Legau vs Spellbook: how they compare in 2026
Legau and Spellbook both put AI drafting and review inside Microsoft Word. Spellbook sells to transactional lawyers and states more than 4,500 teams in over 80 countries, while Legau, founded in Lisbon, also covers research and translation in Word and Outlook. Spellbook sits in the top two bands on twelve of fifteen axes and Legau on ten of fifteen. Spellbook's lead is disclosure about the AI itself. It names GPT-5 and Claude Opus as its models and states zero data retention with OpenAI and Anthropic. Its trust portal carries a subprocessor list, SOC 2 Type II and an EU AI Act opinion from CMS Law. Legau names no model, provider or certification. Legau's counterweight is how it fits a firm. It publishes three tiers from $79 a month, connects by tier to iManage, NetDocuments and SharePoint, and hosts on Azure in the United States or the EU by client jurisdiction. Spellbook publishes no price and names no legal document management connector.
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.
Generative AI drives all five product functions: research, planning, creation, review and translation. The vendor brands the underlying system Legau.AI and offers no conventional mode of the product alongside it. The clearest evidence is commercial rather than editorial: AI Assistant requests are the metered unit on every pricing tier, at 10, 50 and unlimited per user per month, so the machine learning is literally what the buyer is charged for.
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.
Grounding is documented at feature level. The product retrieves from a court decisions database, an enriched layer carrying similar decisions and mentions, a legal papers engine and the firm's own document management system, and an Automatic Quoting feature places retrieved authority into the draft. No accuracy rate, hallucination rate, benchmark or evaluation is published on any located surface. The band is the no published number case; documented grounding is what separates it from C.
Grounding is real and documented with the method described, short of published figures. The vendor states its architecture explicitly and unusually: it does not fine tune, it connects general purpose models to proprietary market data and requires them to fetch and cite rather than rely on learned patterns, on the stated reasoning that putting documents into a model's long term memory encourages hallucination. Compare benchmarks a clause against a stated corpus of more than 2,300 contract types and explains why differences matter, and Ask is published as producing answers with citations. The vendor also publishes educational material on hallucination risk aimed at its own users. Not located as of 29 Aug 2026: any accuracy figure, hallucination rate, test set or evaluation for its own product. Worth noting the CEO has publicly questioned third party benchmarking studies of legal AI tools while the company publishes no measurement of its own.
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 vendor positions the product as assistance with the attorney retaining oversight of drafting, which is a general assurance of human review rather than a stated boundary. No named plan or mode carries a limit on what its output may be used for, and no review checkpoint is described in the product flow. A general assurance is the B shape.
A real written commitment that the models work alongside a supervising lawyer, with a genuine review surface, short of the full control structure. Associate is described as the first AI agent that can work through multi document legal matters with your oversight, which states the oversight position in the product's own headline claim. The delivery model is itself the review mechanism: output arrives as tracked redlines inside a Word document the lawyer accepts or rejects clause by clause, which is a more concrete control point than most of this market publishes. Not located as of 29 Aug 2026: what the agent decides on its own within a matter, the threshold at which it stops, and what happens after an output is wrong.
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.
Three figures are published: 22.1 percent of time gained back per attorney on average, 91 percent of attorneys who used the product saved time, and 75 percent reporting more satisfaction at work. All three are attributed to attorneys who used Legau, with no sample size, measurement period or method published. Five law firm customers are displayed by logo, including PLMJ and Morais Leitao. Named customers are customer evidence rather than outcome evidence, and a figure with no method behind it holds the row at B.
Real deployment evidence with substance, short of the full A bar. Multiple named customer stories are published with individually attributed detail, including Dropbox with a named associate general counsel on video, Panasonic on saving three weeks building an RFP process, KMSC Law with a named partner, Alturas Capital Partners, Elevare Law and Westaway with a named managing partner. The logo wall names large enterprises including eBay, Fender, Crocs, Franklin Templeton, Hapag Lloyd, Valentino and DirecTV, and the vendor states more than 4,500 legal teams across 80 plus countries. Figures appear but attach loosely: a named partner states Spellbook helps him bill an extra hour a day, and Panasonic's three weeks is a stated saving. Not located as of 29 Aug 2026: a dated case study carrying figures with a method a reader can assess.
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 security page documents real architecture. Each customer has its own storage container, external access is restricted to Legau's compute infrastructure, access keys are rotated, and access runs on a need to know basis. The data page states that data is never sold or used beyond providing the service, and marketing surfaces state that client documents are never used to train any AI. Neither attorney client privilege nor work product appears anywhere on the located estate, and no matter level segregation is described. This is confidentiality architecture without the two terms of art that attach a professional duty to it, which holds the row at B.
Substantive published commitments, short of the full picture. Zero data retention agreements are stated as negotiated with both named model providers, OpenAI and Anthropic, with the mechanism described precisely: customer data in requests and responses is not persisted and exists only in memory to process a request. That is a stronger and more specific statement than most of this market publishes. Encryption, SSO through Microsoft Entra with enforced MFA, and audit controls are stated. Two gaps hold this off an A. Attorney client privilege and work product handling is not addressed directly in located material. Segregation between users or matters inside a customer is not documented, and for a firm facing product the applicable standard under the amended band is matter level walls.
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.
Checked 15 September 2026: homepage, the five product pages, both solutions pages, the AI legal assistant page, security, data, pricing, try, and all four documents linked in the footer, being the privacy policy, terms of use, cookies policy and data processing agreement. No statement that the product supplies a tool rather than legal advice, no reference to ABA Formal Opinion 512 or to any bar or ethics guidance, and no jurisdiction limitation located. The published terms of use disclaim accuracy of website content, which is a website disclaimer and not a professional responsibility posture. The audience is attorneys and legal departments throughout, which is recorded here as the mitigating fact rather than credited as a posture.
The audience is unambiguous, transactional lawyers at firms and in house teams, with a signup form that asks a prospect to confirm they are a legal professional and offers no path for non lawyers. The vendor publishes educational material engaging with a lawyer's duty of competence and the obligation to verify AI output. What was not located, after checking the site, the solutions pages, the published terms of service and the learning hub on 29 Aug 2026, is a published position on the advice line, on supervision duties as distinct from competence, or on jurisdiction limits, despite the product being sold in more than 80 countries.
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.
Checked 15 September 2026 across the marketing estate, both trust pages and the four footer legal documents. No governance owner, no pre release testing description, no evaluation practice and no statement on output variation across document types, jurisdictions or parties. Nothing located either way.
A published governance framework with real substance and independent validation, short of testing results or a named owner. The vendor commissioned and publishes an independent legal opinion from CMS Law on its classification under the EU AI Act, states it was assessed as low risk, and makes the full opinion letter downloadable from its trust portal along with the controls implemented for that classification. Commissioning an outside law firm to classify your own AI system and then publishing the letter is a governance artifact rather than a principles page, and no other vendor on this index has published one. Not located as of 29 Aug 2026: a named internal owner of model governance, published pre release testing results for model behaviour, or any disclosure about uneven output across matter types, parties or populations.
AI Safety and Data Stewardship
Retention, deletion, access control, and what happens to prompts and documents after they are processed. Whether the vendor states its subprocessors and its incident practice, or leaves the buyer to assume.
Substantive for the band. Encryption in transit at TLS 1.2 or above with forward secrecy and at rest, per customer storage containers, rotating access keys, zero trust firewall, SSO, injection and cross site prevention, plus published deletion and data portability on request. The gaps that hold it below A are a subprocessor list, an incident response practice and any retention statement covering customer documents, none of which is located. The architecture detail is credited here rather than on Security Certifications, where the question is independent attestation.
Substantive published policy covering most of the ground, short of the full set. Published and specific: zero data retention at the model layer with both providers named and the mechanism described, a complete third party subprocessor list with processing locations in the trust portal, AWS named as primary cloud provider, storage and processing locations stated as Canada and the US, access control through Microsoft Entra so a customer enforces its own authentication and MFA policy, breach notification addressed through implemented HIPAA Breach Notification rule controls with signed business associate agreements downloadable, and a published vulnerability disclosure policy. What holds this off an A is deletion, which the A band requires alongside the rest: searched the security page and FAQ, the published terms of service, the privacy policy and the trust portal entry point on 29 Aug 2026 and located no stated retention period for the vendor's own storage of documents, prompts and outputs, no customer control over that window, and no deletion commitment. This record's own prompt-and-output-retention signal row records the same gap.
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.
Checked 15 September 2026. The only published agreement is a website terms of use, which excludes liability to the fullest extent permissible for use of the website and says nothing about product output. The pricing page names the governing agreement for each tier as Legau Standard for the two lower tiers and Custom for enterprise, and no document under either name is published anywhere on the estate. So no indemnity, no cap, no carve out and no insurance position is reachable, and the agreement that would carry them is named but not published.
Liability is addressed only through published terms a buyer can read in advance, without a position on the exposure the product creates. Terms of service, a privacy policy and a refund policy are all published openly, which is more than several vendors on this index manage, and the refund policy is an unusual published commercial commitment. But searched those documents, the security page and the trust portal entry point on 29 Aug 2026 and located no indemnity running to the customer for third party claims arising from output, no warranty on output, no stated liability cap figure and no insurance position. The vendor will sign a business associate agreement for protected health information, which is a regulatory undertaking rather than recourse for wrong output.
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.
Among the strongest in the lane. The product is a Word and Outlook add in rather than a separate application, so drafting, research, planning, review and translation all run in the client's existing environment, and every function has a stated Outlook variant. Document management support covers SharePoint, OneDrive, iManage, NetDocuments, Google Drive and Dropbox, and the pricing table states which systems each tier reaches, with SharePoint and OneDrive at Starter and the full set from Business upward. A DMS Advanced Layer Sync is published with volume limits of 5,000 and 10,000 documents. Publishing integration depth by tier rather than as a logo wall is what earns the A.
Real integrations exist and are documented, short of depth. The product is delivered as a Microsoft Word add in and also runs in Google Docs, which is the deepest possible integration into the surface where transactional drafting actually happens rather than a connector alongside it. A dedicated integrations page is published, and the ACM product describes contracts arriving from email, Slack and Salesforce. Authentication integrates with Microsoft Entra. Not located as of 29 Aug 2026: legal specific document management connectors such as iManage or NetDocuments, and per integration documentation describing what moves in which direction and what an administrator configures.
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.
Two deployment shapes are published with named regions. The hosted product runs on Microsoft Azure in East US or the EU, and the data page states that data is stored in the United States or Europe depending on the client's jurisdiction, so region follows the buyer rather than being an enterprise negotiation. The Advanced AI Layer add on runs inside the firm's own infrastructure with the firm owning the model. Published option plus named region plus a customer infrastructure path is the A shape.
Deployment model is stated clearly with partial residency detail. The vendor publishes that AWS is the primary cloud provider and that customer data is stored and processed in data centres in Canada and the US, with a full list of subprocessors and their locations in the trust portal. That is a real residency statement naming both jurisdictions. What is missing is customer choice and tenancy: no selectable region, no single tenant or private deployment option, and no statement of the tenancy model was located as of 29 Aug 2026. For a vendor selling into more than 80 countries, the absence of an EU or UK processing option is a live buyer question the site does not address.
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.
Checked 15 September 2026. The security page is substantive and describes architecture at length, but it names no certification at all: no SOC 2, no ISO 27001, no penetration test summary, no trust portal and no audit of any kind, claimed or attested. There is also no self serve request route, so the three tier treatment does not reach even its middle tier. This axis measures independent attestation a buyer can pull, and none exists. The architecture the page does publish is credited on AI Safety and Data Stewardship so that it is not lost. Worth noting for context that the vendor is deployed at two of the largest firms in Portugal, which means procurement has asked these questions and the answers are simply not public.
Certification is real and stated with an open route to the evidence, short of published scope. SOC 2 Type II and HIPAA are both named, and the badges on the home page link directly to named, dated resources in the trust portal rather than sitting as decorative images, which is a materially better pattern than most of this market and is why this is not a C. The trust portal is at a stable URL and carries downloadable documents including business associate agreements and the EU AI Act opinion letter. Under the three tier test this is a self serve request flow rather than a sales gate. What was not located as of 29 Aug 2026 is the audit coverage period, the scope, or the name of the auditing firm.
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.
Checked 15 September 2026 across the marketing estate, the security and data pages and the data processing agreement. No model is named, no model provider is named, and no subprocessor list is published. Legau.AI and Advanced AI Layer are product brand names rather than disclosure. The data processing agreement defines a sub subcontractor category and governs their appointment but publishes no list of who they are. A legal buyer cannot learn from any public surface whose model reads its drafts.
The models underneath are named, their providers identified, where they run is stated, and the commercial terms binding them are disclosed. The vendor names GPT-5 and Claude Opus as the models powering the product on its own home page, names OpenAI and Anthropic as the providers, states the zero data retention agreements negotiated with each and what that means technically, names AWS as the primary cloud provider, states processing locations as Canada and the US, and publishes a complete third party subprocessor list at a stable trust portal URL. Naming the specific model versions in marketing copy is rare and is what a customer inheriting the dependency actually needs. Short of the very top only in that no explicit commitment to notify customers before the model supply chain changes was located, though the subprocessor list is the mechanism through which such a change would surface.
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.
Three tiers carry published monthly rates of 79, 99 and 139 US dollars, with a full feature comparison matrix across research, creation, review, planning, translation and support. The unit of charge is published rather than implied: AI Assistant credits at 10, 50 and unlimited requests per user per month, documents segmented at 300 and 600, and DMS sync at 5,000 and 10,000 documents. SSO type, interface languages, support channel, onboarding format and reporting cadence are all stated by tier. Two add ons, the Advanced Layer and electronic signature, are request only and that is stated plainly. The one qualifier recorded rather than penalised is that every tier reads From, and the page says pricing is tailored to setup complexity, adoption and organisation size, so the published figure is a floor.
Pricing is gated behind a demo request while tier names and feature splits are published, so the shape is visible and the number is not. The pricing page publishes two named tiers, Law Firms and In House Teams, itemises what each includes, states that pricing is structured around the number of team members on a licence, and confirms a 7 day free trial with extended trials available for larger organisations. Free access for academic institutions is published. So a buyer learns the unit of charge and the packaging without a sales call. No figure appears at any tier, and the only route to one is a demo booking. Checked the pricing page, the home page and the footer on 29 Aug 2026.
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.
Practice coverage is enumerated rather than claimed: twelve areas across a transactional page covering corporate and M&A, commercial, banking and finance, real estate, capital markets and securities and intellectual property, and a non transactional page covering litigation, tax, regulatory and compliance, labour and employment, antitrust and competition, and government and public. The buyer is stated as a law firm or legal department. What holds the row below A is firm size: no band is stated anywhere, and the three pricing tiers are the only proxy for whether this is sold to solos, midlaw or the large firms whose logos appear on the homepage.
Segment and practice coverage is described with substance, short of the boundaries. Two buyer segments carry dedicated pages, law firms and in house legal, and six industries have their own: energy, healthcare, financial services, technology, manufacturing, and retail and consumer goods. Firm size is addressed in the trial form from 1 to 10 through 200 plus, and the vendor states more than 4,500 teams across 80 plus countries. Practice focus is stated clearly and repeatedly as transactional and commercial legal work rather than claimed broadly, which is a real self limit. Short of an A because litigation appears as an option in the signup form while nothing on the site describes litigation support, and because no statement of which practice areas or firm sizes the product is not built for was located.
The 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?
Vendor surfaces state plainly that customer documents, templates and client data are not used to train any AI, and the AI legal assistant page repeats the commitment for the Advanced AI Layer, adding that the firm owns its own model. No matching term is located in the published data processing agreement, which governs personal data processing and does not address training in either direction. The commitment names the thing, so this is not silence, but it lives in policy rather than in an agreement a client could hold the firm to.
The vendor states plainly that zero data retention means its model providers never learn from, train on or store customer data, and the security FAQ describes the mechanism: agreements negotiated with OpenAI and Anthropic under which customer data in requests and responses is not persisted and exists only in memory to process a request. The commitment as located covers the model providers specifically and sits on a public security page and pricing page rather than in a term of the published customer agreement, which was searched on 29 Aug 2026.
No separate statement was located as to whether the vendor itself trains on customer content, as distinct from its providers.
Prompt and Output Retention
How long does the product keep what a lawyer typed, and can that be set to zero?
The data processing agreement bounds storage of personal data to the life of the contract. That clause does not reach prompts and drafts, because the vendor defines its personal data footprint narrowly as the name, title and email of users, while uploaded documents are handled separately as Customer Assets on the security page. No located material states how long prompts, outputs or uploaded documents persist, or whether a customer can set that period to zero.
At the model provider layer the answer is specific and zero: data in requests and responses is not persisted and exists only in memory. That is a real published retention position for the part of the pipeline buyers ask about most. What was not located as of 29 Aug 2026, after checking the security page, the published terms of service, the privacy policy and the trust portal entry point, is any statement of how long the vendor itself retains prompts, documents and outputs in its own systems, whether a customer controls that window, or whether deletion is available.
Recorded at the middle value because retention is acknowledged and answered for one layer without a period for the other.
Ethical Walls and Matter Segregation
Does retrieval respect the firm’s ethical walls, or can the model read across them?
Per customer storage containers separate one firm from another, which is tenancy rather than an ethical wall. Nothing located addresses walls or matter level segregation inside a firm, and no material states whether retrieval inherits document management system permissions at query time. The question is live for this product specifically, because it indexes the firm's own document management system and answers out of it.
Searched the security page, the integrations page, the published terms of service and the trust portal entry point on 29 Aug 2026. No vendor material addresses ethical walls or segregation between users or matters. Authentication runs through Microsoft Entra, so a firm enforces its own identity policy at sign in, but that governs who can open the add in rather than what the product may retrieve per user. No legal document management integration was located whose permissions retrieval could inherit at query time. For a product sold to law firms this is the applicable standard and it is not addressed.
Third Party Request and Subpoena Notice
If someone subpoenas the vendor for a firm’s data, does the firm hear about it first?
The privacy policy states that personal data may be disclosed to third parties to comply with applicable law or legal process, and gives responding to a subpoena as its worked example. No commitment to notify the customer is located, and no discretion over notice is reserved either way. The vendor has told the customer that data can leave and has said nothing about whether the firm hears of it. No transparency report is published.
Searched the published terms of service, the privacy policy, the security page and FAQ, and the trust portal entry point on 29 Aug 2026. No clause committing to notify a customer of a government or law enforcement request for their data was located, and no transparency report was located. This records a search across the published documents that did not surface the clause rather than a reading of every document end to end.
Primary Law Corpus Provenance
Where does the law in this product come from, and does the vendor have the right to use it?
The product is described as drawing on a court decisions database, an enriched court decisions layer and a legal papers engine, plus knowledge banks of court decisions and doctrine. No jurisdiction, court, publisher or license basis is identified for any of it, and no update cadence is stated. The only rights related phrase located is a carve out on the pricing page describing the legal papers engine as excluding publishers. Checked 15 September 2026 across the marketing estate and the four footer legal documents.
The corpus here is contract market data rather than primary law, which is the right shape for a transactional product and reads differently against a signal written for case law. Coverage is quantified: Compare benchmarks a clause against a stated more than 2,300 contract types and thousands of similar agreements, and the vendor describes the architecture as fetching from proprietary market data sources and citing them.
What is not published is where that market data comes from, on what rights basis it was assembled, or how current it is. Searched the Compare feature page, the clause index, the state of contracts report page and the security pages on 29 Aug 2026.
Good Law Verification
Does the product tell you when the authority it just cited has been overruled?
The enriched court decisions layer surfaces similar decisions, mentions and related legal papers, which is a citation network rather than a treatment signal. No located material states whether authority the product returns is checked for subsequent history, and no citator is named. Checked 15 September 2026 across the marketing estate and the footer legal documents.
Searched the site, the Ask and Compare feature pages, the learning hub and the help center entry point on 29 Aug 2026. No material was located addressing whether authority returned carries a treatment signal or whether subsequent history is checked, and no commercial citator license was located. Noted for context: this is a transactional contract product whose grounding corpus is contract market data rather than case law, so a citator is largely outside its design. The absence is recorded as found, and a reader should weigh it against what the product is for.
Refusal and Uncertainty Behavior
What does the product do when the answer is not in the corpus?
No located material describes what the product does when it cannot ground an answer. No abstention path is documented, no confidence or grounding score is exposed in published material, and no evaluation is published. Checked 15 September 2026 across the marketing estate and the footer legal documents.
Searched the site, the feature pages, the learning hub and the help center entry point on 29 Aug 2026. No published material describes what the product does when it cannot ground an answer, and no explicit no answer path or confidence signal exposed to the user was located. The vendor publishes a clear architectural position that models should fetch and cite rather than rely on learned patterns, which is about how an answer is grounded rather than what happens when nothing supports one.
Fabricated Citation Record
Does a public court record exist addressing fabricated or hallucinated legal citations in output from this product?
No court order, opinion or disciplinary record addressing fabricated or hallucinated legal citations in output from this product was located as of 15 September 2026. The tracker searched was the AI Hallucination Cases database maintained by Damien Charlotin, alongside a general search of the public record. This is a statement about the public record on that one subject as of that date. It is not a finding about the product, and this signal is not a litigation history.
No court order, opinion or disciplinary record naming this product has been located as of 29 Aug 2026. Instrument searched: the AI Hallucination Cases database maintained by Damien Charlotin, which tracks court decisions worldwide involving AI generated hallucinated content and records the AI tool implicated where it is known. Also checked published 2026 sanctions summaries and secondary sanctions trackers. The entries located name filers, and in some rows other products, rather than this one.
This is a statement about the public record on the date shown and not a clearance. Note that this vendor publishes its own editorial content about AI hallucination sanctions, which surfaces in searches for its name and is not a record about the product. Note also that the product is transactional rather than litigation facing, so its output is less likely to reach a court filing in the first place.
Bar Guidance Alignment
Has the vendor engaged in public with the ethics opinions its buyers are bound by?
No located public material engages with bar or ethics guidance. ABA Formal Opinion 512 is not referenced, no state or national bar opinion is named, and no risk committee facing material is published. Checked 15 September 2026 across the marketing estate, both trust pages and the four footer legal documents.
Public materials refer to professional responsibility in general terms without naming guidance. The vendor publishes substantial educational content on hallucination risk that engages with a lawyer's duty of competence and candour to the court and the obligation to verify AI output, and it is named exclusive AI partner of the Canadian Bar Association, which is a relationship with a bar association rather than engagement with its guidance.
Searched the site, the learning hub, the blog and the guides and reports index on 29 Aug 2026 and located no engagement with a named ethics opinion, including ABA Formal Opinion 512, any state bar guidance, or any Canadian law society guidance.
Billing and Fee Posture
Does the vendor address what happens to the bill when the work takes an hour instead of six?
The vendor markets time savings to the buyer, publishing 22.1 percent of time gained back per attorney and 91 percent of attorneys saving time, and the product sits inside a fee relationship between a law firm and its clients where compressed hours change the invoice. No located material addresses billing treatment, fee disclosure, or what a firm should tell a client about AI assisted work. The savings claim is published and the client side of it is not.
Savings are claimed with nothing published on the client's side of the equation, and unusually the framing runs the other way. A published customer quote from a named partner states the product probably helps him bill an extra hour a day, and the pricing page is headed on boosting profitability, alongside a published return on investment calculator and repeated ten times faster drafting claims. Searched the site, the pricing page, the customer stories and the learning hub on 29 Aug 2026 and located no per matter record of AI assisted work intended for fee purposes, and no guidance on billing, fee or client disclosure treatment.
A published claim about billing more hours, in a market where ethics guidance is direct that a lawyer bills for time actually spent, is the sharpest version of this signal on the index so far.
Outside Counsel Guideline Readiness
Can a firm get this vendor through a client’s AI clause without a bespoke negotiation?
No subprocessor list, no model provider list and no client facing disclosure material located. The data processing agreement defines a sub subcontractor category and governs how they are appointed, but publishes no list of who they are, so a firm facing an AI clause in a client's outside counsel guidelines has nothing here it can forward. Checked 15 September 2026.
A firm can assemble most of what a client AI clause asks for without a sales conversation. Published through a trust portal at a stable URL: a complete third party subprocessor list with processing locations, named model providers with the zero data retention terms binding them, a dated SOC 2 Type II resource, a HIPAA resource, signed business associate agreements from vendors handling protected health information, and an independent EU AI Act classification opinion from CMS Law.
Short of the top value because the material is a self serve portal rather than a client facing consent or notification pack the firm could forward as assembled, and no such pack was located as of 29 Aug 2026.
Court Disclosure Support
If a judge’s standing order requires an AI disclosure, can the product produce one?
No located material addresses court disclosure obligations, judicial standing orders or verification certification, and no export covering model used, sources retrieved and human verification is described. Checked 15 September 2026 across the marketing estate and the footer legal documents.
Searched the site, the feature pages, the security page and the help center entry point on 29 Aug 2026. The vendor states audit controls exist and Ask is published as returning answers with citations, but no per document export covering model used, sources retrieved and human verification together was located, and no disclosure or certification support material was located. Noted for context: this is a transactional drafting product whose output is contracts rather than court filings, so a judicial AI disclosure order is less likely to reach it. Recorded as found.
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.
- Ethical Walls and Matter Segregation
- Good Law Verification
- Refusal and Uncertainty Behavior
- Court Disclosure Support
Which one fits
Choose Legau if
- Your documents live in iManage or NetDocuments. Legau connects to SharePoint and OneDrive on its Starter tier and adds iManage, NetDocuments, Google Drive and Dropbox from Business upward, with document sync limits stated per tier, so drafting and research draw on the firm's own files.
- You want the model inside your own infrastructure. Legau's Advanced AI Layer add on runs a firm specific model on the firm's own infrastructure, with the firm owning the model, and its hosted product sits on Azure in the United States or the EU according to the client's jurisdiction.
- Your work goes beyond contracts. Legau covers research, planning, drafting, review and translation in Word and Outlook, draws on its own court decisions database, and lists twelve practice areas from M&A and capital markets to litigation, tax and employment.
Choose Spellbook if
- You need to know which models read your drafts. Spellbook names GPT-5 and Claude Opus, states zero data retention agreements with OpenAI and Anthropic under which request data exists only in memory, and publishes a subprocessor list with processing locations in Canada and the United States.
- Your procurement team wants attestations and an AI Act position. Spellbook's trust portal links SOC 2 Type II and HIPAA resources and business associate agreements, and carries an independent CMS Law opinion classifying its product as low risk under the EU AI Act.
- You want clauses benchmarked against the market. Spellbook's Compare checks a clause against thousands of similar agreements across more than 2,300 contract types and explains why differences matter, and its Associate agent works through multi document matters under your oversight.
In summary
Legau
Legau is a legal drafting platform founded in Lisbon in 2021 by attorneys, running inside Microsoft Word and Outlook for research, planning, drafting, review and translation across all document types, and launched in the United States in 2024. It connects to SharePoint, OneDrive, iManage, NetDocuments, Google Drive and Dropbox, and retrieves from its own court decisions database and the firm's files. The AI Legal Index grades it in the top two bands on ten of fifteen capability axes, with A grades on AI centrality, integration depth, deployment and pricing. It shows PLMJ and Morais Leitao among its customers. As of 15 September 2026 the index located no named model, no security certification and no published customer agreement.
Spellbook
Spellbook, founded in 2018 in St John's, Newfoundland and renamed from Rally in 2022, is an AI contract review and drafting tool for transactional lawyers that runs as a Word add in and in Google Docs, with Review, Draft, Playbooks, Ask, Compare and a multi document Associate agent. The AI Legal Index grades it in the top two bands on twelve of fifteen capability axes, with A grades on AI centrality and model supply chain disclosure. It names GPT-5 and Claude Opus, states zero data retention with OpenAI and Anthropic, and publishes a trust portal with SOC 2 Type II. It states more than 4,500 teams in over 80 countries. As of 29 August 2026 the index located no price figure, deletion commitment or accuracy measurement.
Questions buyers ask
Legau vs Spellbook: which is better for drafting in Word?
On published evidence Spellbook sits in the top two bands on twelve of fifteen AI Legal Index capability axes and Legau on ten of fifteen. Spellbook publishes far more about its models, providers and security attestations. Legau publishes more about fitting a firm's systems, with document management connectors by tier, a choice of US or EU hosting and published prices. Firms running iManage or NetDocuments will find more that fits in Legau.
Which AI models does Spellbook use?
Spellbook's home page names GPT-5 and Claude Opus, and its security pages name OpenAI and Anthropic as providers with zero data retention agreements, under which request data exists only in memory. Its trust portal publishes a subprocessor list with processing in Canada and the United States. Legau names no model or provider anywhere on its site. Graded by AI Legal Index against 15 capability axes and 12 legal signals, including privilege handling and citation accuracy, from each vendor's own published materials, verified September 25, 2026. No vendor pays for placement.
How much do Legau and Spellbook cost?
Legau publishes three tiers from $79, $99 and $139 a month, with AI requests, document volumes and document management sync limits stated per tier; each figure is a floor tailored to the firm. Spellbook prices by the number of team members on a license, with two tiers for law firms and in house teams, and publishes no figure; it offers a seven day free trial. Graded by AI Legal Index against 15 capability axes and 12 legal signals, including privilege handling and citation accuracy, from each vendor's own published materials, verified September 25, 2026. No vendor pays for placement.
Does Legau work with iManage and NetDocuments?
Yes, from its Business tier. Legau's pricing table lists SharePoint and OneDrive at Starter and adds iManage, NetDocuments, Google Drive and Dropbox from Business upward, with document sync limits of 5,000 and 10,000. Spellbook names Word, Google Docs, email, Slack and Salesforce as integration surfaces, but no legal document management connector. Graded by AI Legal Index against 15 capability axes and 12 legal signals, including privilege handling and citation accuracy, from each vendor's own published materials, verified September 25, 2026. No vendor pays for placement.
What do Legau and Spellbook both leave unpublished?
How accurate their drafts are and how long the vendor keeps them. Neither publishes an accuracy figure or test set, or describes what its AI does when it cannot support an answer. Neither states how long it keeps prompts, drafts and uploaded documents in its own systems, or addresses walls between matters inside a firm. Neither says whether cited authority is checked for later treatment. Graded by AI Legal Index against 15 capability axes and 12 legal signals, including privilege handling and citation accuracy, from each vendor's own published materials, verified September 25, 2026. No vendor pays for placement.
Three readings to weigh. Legau's pricing names its governing agreements, Legau Standard and a custom enterprise agreement, but neither is published, so its low grades on liability and professional responsibility record what could be read. A named partner quoted on Spellbook's site says the product helps him bill an extra hour a day, and nothing on its site addresses how AI assisted work is billed. Legau's court decisions database names no jurisdiction or publisher. Legau was verified on 15 September 2026 and Spellbook on 29 August 2026. Neither vendor reviewed this page.
Neither vendor paid for inclusion, placement or a grade, and neither reviewed this page before it published. Everything above comes from public material on the dates shown. How the index grades.