DraftPilot vs Spellbook: how they compare in 2026
DraftPilot and Spellbook both put proposed redlines inside Word and let lawyers decide which changes to apply. DraftPilot gives particular attention to spreading an approved review standard across a business: legal owns positions and escalation rules, while assigned procurement users and contract managers complete a bounded initial review. Its research and portfolio tools connect questions with supporting sources or contract language. Spellbook also supports reusable review instructions, but its Associate product extends the task from one agreement to a set of related files. It breaks a drafting project into steps and updates terms, parties, and issues across the set. That difference is useful for a team choosing between controlled delegation of recurring reviews and broader transactional drafting projects. Neither workflow makes the proposed language a substitute for the responsible lawyer's decision.
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.
DraftPilot's main product is model driven review and drafting inside Word. A selected playbook supplies preferred positions and fallbacks; the AI identifies departures, proposes language, and explains changes to the reviewer. The same models generate playbooks from past work and support conversational drafting, comparison, and research. Mass Review uses AI to answer questions across agreements and connect findings with source language. Conventional functions such as workspaces, permissions, and file conversion support that workflow, but they are not an independent contract management system. Removing the models would remove the review, analysis, and drafting service that customers buy.
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.
AI Chat uses a curated legal network containing legislation, secondary sources, and commentary, with general web access excluded from legal research. Its research guide instructs users to specify the jurisdiction and inspect the list of source links used in an answer. Research can then become proposed changes to the contract, subject to reviewer acceptance. Mass Review separately lets users inspect the contract language underlying a table result. Published totals for the research network differ between the FAQ, guide, and trust center. No reproducible accuracy test, source freshness method, or systematic citation treatment results accompany those totals.
Ask can use selected iManage files and return citations to the team's own contracts. The legal data connection retrieves material from named public sources such as CanLII, CourtListener, Cornell Law, EUR Lex and regional legal information institutes, with links to the underlying authority. Those sources can inform questions, drafting and review inside the same workflow. Their currency follows the source operator's updates. A reproducible accuracy evaluation for the current product, an automatic subsequent treatment check and a stated abstention threshold are not specified. A citation makes an answer inspectable; it does not establish that a quotation or legal proposition has been verified by the reviewing lawyer.
Autonomy and Oversight Model
What the system decides on its own, what a lawyer must approve, and whether the vendor documents where the review point sits. A tool that drafts under review and a tool that files without one are different products and different risks.
The enterprise workflow divides authority between legal and approved business reviewers. Legal owns playbooks, permissions, acceptable positions, and escalation rules; procurement or contract managers perform a bounded first review on agreed contract types. Issues outside the approved route return to legal or the appropriate specialist with the clause and business context. The product proposes tracked edits and comments in Word, which authorized reviewers can edit, accept, or reject. DraftPilot expressly describes this arrangement as something other than autonomous contracting. Its control boundary is organizational approval and exception routing, rather than a published numeric model confidence threshold.
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. The terms place responsibility for reliance and verification with the customer. The existing suite therefore has recognizable human review surfaces, but no universal threshold is stated at which Associate must stop or escalate an unsupported conclusion. The separately announced Autonomous Contract Management offering remains in early access.
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.
Axiom's 2025 white paper describes an eight week pilot in which 18 volunteer attorneys used DraftPilot on client work after an evaluation of eight suppliers. Evidence came from surveys, product analytics, participant calls, and feedback sessions. Forty four percent of participants reported time savings in the 40 to 60 percent band, while 16 of 18 reported moderate or significant improvement in work quality. The vendor's case study also separates tasks such as drafting, issue spotting, and summaries. These are reported observations from motivated volunteers, not a randomized benchmark. Raising Cane's provides another named deployment involving real estate positions and lease review.
Spellbook has named customer accounts involving 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. The current pricing page states use by more than 5,000 legal teams and includes those stories alongside separate firm and in house offerings. 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.
DraftPilot states that customer material does not train its models or public models, and its security guide says original contracts are not stored after analysis. Playbooks remain in the customer's workspace, with permissions controlling their use and editing. OpenAI inputs and outputs receive the stated zero retention arrangement. The broader trust center also names Anthropic and lists 30 days for generated redlines and comments, which narrows the general no retention headline. No accessible commitment directly addresses attorney client privilege or work product. The linked customer terms require sign in, and the trust center requests access before releasing the service agreement or DPA.
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.
The enterprise operating model keeps legal judgment with lawyers and approved specialists. Procurement and contract managers may conduct an initial review only within legal's chosen contract types, positions, and escalation rules. Suggested language remains subject to acceptance, and exceptional issues return to the legal team. This division keeps assistance separate from professional judgment and reserves consequential advice for legal. The research guide also asks the user to state a jurisdiction and intended use. Public pages do not define professional eligibility by jurisdiction or connect those controls to specific competence and supervision duties.
Spellbook's terms identify output as information rather than formal legal advice and 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.
DraftPilot's trust center publishes principles covering privacy in product design, human empowerment, and transparency through security certification. It also describes output protection, operational guardrails, and grounding of AI Chat in a verified source network. Those statements give a direction for responsible use but do not identify an accountable model owner, a release evaluation procedure, or results across languages and contract types. An AI Governance Policy is listed among resources that require access approval, so its contents cannot establish additional public controls. Customer playbooks and escalation rules govern a customer's review process; they do not disclose the vendor's own model testing.
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. A named internal owner, a reproducible release test set and disclosed results about uneven behavior across populations or matter types are not specified in the available framework.
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.
Public resources distinguish contract analysis from stored customer configuration. The security guide says playbooks normally reside on AWS in Ireland and describes immediate deletion of OpenAI API inputs and outputs. The AI posture page separately lists 30 days for generated redlines and comments. Administrators use SSO, SCIM, workspaces, and permissions to control access. Twelve subprocessors are named with service roles, including hosting, model, email, analytics, and business operations providers. Encryption is specified for transit and storage. However, a complete deletion process for retained playbooks, a binding incident notification period, and the DPA terms are not available in the readable public material.
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. The ordinary lifetime of all application history is not stated as a single fixed period.
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.
DraftPilot links to customer terms on SharePoint, but the linked document leads to a Microsoft sign in page. Its public trust center lists a Master Services Agreement and DPA behind an access request. As a result, no readable contract establishes liability caps, indemnity scope, an AI output warranty, or remedies for an incorrect clause or research answer. This is an access limitation, not evidence that the negotiated agreement lacks those provisions. The published review workflow allocates final decisions to authorized people, but that operational allocation does not reveal what financial responsibility DraftPilot accepts when its service makes an error.
Spellbook gives an indemnity for specified intellectual property claims against its software and provides service warranties, while disclaiming the accuracy of generated output and responsibility for customer reliance on it. 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.
The Microsoft Word connection has a described installation and editing path. Users install the add in through AppSource or central IT deployment, open it from the Word ribbon, and work with the agreement already being negotiated. Proposed language becomes native tracked changes, while explanatory comments accompany the edits. Reviewers can accept, reject, or alter individual suggestions and handle later rounds by focusing on counterparty changes. AI Chat can insert drafting or tables into the same file. Workspaces and identity controls manage product access. No comparable public sync specification describes a connection to a legal document management repository.
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.
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.
DraftPilot is delivered through a Word add in and a browser interface, with hosted services handling analysis and team configuration. Its security guide places default playbook storage on AWS in Ireland and offers United States only hosting on Enterprise. The subprocessor list separately identifies Heroku in Ireland and OpenAI and Anthropic in the United States. Those provider locations do not establish where every model request is processed. The guide's OpenAI zero retention statement addresses persistence, not processing geography. Public materials therefore identify hosting choices and part of the provider chain without a complete regional account for all AI tasks.
Spellbook uses AWS as its primary cloud provider and states that customer content is stored and processed in Canada and the United States. 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.
The public trust center names SOC 2 Type II and ISO 27001, with an ISO 27001:2022 certificate and a SOC 2 report listed as resources. Both require access approval, so their audit periods, organizational scope, and qualifications are not visible in the accessible pages. GDPR and UK GDPR are presented as compliance frameworks rather than independent security certifications. Additional resources include a network diagram and CAIQ Lite questionnaire, also behind requests. Product pages specify AES 256 encryption at rest and TLS 1.2 in transit. These published controls support the security description but do not replace examination of the underlying reports.
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 accessible product explanation does not establish the current SOC audit period, auditor and 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.
The main FAQ identifies OpenAI as the provider behind the contract workflow. The trust center supplies a broader inventory: GPT 4 Turbo with an April 2024 version identifier, and Anthropic Claude 3.5 Sonnet with an October 2024 identifier, both accessed through APIs. The subprocessor list confirms both companies and associates them with AI services. The security guide explains OpenAI's zero retention arrangement, but does not extend that provider specific statement expressly to Anthropic. Public material does not map every feature to its active model or commit to customer notification when a model changes. The inventory therefore discloses providers without a complete change framework.
Spellbook names OpenAI and Anthropic as language model suppliers and uses zero retention agreements that keep request and response content in memory for processing rather than persistent storage at those providers. 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. Exact production model versions and a routing map for each feature are not specified. 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.
DraftPilot Pro starts at £7,200 per year for a minimum of three users, equivalent to £2,400 per user annually. A separate Customer Success Advisory Fee applies without a published amount. Everyday review and chat are unlimited under the package, while Mass Review includes an allowance and optional additional capacity. Pro includes playbooks, workspaces, identity controls, onboarding, and optimization support. Enterprise uses a negotiated organization package with tailored deployment and ongoing support. The posted subscription amount is therefore a real entry point, but it is not the complete first year cost because advisory charges and additional portfolio analysis remain unspecified.
Spellbook prices the suite according to the number of team members on a license. 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. 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 describe annual renewal by default and included maintenance and support, but the price of a particular deployment and any separately agreed services remains part of its order.
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.
DraftPilot primarily addresses corporate legal departments handling repeatable commercial agreements. Its enterprise workflow also supports procurement teams and contract managers operating within legal's approved boundaries. The playbook materials cover agreements such as NDAs, services contracts, statements of work, data processing terms, and reseller arrangements. Axiom's deployment extends the audience to lawyers delivering client services, while Raising Cane's demonstrates lease and real estate work. The FAQ describes review across more than 58 languages, including applying a playbook in a different language from the agreement. That breadth is not accompanied by a jurisdiction by jurisdiction account of supported law or tested performance.
Spellbook separates law firm and in house packages and organizes its principal tools around transactional drafting, review, negotiation and questions about agreements. Associate extends work across several files, and iManage access allows firms to use existing contract precedents. Industry material covers energy, healthcare, finance, technology, manufacturing and consumer businesses. The legal data connection adds government and court sources across many regions, but that source breadth does not establish tested competence in every practice. The terms warn about non English results, while Autonomous Contract Management remains in early access. A complete account of unsupported jurisdictions or specialized legal tasks is not specified.
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?
DraftPilot's FAQ says neither it nor OpenAI uses customer data to train models. Its security guide extends that position to contracts and interactions, while the trust center repeats a no training policy. The public customer terms lead to a sign in page and the service agreement requires access approval, so no matching contractual prohibition was verified. The policy is explicit, but the readable evidence does not establish the scope of a binding customer term.
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 AI posture page distinguishes original contract analysis, marked as having no retention, from generated redlines and comments, which it assigns a 30 day period. The security guide separately says playbooks are stored and OpenAI API inputs and outputs are deleted immediately under its zero retention agreement. These statements concern different data layers. No public setting lets a customer shorten the stored suggestion period or apply zero retention across playbooks and generated work.
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 do not establish 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?
Workspaces organize individual and team playbooks, and administrators determine who may view, use, or edit them. This gives legal a way to separate ownership of approved positions from business use of those positions. The public instructions do not establish matter based retrieval restrictions, conflict walls, or inheritance of a document management system's permissions. Playbook access controls therefore provide a narrower form of separation than a documented ethical wall around client files.
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. This protection is specifically described for the iManage connection; it does not establish the same permission inheritance for every optional storage connection.
Third Party Request and Subpoena Notice
If someone subpoenas the vendor for a firm’s data, does the firm hear about it first?
No readable public commitment establishes whether DraftPilot tells a customer before responding to a subpoena or other demand for customer material. The current terms and privacy links lead to SharePoint sign in, while the trust center's service agreement and DPA require access approval. Its security controls and no training policy do not answer this notice question. The finding records the access limit and does not determine what the negotiated agreement might promise.
Spellbook's terms require 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. A published report enumerating government requests and their outcomes is not specified alongside that commitment.
Primary Law Corpus Provenance
Where does the law in this product come from, and does the vendor have the right to use it?
The research guide describes a curated network containing legislation, secondary sources, and legal commentary across more than 150 jurisdictions; the FAQ gives a larger jurisdiction total. Answers expose the links used, so the reviewer can inspect their immediate basis. A public inventory of named collections, licensing permissions, and update schedules is not supplied. The product therefore describes geographic reach and source categories more clearly than the rights and maintenance arrangements behind the research network.
The legal data connection names public 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?
DraftPilot gives users a source list for research answers and asks them to identify the relevant jurisdiction. Those links allow inspection of the cited material, but the public research guide does not describe subsequent case history, treatment flags, or a licensed citator. A real source can still be superseded or limited by later authority. No product mechanism for resolving that separate currency question was identified in the research, FAQ, or trust material.
Spellbook's legal data feature returns citations to public case law, statutes and registers, 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?
The trust center describes grounding and output safeguards, but it does not specify an abstention response when the curated network cannot support an answer. The Issues Report assigns risk to contract departures; that risk describes the agreement against a playbook, rather than model confidence or missing support. Reviewers can reject suggestions and inspect sources, yet those human controls do not show that the system itself refuses an unsupported legal assertion.
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?
The AI Hallucination Cases database maintained by Damien Charlotin contains no entry naming DraftPilot or Draft Pilot. The database concerns judicial decisions involving hallucinated AI material and records implicated tools when identified. DraftPilot does provide legal research as well as contract drafting, so source accuracy remains relevant even though its principal workflow concerns negotiation. The absence of a named case does not test its research answers, proposed clauses, or handling of later legal authority.
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?
DraftPilot gives legal control over approved positions, access rights, and exceptions, and it describes a supervised role for business reviewers. Those operating controls address practical oversight, but the published enterprise and research materials do not map them to a named bar opinion or jurisdiction's professional conduct guidance. In particular, no client consent method or fee treatment framework is tied to a specific professional rule. Product supervision should therefore be distinguished from demonstrated guidance alignment.
Spellbook's educational material addresses competence, candor and checking AI output in general terms, and the company has a relationship with the Canadian Bar Association. Its terms also require appropriate legal review and distinguish output from formal advice. Those positions concern professional responsibilities, but the available account does not map the suite to a named ethics opinion or a set of jurisdiction specific bar requirements. A partnership alone does not supply that mapping.
Billing and Fee Posture
Does the vendor address what happens to the bill when the work takes an hour instead of six?
Axiom's published DraftPilot offering attaches a $250 monthly technology fee to qualifying client engagements and explains that its lawyers use the tool to save time on contract work. Its white paper explicitly presents those gains as a client benefit. This identifies a disclosed software charge reaching the client through the legal service arrangement, rather than only an internal corporate efficiency claim. DraftPilot's own subscription pricing is separate, and no universal billing policy for other customers is stated.
Spellbook presents the law firm suite 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?
A public register names 12 providers and their roles, including OpenAI, Anthropic, hosting, email, analytics, and business support services. The trust center also exposes policy summaries and lists a service agreement, DPA, security reports, and governance policy for access requests. These resources provide material for vendor diligence. They do not include a complete client notification or consent package explaining how a law firm's proposed use satisfies a particular client's outside counsel requirements.
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?
Word tracked changes and comments preserve proposed revisions, while research answers expose their source links and the Issues Report identifies clauses, problems, risk, and possible responses. These are useful components of a review record. Inserted changes appear under the user's Office name, so the file alone does not label which work came from AI. No single export combines the generating model, retrieved authorities, and human verification for a court disclosure.
Word review retains proposed tracked edits, and answers based on contracts or public legal data include source citations. 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
Which one fits
Choose DraftPilot if
- Legal wants procurement reviewers to work within assigned playbooks and explicit exception routes.
- The team frequently turns research answers or contract portfolio findings into review work.
- A recurring process depends on separating playbook ownership from permission to use it.
Choose Spellbook if
- Lawyers need an agent to update terms and party details across related transaction files.
- The practice handles financing packages, disclosure schedules, or similar drafting projects.
- Reviewers want reusable instructions with bulk approval of redlines and comments.
In summary
DraftPilot
DraftPilot builds playbooks from existing agreements, markups, templates, and policies. Legal determines who can edit those positions and who can apply them during review. The AI Legal Index highlights its explicit route for bringing exceptions back to legal with the relevant clause and business context. Users review tracked changes and explanatory comments in Word. AI Chat adds drafting and cited research, while Mass Review organizes answers from multiple contracts with access to their supporting language.
Spellbook
Spellbook Review generates edits and comments against reusable instructions, with individual or bulk approval by the user. Associate handles larger projects across related files, including financing sets, disclosure schedules, and employment packages. Its ability to plan tasks and carry revisions across a set is a product finding identified by the AI Legal Index. Spellbook addresses both corporate teams and law firms, with separate drafting and question answering functions alongside review.
Questions buyers ask
What does DraftPilot delegate to procurement?
Approved reviewers can perform an initial review on agreed contract types using legal's assigned positions and fallbacks. Legal retains ownership of those standards and responsibility for exceptions. From the AI Legal Index, based on each vendor's own published materials as of October 16, 2026. No vendor pays for placement.
How does Spellbook Associate differ from an ordinary redline?
Associate plans and executes a drafting project across a set of files. It can update terms, party information, and related issues across the set rather than treating each contract as an isolated review. From the AI Legal Index, based on each vendor's own published materials as of October 16, 2026. No vendor pays for placement.
Can either tool apply edits without displaying proposed changes?
Both describe review through Word tracked changes and comments. Users can inspect and approve proposed language; Spellbook additionally describes bulk approval, while DraftPilot also permits editing or rejecting individual suggestions. From the AI Legal Index, based on each vendor's own published materials as of October 16, 2026. No vendor pays for placement.
Is Spellbook ACM offered through early access?
Spellbook labels ACM as early access. Review and Associate are separate parts of its contract suite; the ACM label does not establish a general release of the larger service. From the AI Legal Index, based on each vendor's own published materials as of October 16, 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.
DraftPilot's primary audience is corporate legal, with Axiom also using it in client work. Spellbook addresses both law firms and internal legal teams. Proposed revisions remain subject to the relevant professional's review.