified data incident claims and gross misconduct. Beta Features have separate warranty exclusions and a CAD 10,000 cap. These are concrete protections for platform and data risks, but they do not provide an accuracy warranty compensating a client when an accepted clause or legal assertion is wrong.
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.
Exec places proposed revisions and comments in Word. Workflows connects document generation to Clio Manage, Docusign, Zapier, DecisionVault, and LegalServer. Clio contacts, matters, custom fields, and billing codes can populate intake, and completed files can return to a matter. Docusign supports variables for recipient details, ordered signers, signature status, and return of completed agreements. DecisionVault fields can be mapped into questionnaires, while LegalServer supports case data and return through a webhook. These are described data movements and configuration choices. The public overview does not provide a complete setup procedure or permission synchronization specification for each connector.
The iManage connection starts from Add from iManage in Ask or an Associate Project and authenticates the user's account once. The same connection then works in Word and Associate. Users select files through the attachment control or project file list; selected content becomes available as chat context or project references without a manual download. Answers cite the imported contracts, and precedents can guide review of incoming paper. Existing iManage permissions and ethical walls govern file access. The connection describes movement from iManage into Spellbook's working context; it does not promise automatic return of revised files to the source repository. Spellbook also runs in Google Docs, connects to Slack, OneDrive, Dropbox, SharePoint and Google Drive, and Autonomous Contract Management takes contracts in from Gmail, Outlook, Slack and Salesforce.
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.
Each customer gets a separate subdomain, database, and file storage in the hosted service. The default storage location is in Amazon Web Services facilities in the United States, with other hosting regions offered in the European Union, Canada, Australia, and elsewhere in AWS. The terms nevertheless obtain consent to processing in the United States, and the public regional hosting offer does not map each AI provider's processing location. A chosen storage region therefore does not fix where every model operation runs. Firms with residency requirements need the configured service and processing agreement to specify that boundary.
Customer content is stored and processed in Canada and the United States, Spellbook states, with AWS as its primary cloud provider. Third party model requests are handled under zero retention agreements with OpenAI and Anthropic, while Spellbook itself has separate retention rights for quality and abuse monitoring. The Word add in and Associate connect to shared cloud services, including optional sources such as iManage. The public description identifies storage and processing countries but does not offer a per tier residency selector or a dedicated customer deployment. A source system's location therefore does not confine every later processing step to that same location.
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.
Gavel now states that Gavel Exec has SOC 2 Type II attestation covering security, availability, and confidentiality. The scope is the Exec product; AWS infrastructure has its own separate certifications. The security materials also describe annual external testing, secure development practices, employee training, encryption, and authentication controls. A Type II examination concerns operation of controls over a period, but the public page does not expose the report date, examination period, auditor, or full report. Procurement teams can request additional vendor documentation. The attestation statement should not be extended automatically to every Workflows feature or treated as an evaluation of legal output quality.
Spellbook states that it is SOC 2 Type II compliant and provides a trust portal for reports, processor information and compliance resources. Its security program uses encryption, Microsoft identity controls and agreements governing model providers. The public security explanation also describes HIPAA support through business associate agreements where appropriate and a legal opinion on EU AI Act classification. These are different assurances with different scopes. The open product explanation leaves out the current SOC audit period, the auditor and the full service scope. The named SOC standard therefore supports a specific certification claim without treating every resource or regulatory statement as an equivalent independent security audit.
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.
One provider is named, without the full set, the models or change notice. The security page and Privacy Policy say Gavel holds zero data retention agreements with the AI models it uses, including OpenAI, so one provider and its retention position are stated. Other providers, the models and versions, and where they run are not. The Gavel Exec information page describes the architecture: hybrid semantic and full text retrieval, trained on precedent. No commitment to notify customers of changes is made.
Language models come from OpenAI and Anthropic, under zero retention agreements that keep request and response content in memory for processing rather than persistent storage at those providers. Spellbook describes its models as GPT-5, Claude and other models it does not name, while older pages of its own still cite GPT-4o and GPT-4. AWS is the primary cloud provider, and storage and processing are described in Canada and the United States. The trust portal lists processors and records updates when suppliers change. Spellbook does not map models to features or give exact production versions, and a public processor update history is not an explicit commitment to notify every customer whenever a model version or deployment location changes within the same supplier.
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 for Gavel Exec is $160 per user each month or $1,740 per user billed annually, with 1,000 monthly completions. A trial includes 25 requests per user, and teams of at least ten can request pricing. Workflows starts at $83 monthly for Lite, with Pro advertised at $290 and Scale from $417 monthly when billed annually. Its public pricing sections show conflicting Standard figures of $210 and $165, so that tier needs confirmation. General onboarding and training are advertised as free, while custom automation work can require a separate quote. The products have different allowances and should not be treated as one combined subscription.
The number of team members on a license sets the price of the suite, which now lists Review, Draft, Ask, Benchmarks, Playbooks and Associate. Law firm and in house packages both include the Word add in and Associate, training and online support, with dedicated support for teams above ten. The in house offering includes a playbook build service, and academic institutions get free access. A seven day trial is available, with extended trials possible for larger organizations. Subscription amounts remain custom rather than a public per user rate. The terms of 17 September 2026 renew orders for 12 month terms and cap annual increases in subscription fees at 10 percent, and Spellbook may change the terms by posting them, effective after 30 days.
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.
Transactional attorneys, corporate legal teams, and in house counsel working on commercial agreements, corporate matters, and real estate are the users of Gavel Exec. Gavel Workflows addresses repeatable document production across estate planning, probate, family law, bankruptcy, employment, corporate work, and property matters. Its customers range from solo practices to larger firms and legal startups. Court forms and legal templates extend the automation product beyond negotiated contracts, while client portals support direct intake. The company describes use across multiple countries, but does not define the legal reliability of every AI feature by jurisdiction or identify a complete set of unsupported practice areas.
Law firm and in house packages are sold separately, and the principal tools center on transactional drafting, review, negotiation and questions about agreements. Associate extends work across several files, iManage access allows firms to use existing contract precedents, and Autonomous Contract Management, generally available since October 2026, handles routine incoming contracts for in house teams. Industry material covers energy, healthcare, finance, technology, manufacturing and consumer businesses, and academic institutions get free access. The legal data connection adds government and court sources across many regions, though breadth of sources is a different matter from tested competence in every practice. The terms warn about non English results. Spellbook does not list the jurisdictions or specialized legal tasks it leaves unsupported.
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 terms incorporate a privacy policy that permits analysis of anonymized workflow builder questions to improve questionnaire suggestions. It expressly excludes the answers and says generated questionnaires contain no personal information. That is a limited product improvement permission concerning builder content, not a statement that client answers train models. Gavel's security promise separately rejects training on customer data, and its providers are bound to zero retention. The contract does not expressly exclude model improvement from the builder question permission.
The terms prohibit third party models from retaining or training on customer content. Spellbook itself may process deidentified customer material to improve that customer's features and calibrate personalized systems, without using that personalization for other customers. It can also evaluate prompt and system improvements through limited quality monitoring. These own service improvement permissions are distinct from the provider prohibition and do not require a separate opt in in the standard agreement.
Prompt and Output Retention
How long does the product keep what a lawyer typed, and can that be set to zero?
The customer controls storage and zero is available. The security page says that for AI features Gavel stores no documents, that its AI providers process data only for the request and then delete it under zero data retention agreements, and that customers decide whether Workflows data is stored and can delete it immediately. The Terms and Privacy Policy add that account data is deleted seven days after cancellation, save where law or backups require longer. Gavel Exec Projects keep instructions and referenced files together, which is storage the customer chooses.
Model providers handle request and response content in memory under zero retention agreements. Spellbook may keep quality assurance inputs and outputs for up to 90 days, and self service abuse monitoring data for up to 30 days, with investigation and legal exceptions. Those are specific secondary uses rather than a stated ordinary lifetime for all application history. Deletion and return provisions are a different mechanism from a configurable zero history setting.
Ethical Walls and Matter Segregation
Does retrieval respect the firm’s ethical walls, or can the model read across them?
Separation between customers is documented; walls inside a customer are asserted without detail. The security page states that each customer has its own subdomain, isolated database and separate file storage. Within a firm, the Gavel Exec FAQ describes matter-based Projects with granular access controls and Workspaces that share Projects and Playbooks, but no permission model, roles or enforcement are documented.
The iManage integration applies existing iManage permissions and ethical walls to file access inside Spellbook. A user authenticates the source account once, then selects permitted files for Ask in Word, Ask in Associate or an Associate Project. Selected material becomes context for answers and review. Spellbook describes this protection specifically for the iManage connection and does not extend the claim to permission inheritance on the other optional storage connections.
Third Party Request and Subpoena Notice
If someone subpoenas the vendor for a firm’s data, does the firm hear about it first?
The Terms of Service (19 August 2025, section J) reserve Gavel's right to cooperate fully with law enforcement or a court order requiring disclosure of information about anyone posting materials on the platform, with the user waiving claims arising from it, and the Privacy Policy permits disclosure where required by law, legal process or government request. Neither document commits to, or reserves discretion over, notifying the customer.
Section 4.3(d) of Spellbook's terms, updated 17 September 2026, requires prompt notice of a legal or government demand for customer data and reasonable cooperation with efforts to obtain a protective order or contest disclosure. The confidentiality provisions also address compelled disclosure and protection of privileged material. These contractual steps give the customer an opportunity to respond to a demand. Spellbook does not publish a report counting government requests and their outcomes.
Primary Law Corpus Provenance
Where does the law in this product come from, and does the vendor have the right to use it?
Gavel Exec identifies customer precedents and matter files, EDGAR, government sources, and the open web as inputs to its retrieval and verification process. It does not publish a licensing basis or update schedule for the complete collection, and the dataset behind market clause benchmarking is not identified. Naming those sources helps explain the product's inputs, but says nothing about the rights, coverage, or continued currency of every item used in an answer.
The legal data connection names its sources, including CanLII, Cornell Law, CourtListener, EUR Lex, BAILII and national government registers. Spellbook retrieves material directly from each source of record and follows its update cadence. The same workflow can use the customer's own contracts and iManage precedents. The named source list makes jurisdiction coverage inspectable, but does not state an individual license or public domain basis for every external collection or its separate market benchmark data.
Good Law Verification
Does the product tell you when the authority it just cited has been overruled?
Agreements are what Exec primarily analyzes and revises, while Workflows assembles documents and court forms from templates. Neither product identifies a citator that tracks subsequent treatment of a judgment. The template library also does not describe a complete process for verifying the continuing currency of every statutory reference or form. Lawyers need to verify any authority used in the resulting work and ensure that their chosen templates remain appropriate for the filing jurisdiction.
Citations to public case law, statutes and registers come back from the legal data feature, with currency tied to the operator of each source. Ask, Draft and Review can use that authority within the contract workflow. The feature does not describe a licensed citator or a method for checking subsequent judicial treatment of a case. A current link to the underlying decision is therefore separate from a signal that its legal proposition remains reliable.
Refusal and Uncertainty Behavior
What does the product do when the answer is not in the corpus?
Gavel Exec explains proposed revisions and uses playbooks and reference material to support review. It does not describe a specific abstention response when those inputs cannot support an answer, or a confidence indicator that determines when work returns to a lawyer. Reviewable redlines help a user inspect the result, but they do not show that the system recognizes every unsupported legal proposition. The lawyer remains responsible for resolving uncertainty before relying on the suggested language.
Source citations and selected precedent files provide context for Spellbook's answers and proposed redlines. A lawyer can inspect that material and accept or reject suggested changes. The product does not describe an automatic no answer response, an exposed confidence threshold or a required escalation when available material cannot support a conclusion. A contractual warning about unreliable output assigns verification to the user rather than defining an abstention mechanism.
Fabricated Citation Record
Does a public court record exist addressing fabricated or hallucinated legal citations in output from this product?
No reported citation fabrication incident naming Gavel, Gavel Exec, or the former name Documate appears in the AI Hallucination Cases database reviewed on October 16, 2026. This observation concerns reported false authority, not every form of product error or litigation involving the company. A contract revision can still misstate a provision or market position without fabricating a citation, so an absence of reported cases does not replace professional verification.
Youssian v Village of Kings Point, 2026 NY Slip Op 26150, Supreme Court of New York, Nassau County, September 9, 2026, addresses counsel's fabricated quotations and misrepresented holdings. The opinion recounts counsel accepting Spellbook AI changes without repeating a citation check. It sanctions counsel $5,000, awards $10,000 in fees and strikes both petitions. The findings concern the lawyer's verification and response to the errors; the product attribution appears in counsel's explanation.
Bar Guidance Alignment
Has the vendor engaged in public with the ethics opinions its buyers are bound by?
Professional responsibility appears in general terms only. The Terms of Service make users solely responsible for complying with rules of professional conduct, including those on unauthorized practice, communications and confidentiality, and prohibit use that violates them. No ethics opinion or bar guidance is named.
Youssian v Village of Kings Point, 2026 NY Slip Op 26150, Supreme Court of New York, Nassau County, September 9, 2026, addresses counsel's fabricated quotations and misrepresented holdings. The opinion recounts counsel accepting Spellbook AI changes without repeating a citation check. It sanctions counsel $5,000, awards $10,000 in fees and strikes both petitions. Damien Charlotin's AI Hallucination Cases database lists the case with Spellbook AI as the tool, and it is the only case naming Spellbook among the database's 2,262 entries.
The findings concern the lawyer's verification and response to the errors; the product attribution appears in counsel's explanation.
Billing and Fee Posture
Does the vendor address what happens to the bill when the work takes an hour instead of six?
Gavel markets faster document preparation and contract review to firms that bill clients. Workflows also supports packaging legal services and collecting payments, but that commerce function does not explain how to bill time saved by AI or disclose an AI expense to a client. No method is published for attributing actual lawyer time to model assisted work. The product's efficiency claims therefore need a separate firm policy on fees, time records, and client communication.
The law firm suite is pitched as a way to improve profitability and the in house suite as a way to retain more work internally. Customer stories describe time savings, including Panasonic's RFP process. The product's per user subscription is separate from a lawyer's charges to clients. A matter level invoice record of AI assisted time or instructions for disclosing those savings on a client's bill are not described in the current pricing offer.
Outside Counsel Guideline Readiness
Can a firm get this vendor through a client’s AI clause without a bespoke negotiation?
The material exists behind a sales conversation. OpenAI is the only AI provider named, as one of the providers Gavel uses, so the list is incomplete. No subprocessor list is published, the Gavel Exec page directs buyers needing security, privacy or vendor details to schedule a demo, and the Terms route customers handling third party data to a survey to decide whether a Data Processing Addendum is needed.
Spellbook identifies OpenAI and Anthropic, provides a processor register and explains provider retention and training restrictions. Its security resources address SOC 2 Type II, HIPAA support and an EU AI Act opinion, while the agreement covers privileged information and legal demand notice. Those materials support a firm's client review. They do not form a single client consent pack, and the firm's account must distinguish provider restrictions from Spellbook's own personalization and monitoring permissions.
Court Disclosure Support
If a judge’s standing order requires an AI disclosure, can the product produce one?
Suggestions arrive as Word revisions and comments, with no described export identifying AI involvement, the producing model, retrieved sources, and human verification for each filing. Workflows can generate court forms from templates, which likewise does not show whether a model contributed to particular language. Gavel describes no court disclosure template or certification workflow. A lawyer who must disclose AI use would need to preserve the necessary record separately.
Word review retains proposed tracked edits, and answers based on contracts or public legal data include source citations. Admin audit logs, added in September 2026, record administrative changes rather than where an AI output came from. Those features preserve portions of the review process and allow a lawyer to check supporting material. An export combining exact model version, retrieved sources and human verification for each generated passage is not described.
The available editing and citation records are therefore partial support for an account of AI use rather than a complete court certification package.
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
- Refusal and Uncertainty Behavior
In summary
Gavel
Gavel separates AI contract work from rules based document production. Exec drafts clauses, reviews agreements against precedent and playbooks, benchmarks terms and answers document questions in Word and on the web. Projects hold instructions and reference files, while Workspaces support shared use. Workflows turns intake answers and Word or PDF templates into finished documents, with client portals and a court form library. For repeatable client intake, the AI Legal Index describes Gavel Workflows taking Clio matter fields into questionnaires and returning completed documents to the matter.
Martin Algie of MIA Contract Lawyers describes using Exec for negotiation and redlining. Streeter Law Firm's estate plan example concerns Workflows, not Exec's AI review. Gavel belongs to Relativity following its June 2026 acquisition. Exec's subscription includes 1,000 monthly completions, while Workflows has separate plans and allowances. Gavel identifies OpenAI among its providers and describes zero retention agreements. Its documents do not map every model to a feature or define when an unsupported answer must stop and return to a lawyer.
Spellbook
Spellbook combines Review, Draft, Ask, Benchmarks and Playbooks with Associate for work across several documents. It operates in Word and Google Docs, and selected iManage files can become context for answers or project references under existing permissions and ethical walls. Autonomous Contract Management takes agreements from Gmail, Outlook, Slack and Salesforce. At contract intake, the AI Legal Index describes Spellbook allowing automatic approval for agreements that satisfy configured rules, while flagged items go to a person and AI edits appear as tracked changes.
Named customers include Dropbox, Panasonic and KMSC Law. Panasonic describes saving three weeks while building an RFP process, a particular customer result rather than a measured expectation for every contract team. The suite's price depends on team members and requires a quote, with training and online support included. OpenAI and Anthropic operate under zero retention and no training commitments. Spellbook's own terms separately allow customer specific personalization and temporary quality monitoring copies. Those permissions matter when setting client data rules, alongside the limits on automatic approvals and the scope of the iManage connection.
Questions buyers ask
Is Gavel or Spellbook better for contract review and document automation?
Gavel Exec and Spellbook both review contracts in Word against instructions and playbooks. Gavel's other product, Workflows, handles questionnaire driven document assembly, client intake and templates. That is a separate purchase from its AI review assistant. Workflows also includes client portals, a court form library and tools for selling legal services online. Spellbook combines contract drafting with Associate for work across files and offers Autonomous Contract Management for incoming agreements. Gavel Workflows fits a firm producing repeatable estate planning documents from intake logic and templates. Spellbook's routing, approval rules and exception handling fit a department trying to reduce a commercial contract queue. From the AI Legal Index, based on each vendor's own published materials as of November 8, 2026. No vendor pays for placement.
How much do Gavel and Spellbook cost?
Gavel Exec costs $160 per user monthly or $1,740 per user billed annually, with 1,000 monthly completions. Its trial includes 25 requests per user, and teams of at least ten can request pricing. Gavel Workflows has a separate subscription starting at $83 monthly. Its Standard plan appears with conflicting public prices and allowances. General onboarding and training are advertised as free, while custom automation work can require a separate quote. Spellbook prices its suite by team members through a custom quote. A seven day trial, training and online support are included, with dedicated support above ten users. Spellbook's in house package includes playbook building. Spellbook's terms renew orders for 12 month terms and cap annual subscription increases at 10 percent. From the AI Legal Index, based on each vendor's own published materials as of November 8, 2026. No vendor pays for placement.
How do Gavel and Spellbook connect to a firm's existing files?
Gavel Exec uses precedent and reference files in its review work and puts revisions and comments in Word. Gavel Workflows connects document generation to Clio Manage, Docusign, DecisionVault, LegalServer and Zapier. The Clio connection can bring contacts, matter fields and billing codes into intake and return finished documents. Spellbook's iManage connection lets an authenticated user select permitted files for Ask or an Associate Project, with existing permissions and ethical walls applied to access. It describes bringing those files into Spellbook's context without promising automatic return of revised documents. Spellbook's other file connections include OneDrive, SharePoint, Google Drive and Dropbox. From the AI Legal Index, based on each vendor's own published materials as of November 8, 2026. No vendor pays for placement.
Do Gavel and Spellbook require a lawyer to approve every AI action?
Gavel Exec places proposed revisions and negotiation comments in Word for a lawyer to review and revise. Its Projects and playbooks guide the work, but its materials do not define a universal stopping rule for unsupported answers or a recovery process after an accepted error. Spellbook Review also presents edits for approval, individually or together, and Associate works with user oversight. Spellbook's Autonomous Contract Management behaves differently. Configured rules can allow automatic approval, including an example for contracts under $50,000 that pass every playbook rule, with flagged items sent to a person. From the AI Legal Index, based on each vendor's own published materials as of November 8, 2026. No vendor pays for placement.
How do Gavel and Spellbook handle client data and model training?
Gavel states that customer prompts and document content do not train models and describes zero retention agreements with providers including OpenAI. Its incorporated privacy policy permits analysis of anonymized Workflows builder questions to improve questionnaire suggestions, while excluding client answers. Spellbook names OpenAI and Anthropic under no training and zero retention commitments, but its own terms permit customer specific personalization and quality assurance copies for up to 90 days. Self service abuse monitoring can retain data for up to 30 days, with exceptions. Gavel offers separate customer storage and several hosting regions. Spellbook stores and processes content in Canada and the United States. From the AI Legal Index, based on each vendor's own published materials as of November 8, 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.
Neither Gavel nor Spellbook publishes a reproducible accuracy evaluation of its full contract workflow or a rule for when an unsupported answer must stop and return to a lawyer. Gavel sells Exec and Workflows separately, and its public Workflows plans show conflicting prices and allowances. Spellbook's own terms allow customer specific personalization and temporary quality monitoring copies. On a Gavel order, the points to settle are whether it covers Exec, Workflows or both, the completion allowance, the Workflows plan, custom automation work, the Exec audit scope and where each enabled AI feature processes data. On a Spellbook order, they are the suite and contract management entitlements, who may set automatic approval rules, how an incorrect approval is corrected, and how personalization and quality monitoring fit the firm's client commitments.