Pactly vs Spellbook: how they compare in 2026
Spellbook places drafting and review directly in Word and can bring a law firm's connected repositories into the work. Pactly also reviews in Word, but combines that activity with corporate contract routing and a standalone analysis product. The access model is a particularly concrete difference. For a team connecting client matter files, AI Legal Index highlights Spellbook's iManage permission inheritance, whereas Pactly project membership can widen access beyond the ordinary repository. Pactly's Projects is well suited to repeated questions with inspectable source excerpts and protected corrections. Spellbook's drafting, comparison and Associate workspace cover broader legal work around files and projects. The choice therefore turns on whether the team is extending a lawyer's existing matter environment or organizing a corporate contract process with its own analysis and sharing rules.
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.
Models identify clauses and concepts for playbook review, generate proposed revisions and extract values across contract collections. Assist adds questions about a contract's text and history, with proposed edits and comments in Word. Projects applies the same questions to many agreements and returns a structured table with reasoning and source passages. These are core analysis functions alongside the conventional platform: questionnaires generate approved templates, workflows route approvals, signatures execute agreements and reminders track renewals. Those administrative features do not depend on generative output. Projects is available separately, while Growth and Ultimate include it within an unspecified fair use allowance.
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.
Projects connects an extracted value to reasoning, a quoted source passage and a document view that highlights the relevant text. Users can correct a value, preserve the original AI extraction and mark a result as verified. The guidance names concrete failure modes, including confusion between effective and commencement dates, loss of qualifiers in compound liability caps and missing values in drafts with placeholders. Word review also exposes the clauses behind each playbook assessment. No reproducible benchmark or measured error rate accompanies these mechanisms. The terms expressly warn that AI answers can be incomplete or wrong and require checking against the source.
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.
Assist never applies a contract edit or comment silently: proposed changes require acceptance and enter Word as tracked changes. A reviewer can reject, revise or copy the proposal, and a support message is not sent without the user's choice. Playbook results can be Uncertain, returning the decision to a human; accepted deviations carry a written justification. Projects preserves corrected and verified values during reruns and identifies outdated results when a column question changes. The external MCP connection is read only and cannot create, modify, delete or send signature requests. Standalone Word generation remains described as an upcoming release rather than an existing unrestricted action.
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.
A September 2022 case study identifies Virtuos and its Senior Legal Counsel, Johnathan Yong, and describes an NDA process before and after adopting Pactly. Requests previously took several days or sometimes a week across Word, shared drives and email. Following template questionnaires, legal review and DocuSign execution, reported median finalization fell to two hours and median completion of a signed agreement to twelve hours. Yong describes feedback more than two months after implementation. The account explains the workflow change and measured contract type, although it does not provide the sample size. It measures contract automation rather than the accuracy of today's generative review features.
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.
The service agreement protects nonpublic customer data as confidential information and preserves customer ownership. Its improvement license nevertheless permits analysis of service information involving customer data during the term and use of anonymized aggregate customer data for lawful business purposes afterward. Public marketing says contracts never train AI models, without the same express restriction in the agreement. Sensitive groups can hide contracts from nonmember administrators, but deliberate sharing and project membership can widen access. The provider list explains where contract data travels. No specific attorney client privilege, work product or accidental disclosure protection is stated for lawyers using these features.
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.
Pactly's agreement says the company is not a law firm, use creates no attorney client relationship and the service does not solicit legal advice. It separately warns that AI answers may be wrong and makes the customer responsible for comparison with the source. Product guidance describes the reviewer accepting edits and resolving uncertain playbook findings, and the company explicitly rejects a fully automatic robot lawyer role. Corporate legal departments are its principal audience, with business users working through forms and approvals. The material does not map the controls to named bar guidance or publish jurisdiction specific professional responsibility limits.
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.
Published AI guidance explains how customers verify results, handle uncertain findings and correct extraction mistakes. Release notes describe feature changes, and security materials identify a data protection officer and engineering responsibilities for incidents. These do not establish an AI governance program with an accountable model owner, release testing criteria or results on uneven behavior across languages, populations or contract categories. Positive and negative playbook examples help customers configure review, rather than disclose Pactly's own evaluation program. No formal bias assessment, model card or governance framework accompanies the descriptions of Assist, Projects and playbook review.
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.
Pactly describes encrypted storage and transport, monitoring, backups, vulnerability testing and separate production and test environments. Administrators can require two factor authentication, and high criticality incidents trigger notice to affected customers or all customers when the affected group cannot be identified. A public supplier register details processing functions and regions with advance change notice. The terms provide sixty days to retrieve data after termination, followed by requested deletion with an anonymized aggregate exception. Assist attachments expire after seven days, but ordinary chat history, backup deletion and underlying AI provider retention lack a complete fixed schedule. No definite breach notification deadline is stated.
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.
The service agreement includes an indemnity for third party claims involving patents, copyright or trade secrets infringed by the service, subject to stated exclusions and control of the defense. Available remedies include replacement, modification, a license or termination with unused fees returned. General liability is capped at fees paid in the preceding twelve months and excludes data inaccuracies and several categories of loss. AI answers are expressly described as potentially incomplete or wrong, with verification assigned to the customer. There is no separate output accuracy warranty or AI insurance promise. Availability remedies have separate claim deadlines and exclude beta features.
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 Word plugin uploads an agreement for playbook review, displays matched clauses and proposed fixes, inserts approved language as tracked changes and records review decisions between rounds. The MCP connection exposes eight read only tools for contract text, metadata, parties, playbooks, clauses and account information to external clients such as Claude and Cursor. Public instructions specify API key or OAuth authentication, administrator consent, filters, returned fields and request limits. Separate APIs can generate contracts from templates and support webhooks. DocuSign and Adobe Sign support execution, while the Ultimate plan's SharePoint connection is described as backup only rather than general document synchronization.
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.
Core hosting, compute and Bedrock inference use AWS in Singapore by default, with Malaysia for specified Malaysian customers. Structured data in MongoDB Atlas remains in Singapore for all customers. The supplier table separately identifies United States processing for document conversion, OCR, Cerebras inference and fallback Anthropic or OpenAI services, plus Langfuse monitoring in Germany and Cloudflare's global edge. Those routes make regional hosting different from exclusive regional processing. The SLA also recognizes fully managed private deployments, without a standard public price for them. Singapore and Malaysia have separate service entry points, and the published provider map identifies functions as well as locations.
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.
Pactly identifies ISO 27001 certification in its product, pricing and trust materials and offers its certificate, security whitepaper and penetration test results on request. The public trust FAQ describes Amazon's certified data centers when explaining ISO coverage, so infrastructure attestations need to be distinguished from Pactly's own claim. No openly supplied certificate names its current auditor, validity period and exact company scope. SOC, PCI and FISMA references in the infrastructure section concern AWS rather than a separate Pactly audit. Security practices include vulnerability scans, access logging, staff training and incident response, without resolving that certification scope question.
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.
Pactly names AWS Bedrock for core inference, Cerebras for tasks requiring low latency, and Anthropic and OpenAI as fallback providers when Bedrock is unavailable. The supplier register identifies processing locations and also lists Langfuse for AI monitoring. Customers can subscribe to at least thirty days' written notice before a new subprocessor is engaged and raise an objection during that period. Exact production model families and versions are not supplied for each feature, nor is there a promise to notify every model version change within an existing provider. External MCP clients bring their own model relationship in addition to Pactly's built in AI.
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.
Standalone Projects starts at $69 a month for one user, fifty documents and 250 monthly runs, or $690 annually with 3,000 runs available immediately. Larger packages, additional documents and extra runs have published charges. The wider CLM starts at $99 per user monthly on an annual plan; Growth is $139 with five users minimum and Ultimate $179 with ten. Their monthly AI review allowances are ten, fifty and one hundred respectively. Growth and Ultimate include Projects under fair use without a numerical allowance. Enterprise, migration and some implementation services require a quote. Projects has a fourteen day trial, while the CLM trial lasts thirty days.
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.
Pactly primarily serves corporate legal departments, including solo counsel and small teams across Southeast Asia and other Asia Pacific markets. Larger organizations can configure approval routes, business intake and administrator controls. Supported examples include NDAs, services, procurement, leases, employment and software licenses; Projects extends analysis to loan agreements, insurance and related portfolios. Sales, HR, finance and procurement can participate without turning the product into a consumer legal advice service. The company explicitly describes most customers as internal legal departments rather than firms. No measured language coverage or comprehensive jurisdiction matrix defines where AI interpretation is most reliable.
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?
The agreement permits analysis of service information involving customer data during the subscription for improvement and development. It also allows anonymized customer data to enter aggregate datasets used for lawful business purposes during and after the term, with safeguards against reidentification. Marketing separately promises that contracts never train AI models. The published agreement does not repeat that prohibition or exclude model improvement from its permission.
This records the contractual scope, not a claim that Pactly actually feeds every raw agreement into a shared training process.
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?
Contract data remains retrievable for sixty days after termination. The standard terms then provide deletion on written request, excluding anonymized data already combined into aggregate datasets; online plans may delete after the same access window. Assist attachments expire after seven days, but a complete schedule for normal chat history, backups and provider copies is absent. The upcoming standalone Word generation description gives a thirty day file expiry, which should not be treated as the lifetime of all current AI outputs or contracts saved to the repository.
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?
Pactly uses its own groups and roles rather than inheriting a document management system's matter walls. Sensitive groups hide contracts even from nonmember administrators, but an authorized person can deliberately share a contract outside the group. Projects creates another boundary: every project member sees all present and future project documents, even when the normal repository link is unavailable. Administrators can see all projects.
This is a described access model with important widening rules, not a promise that an original contract restriction automatically follows every AI analysis surface.
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?
The service agreement incorporates Pactly's law enforcement request policy for compelled disclosure of customer data. That policy requires evaluation of governmental requests and notification to the customer where legally permitted, allowing an opportunity to seek protective measures. It applies to hosted and fully managed deployments, while excluding self hosted or customer managed solutions. Foreign authorities are directed through applicable legal and diplomatic channels.
No report of request volumes or outcomes accompanies this commitment, and the general privacy notice's legal disclosure permissions do not replace the more specific customer data policy.
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 analysis context is the customer's agreements, playbooks, approved clauses and related files. Projects reads each row's main contract and supporting amendments or schedules; Word review uses configured positions and fallback language. These are customer supplied materials rather than a catalog of primary law or licensed legal commentary. Pactly does not name an external research corpus, describe the source rights behind general model knowledge or supply an update process for legislation and case law. The public subprocessor list identifies processing suppliers, not a legal content licensing arrangement.
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?
A source passage in Projects establishes where a contract value came from, and playbook review identifies the agreement language relevant to a configured rule. Neither function determines whether a case remains good law or legislation has changed. No licensed citator, subsequent history service or independent treatment signal is described. The legal team maintains its own clause positions and decides whether they remain appropriate.
Contract source highlighting and a verified cell marker therefore support review of supplied material without establishing the continuing validity of an external legal proposition.
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?
Playbook review includes an Uncertain result when a clause cannot be conclusively assessed, directing a person to decide. Each position also defines what happens when no relevant clause is found: compliant, not compliant or uncertain, according to the customer's chosen rule. Projects treats placeholders such as an unfilled name as not found and explains common interpretation failures. These are described negative and uncertainty states rather than a general guarantee of refusal. A wrong configuration of the absent clause rule can still produce a misleading result.
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?
Damien Charlotin's AI Hallucination Cases database contained no entry naming Pactly on October 16, 2026. The database concerns reported court decisions involving fabricated AI material and does not capture every private error in contract analysis. Pactly principally supports corporate agreements rather than preparation of court authorities, which limits what that incident record can say about its usual work. Its terms independently warn that AI answers may be incomplete or incorrect. No named court incident is therefore a limited reporting observation, not a validation of model accuracy.
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?
Pactly explains that it is not a law firm and requires people to verify AI answers against source text. Its review guidance describes accepting tracked edits, recording deviations and resolving uncertain results. These are practical controls for legal work, but the materials do not map them to a named professional ethics opinion, bar rule or regulator's jurisdiction specific AI guidance. References to Singapore privacy law and a data protection officer address data regulation rather than a lawyer's professional obligations when serving a client.
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?
The principal buyer is a company's own legal department, with sales, procurement and HR using forms and approvals around that team's contracts. The Virtuos case measures internal NDA turnaround, and the product's savings claims concern corporate workloads and staffing capacity. Those examples do not involve a lawyer billing an external client for AI assisted work. Published subscription and run charges describe Pactly's software fees, without a client invoice method, pass through rule or accounting of billable legal time. Law firm fee treatment is not part of the described workflow.
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 provider register identifies data categories, functions and regions, including core Bedrock inference, fallback Anthropic and OpenAI services, and AI monitoring. Customers can subscribe to change notices and object before a new supplier is engaged. The trust page offers security reports and a certificate on request, while service terms and the law enforcement policy provide additional diligence material. No dedicated client consent pack or outside counsel AI disclosure form is supplied. Counsel would still need to distinguish the contractual improvement permissions from the marketing training promise.
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?
Projects can export values, reasoning and source references to Excel, and produce a PDF preserving the table's visual labels. Human corrections and verifications record who acted and when inside the application, but the help guide expressly says the Excel export omits that sign off marker. Word review retains tracked edits and written justifications for deviations, while account activity is available through logs. These records preserve parts of the process without a combined export of model version, exact prompts, source context and human approval for a court filing.
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
Which one fits
Choose Pactly if
- A corporate contract process needs review, approvals and signatures.
- Repeated questions should produce a structured table of answers.
- Analysts need original AI values retained alongside their corrections.
Choose Spellbook if
- Lawyers want drafting and review within their everyday Word work.
- iManage matter permissions should govern access to connected material.
- A file and project workspace should support broader legal assistance.
In summary
Pactly
Pactly supports playbook review, approvals and signing for corporate contracts. Projects creates a separate portfolio analysis space with source excerpts, correction history and its own membership based access.
Spellbook
Spellbook brings drafting, review and comparison into Word and connects to legal repositories. Its iManage connection follows existing permissions, while Associate supports work across files and projects.
Questions buyers ask
Do both products work inside Microsoft Word?
Yes. Pactly runs playbook review and proposes tracked changes through its Word plugin. Spellbook also supports drafting, review and comparison in Word, with additional connected repository and project capabilities. From the AI Legal Index, based on each vendor's own published materials as of October 16, 2026. No vendor pays for placement.
Why is project membership important in Pactly?
Membership gives access to all current and future files in a project, including previews, even where ordinary repository permission is absent. That access needs to be understood separately from a person's normal contract groups. From the AI Legal Index, based on each vendor's own published materials as of October 16, 2026. No vendor pays for placement.
How do connected permissions affect the comparison?
For a firm relying on matter access restrictions, AI Legal Index identifies Spellbook's inheritance of iManage permissions as a specific integration benefit. Pactly's own Projects sharing uses a different boundary and can expand access.
Does either review surface remove the need to verify legal assertions?
No. Tracked changes, linked passages and human acceptance help a lawyer inspect work, but do not establish that every assertion is correct or that a cited authority remains valid. 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.
Spellbook's connected repository permissions and Pactly's project membership govern different kinds of access.