Ivo vs Spellbook: how they compare in 2026
Ivo and Spellbook both put AI contract review inside the document a lawyer is already editing, and they split on who they are built for. Ivo sells to in house legal teams at large enterprises. Its Review assigns an agent to each topic, a supervising agent reconciles their findings, and redlines land in Word or Google Docs against the company's playbooks and its own executed contracts. Intelligence connects to contract repositories, and Collaborate routes intake from Salesforce and approvals through Slack. Spellbook serves law firms as well as in house teams from inside Word, with Review, Draft, Ask, Compare and an Associate agent that works across several files. Its iManage connection keeps existing permissions and ethical walls in force. Their contract terms differ sharply. Ivo's standard terms cap its liability at $100 and have the customer indemnify Ivo, with enterprise customers signing a separate agreement. Spellbook's terms carry an intellectual property indemnity and a cap of twelve months of fees, with exceptions for confidentiality and data incidents.
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.
Ivo applies models to contract review, portfolio analysis and the contracting workflow. Ivo Intelligence connects to contracts where they already live and adds extraction, plain English questions, amendment timelines and flags on departures from standard positions. Ivo Review assigns a separate agent to each topic, with a supervising agent that reconciles overlapping findings into one recommendation per topic, and applies playbook backed redlines in Word or Google Docs. Review also benchmarks clauses against the customer's executed contracts, narrowed by contract type, governing law, party role and industry, and Playbook Builder derives positions from those agreements. Ivo Assistant compares documents, researches regulation and reports on changes in the law. Each of these steps is model work over the customer's own contracts.
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.
The contract review comparison set Ivo, Claude for Word running Opus 4.6 and a practicing Special Counsel at an Am Law 25 firm against the same 19 real, anonymized contracts. They spanned NDAs, MSAs, DPAs and other commercial types. Three attorneys with recent Am Law 100 or in house technology experience rated each output blind from 1 to 10 on issue spotting, surgical redlining, formatting retention, judgment and comments. The attorney averaged 4.56, Ivo 4.52 and Claude for Word 3.50, and the redlines and playbooks are downloadable. A contract took Ivo 2 minutes 45 seconds on average, against about 32 minutes for the attorney. The study names formatting retention as Ivo's weak area, and Ivo ran the study itself. Separately, Intelligence reports 97% accuracy against the Contract Understanding Atticus Dataset of 30,000 expert annotations, and Assistant returns cited answers from more than 100 legal sources.
Ask can use selected iManage files and return citations to the team's own contracts. The legal data connection retrieves material from named open legal databases such as CanLII, CourtListener, Cornell Law, EUR Lex and regional legal information institutes, with links to the underlying authority. Those sources can inform questions, drafting and review inside the same workflow. Their currency follows the source operator's updates. Spellbook publishes no reproducible accuracy evaluation for the current product, no automatic subsequent treatment check and no abstention threshold. A citation makes an answer inspectable, but checking the quotation or legal proposition against it is still the reviewing lawyer's job.
Autonomy and Oversight Model
What the system decides on its own, what a lawyer must approve, and whether the vendor documents where the review point sits. A tool that drafts under review and a tool that files without one are different products and different risks.
Redlines appear in Word or Google Docs for a reviewer to accept or reject. Playbook Builder cites the agreements behind its proposed positions and allows review before saving. Collaborate selects a workflow when an agreement arrives, progresses low risk agreements to signature and routes matters requiring judgment to a reviewer. The customer supplies the workflow steps, playbook and policy in plain English. The terms require use under a lawyer's direct supervision. Precise criteria for classifying a contract as low risk and the response to an incorrect automatic approval are not specified.
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.
Atlassian, Canva and CDW are featured with case studies, and Suhayb Ahmed, head of commercial legal at Canva, and Carla Michel, director and senior counsel at CDW, are quoted on the home page. Quora's legal operations lead, Adrie Christensen, says the first pass of redlines back to a counterparty fell from about 11 hours to 5 minutes. An assistant general counsel at Kandji says Ivo saved hundreds of hours in a year. None of these figures carries a date or a stated method. The benchmarking study compares output quality rather than production use: the attorney took 10 hours for the redlining tasks, while Ivo averaged 2 minutes and 45 seconds a contract.
Named customer accounts involve Dropbox, Panasonic, KMSC Law, Alturas Capital Partners and Elevare Law. Panasonic's account concerns saving three weeks while building an RFP process, while other testimonials describe drafting capacity and keeping work inside the legal team. 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.
Ivo's policy prohibits training AI models on customer data, while its general terms grant use of customer content to provide the service without a matching express training prohibition. Intelligence offers separate rooms for projects, acquisitions and business units, and customers assign roles and permissions. The terms provide deletion of customer content on request within 60 days after termination, with ordinary backup and record retention exceptions. Their No Legal Advice clause waives claims of malpractice, privilege and an attorney client relationship in relation to Ivo. Model provider retention and the detailed enforcement of room boundaries are not specified.
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 terms carry a No Legal Advice clause. It says the service is no substitute for professional legal advice and that its legal information is general. Ivo does not guarantee the accuracy, completeness or timeliness of legal materials, and no attorney client or special relationship forms, including during implementation or training. The same clause has the customer warrant that use runs under the direct supervision of a lawyer representing it, which carries the supervision duty into the contract. No jurisdiction limit is stated, and no bar or ethics opinion is cited.
Output counts as information rather than formal legal advice under Spellbook's terms, which place verification and appropriate lawyer review with the customer. The product is directed to law firms and legal departments, with review controls inside Word and oversight of Associate's work across files. The agreement also warns that non English use can produce unsatisfactory results. That is a concrete language limitation, but not a tested jurisdictional coverage matrix or a map of which regulated services the software can provide. Human acceptance of a redline remains part of contract work, and an answer from a cited public source is not a substitute for checking its legal application.
AI Governance and Bias Disclosure
Published governance over model behavior: who owns it inside the vendor, what is tested before release, and what is disclosed about disparate output across matter types, parties, or populations.
Ivo's benchmark compares contract redlines through a blind review method. Three attorneys with recent Am Law 100 or in house experience judged redlines from Ivo, Claude for Word and a practicing Special Counsel across 19 real, anonymized contracts. Every output was stripped of identifying information and rated blind on five criteria, issue spotting, surgical redlining, formatting retention, comments and judgment. Ratings run from 1 to 10 as the mean of the three judges: 4.56 for the attorney, 4.52 for Ivo and 3.50 for Claude for Word. The study page sets out the playbook positions the redlines were judged against and offers the full report for download. No responsible AI policy, framework or accountable owner sits beside it, and SOC 2 and ISO 27001 cover information security.
Spellbook's terms describe internal AI risk and prohibited use policies, staff education and regular reassessment of ethical and legal requirements. Its security material also cites a CMS Law opinion classifying the product under the EU AI Act and identifying applicable controls. These are concrete governance arrangements beyond a general promise to act responsibly. The product supports verification through citations and user approval of edits, but those controls are separate from evaluating a model before release. The framework names no internal owner, no reproducible release test set and no results on uneven behavior across populations or matter types.
AI Safety and Data Stewardship
Retention, deletion, access control, and what happens to prompts and documents after they are processed. Whether the vendor states its subprocessors and its incident practice, or leaves the buyer to assume.
The privacy policy keeps a contract or document tied to a thumbs down rating for 14 days before deleting or deidentifying it. Other personal information is kept as long as Ivo has a business or operational purpose, and on request after termination customer content is deleted within 60 days. Access control appears as the customer assigning roles and permissions to its authorized users. The subprocessor list and security documents sit in a Vanta trust center. No incident or breach notification practice 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. Outside those secondary uses, Spellbook gives no single fixed period for how long application history is kept.
AI Liability and Recourse
What the vendor stands behind contractually when its output is wrong. Indemnities, caps, carve outs, insurance, and whether any of it is published or only reachable through a negotiated agreement.
The terms of 20 November 2024 cap Ivo's total liability at $100, and more than one claim does not raise the limit. Indirect, consequential and punitive damages are excluded, and clause 8 disclaims all warranties, accuracy and fitness included. The customer indemnifies Ivo, and no indemnity runs the other way. The customer also releases Ivo from every past, present and future claim relating to the service and waives section 1542 of the California Civil Code for unknown claims. Clause 14 adds a waiver of malpractice and privilege claims. Ivo's trust center lists a certificate of insurance among the documents it releases on request, and enterprise customers sign a separate Services Agreement that is not publicly available.
Specified intellectual property claims against the software are covered by an indemnity, alongside service warranties, while the accuracy of generated output and responsibility for customer reliance on it are disclaimed. The general limit is twelve months of fees, with exceptions including confidentiality, security, data incidents and indemnification duties. The agreement includes mutual protection for specified data incident claims and gross misconduct. Beta Features have separate warranty exclusions and a CAD 10,000 cap. These are concrete protections for platform and data risks, but they do not provide an accuracy warranty compensating a client when an accepted clause or legal assertion is wrong.
Practice Systems Integration Depth
How deeply the product reaches into the systems legal work already lives in: document management such as iManage and NetDocuments, Word and Outlook, contract lifecycle management, matter management, e-billing, and court filing systems.
Review and Assistant run as add ins inside Microsoft Word and Google Docs, and review works on Word, PDF and Google Docs files. Intelligence connects to contracts wherever they are stored. Collaborate takes intake in Salesforce, redlines in Word and approvals in Slack, and syncs each teammate's changes back to the same deal with version history. Connections also reach existing file systems, cloud storage, common CRMs and e signature vendors. Slack, Google Docs and Teams are among the services a customer may connect, through which Ivo may receive messages and attachments. Named document management systems, a developer reference and what syncs in each direction are not described.
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.
Delivery is in the cloud, with no region, residency option, tenancy model or hosting provider stated. The privacy policy says the business operates from the United States, Canada and other jurisdictions. Personal information may be transferred to and stored in the United States and other places whose laws differ, and transfers out of Europe rely on standard contractual clauses.
Customer content is stored and processed in Canada and the United States, Spellbook states, with AWS as its primary cloud provider. Third party model requests are handled under zero retention agreements with OpenAI and Anthropic, while Spellbook itself has separate retention rights for quality and abuse monitoring. The Word add in and Associate connect to shared cloud services, including optional sources such as iManage. The public description identifies storage and processing countries but does not offer a per tier residency selector or a dedicated customer deployment. A source system's location therefore does not confine every later processing step to that same location.
Security Certifications and Trust Center
Independent attestation a buyer can pull without a sales call: SOC 2, ISO 27001, penetration test summaries, a trust center with current reports and named scope rather than a badge image.
SOC 2 Type II and ISO 27001 certification are stated, with GDPR and CCPA compliance. A Vanta trust center handles requests for the certifications and supplies subprocessor and audit material. No auditor, coverage period or scope appears on the open site. Access to the underlying reports depends on approval through that portal.
Spellbook states that it is SOC 2 Type II compliant and provides a trust portal for reports, processor information and compliance resources. Its security program uses encryption, Microsoft identity controls and agreements governing model providers. The public security explanation also describes HIPAA support through business associate agreements where appropriate and a legal opinion on EU AI Act classification. These are different assurances with different scopes. The open product explanation leaves out the current SOC audit period, the auditor and the full service scope. The named SOC standard therefore supports a specific certification claim without treating every resource or regulatory statement as an equivalent independent security audit.
Model Supply Chain Disclosure
Which models sit underneath, whose they are, where they run, and whether the vendor commits to telling customers when that changes. A legal buyer inherits every dependency it cannot see.
The engine is described as proprietary, and no model or provider is named for live use. The privacy policy lists artificial intelligence among the services that vendors help with, and the benchmark tested Claude for Word as a comparison rather than as a component. Where inference runs is not stated, and the subprocessor list sits in the trust center rather than on the site.
Language models come from OpenAI and Anthropic, under zero retention agreements that keep request and response content in memory for processing rather than persistent storage at those providers. AWS is the primary cloud provider, and storage and processing are described in Canada and the United States. The trust portal lists processors and records updates when suppliers change. Spellbook does not give the exact production model versions or a map of which model serves each feature. 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.
Every route in is a demo request, and no price is listed. The terms set the shape. Fees are fixed in a Services Agreement for an initial term with renewal terms, priced and invoiced in United States dollars, and nonrefundable apart from prorated refunds on certain terminations. Ivo can change fees or add charges at the end of a term with 30 days notice, and the privacy policy describes the business as subscriptions. Implementation takes about a week.
The number of team members on a license sets the price of the suite. 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.
The buyer is the in house legal department at large enterprises, and the named customers run across technology, semiconductors, payments, food service, industrials and retail distribution. Coverage is described by document type: the benchmark covers NDAs, MSAs, DPAs and other commercial agreements, and Review handles any document in Word, PDF or Google Docs. Research covers United States sources such as EDGAR, the United States Code, Congress.gov, eCFR and the Federal Register, and UK and EU material from Companies House, Parliament and the Court of Justice. No company size floor, excluded contract type or unsupported jurisdiction is stated, and law firms are not addressed.
Law firm and in house packages are sold separately, and the principal tools center on transactional drafting, review, negotiation and questions about agreements. Associate extends work across several files, 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, though breadth of sources is a different matter from tested competence in every practice. The terms warn about non English results, while Autonomous Contract Management remains in early access. Spellbook does not list the jurisdictions or specialized legal tasks it leaves unsupported.
The 12 legal signals, side by side
Recorded rather than graded. These are the questions a practitioner has to answer before a tool touches a client matter, and the answers are taken from public material only.
Client Data in Training
Can material a lawyer puts into this product be used to train a model?
Customer data never trains AI models, according to the home page. The terms carry no matching clause; they let Ivo use customer content to provide the service and use feedback freely. The privacy policy lets Ivo improve its services by analyzing feature use and submitted documentation, and use deidentified or aggregated information for any purpose. Intelligence uses customer agreements to build playbooks and answer repository questions.
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?
Information is kept as long as Ivo has a business or operational purpose, with no period and no customer setting. A contract or document tied to a thumbs down rating is kept for 14 days, then deleted or deidentified unless the law requires otherwise. On request after termination, customer content is deleted within 60 days, subject to ordinary backup and record retention exceptions in the terms.
Model providers handle request and response content in memory under zero retention agreements. Spellbook may keep quality assurance inputs and outputs for up to 90 days, and self service abuse monitoring data for up to 30 days, with investigation and legal exceptions. Those are specific secondary uses rather than a stated ordinary lifetime for all application history. Deletion and return provisions are a different mechanism from a configurable zero history setting.
Ethical Walls and Matter Segregation
Does retrieval respect the firm’s ethical walls, or can the model read across them?
Intelligence offers separate rooms for projects, acquisitions and business units to control access and the scope of analysis. Customers also assign user roles and permissions. The rooms provide a way to separate contract collections inside the service, but the permission inheritance, administrator setup and enforcement at retrieval time are not described. No automatic inheritance of a source document system's ethical walls is specified.
The iManage integration applies existing iManage permissions and ethical walls to file access inside Spellbook. A user authenticates the source account once, then selects permitted files for Ask in Word, Ask in Associate or an Associate Project. Selected material becomes context for answers and review. Spellbook describes this protection specifically for the iManage connection and does not extend the claim to permission inheritance on the other optional storage connections.
Third Party Request and Subpoena Notice
If someone subpoenas the vendor for a firm’s data, does the firm hear about it first?
The Legal Process clause of the terms lets Ivo respond to subpoenas, warrants, liens and other legal orders about an account, without responsibility for the customer's resulting losses. Where permitted, Ivo gives reasonable notice that it received the order. No transparency report is offered.
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. Spellbook does not publish a report counting government requests and their outcomes.
Primary Law Corpus Provenance
Where does the law in this product come from, and does the vendor have the right to use it?
Assistant answers from more than 100 legal sources. For the United States these include EDGAR and SEC filings, the United States Code, Congress.gov, eCFR and the Federal Register, and UK and EU questions draw on Companies House, Parliament and the Court of Justice. No license basis or update schedule is given. Most of the product's material is the customer's own executed contracts and playbooks, with Playbook Builder citing each position back to its source agreement.
The legal data connection names its sources, including CanLII, Cornell Law, CourtListener, EUR Lex, BAILII and national government registers. Spellbook retrieves material directly from each source of record and follows its update cadence. The same workflow can use the customer's own contracts and iManage precedents. The named source list makes jurisdiction coverage inspectable, but does not state an individual license or public domain basis for every external collection or its separate market benchmark data.
Good Law Verification
Does the product tell you when the authority it just cited has been overruled?
Assistant and Review retrieve case law and statutes with citations, described as verified, and Assistant reports on changes in the law. Whether a cited authority has later history or has been superseded is not flagged.
Citations to public case law, statutes and registers come back from the legal data feature, with currency tied to the operator of each source. Ask, Draft and Review can use that authority within the contract workflow. The feature does not describe a licensed citator or a method for checking subsequent judicial treatment of a case. A current link to the underlying decision is therefore separate from a signal that its legal proposition remains reliable.
Refusal and Uncertainty Behavior
What does the product do when the answer is not in the corpus?
Review gives one recommendation per topic with the reasoning and source behind it, and a user can rate an answer down after the fact. No behavior is described for a question the product cannot answer from its sources, and no confidence measure is shown.
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, which records court decisions worldwide that address hallucinated AI content and the tool involved where known, has no entry naming Ivo or Ivo AI, Inc. Its products review and manage contracts for in house legal teams.
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?
The terms require use under the direct supervision of a lawyer representing the customer. Their No Legal Advice clause says the service provides general legal information, forms no attorney client relationship and cannot replace professional advice. Ivo does not guarantee the accuracy, completeness or timeliness of legal material. A named bar opinion or jurisdiction specific ethics guidance does not accompany that contractual supervision requirement.
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?
Ivo is sold to in house legal teams at large enterprises, with Atlassian, Canva and CDW as its featured customers. Its time claims are aimed at those teams. The home page promises review, redlines and insights from contracts in minutes. In Ivo's benchmarking study the attorney took 10 hours for the redlining tasks, while Ivo averaged 2 minutes and 45 seconds a contract.
The law firm suite is pitched as a way to improve profitability and the in house suite as a way to retain more work internally. Customer stories describe time savings, including Panasonic's RFP process. The product's per user subscription is separate from a lawyer's charges to clients. A matter level invoice record of AI assisted time or instructions for disclosing those savings on a client's bill are not described in the current pricing offer.
Outside Counsel Guideline Readiness
Can a firm get this vendor through a client’s AI clause without a bespoke negotiation?
The subprocessor list and security documents sit in a Vanta trust center where copies of the SOC 2 Type II and ISO 27001 certifications are requested. The privacy policy confirms that AI providers are among Ivo's service providers without naming them, and no client facing disclosure material is offered. Requests pass through the portal's access process before the reports are supplied.
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?
Playbook Builder cites each drafted position back to the agreement it came from, Review gives the source behind each recommendation, and redlines land as tracked changes a person accepts. The model behind a passage is not recorded, and no export for a court filing is offered.
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 Ivo if
- You run an in house team at a large enterprise. Ivo's named customers include Atlassian, Canva and CDW, and its tools center on the company's own playbooks and executed contracts.
- You want clause positions drawn from deals you have already signed. Review benchmarks clauses against executed contracts by governing law, contract type, party role and industry, and Playbook Builder derives positions from them.
- Your team works in Google Docs as well as Word. Review and Assistant run as add ins in both, and Collaborate syncs each teammate's changes back to the same deal.
Choose Spellbook if
- You are a law firm on iManage. Spellbook brings selected iManage files into Word or Associate and applies the existing permissions and ethical walls.
- You want the model providers named. OpenAI and Anthropic process requests under zero retention agreements, with storage and processing in Canada and the United States on AWS.
- You want platform risks covered in the contract. Spellbook's terms carry an intellectual property indemnity and lift the liability cap for confidentiality, security and data incidents.
In summary
Ivo
Ivo is an AI contract review platform for in house legal teams at large enterprises, with Review, Intelligence, Assistant and Collaborate products. Review gives each topic its own agent and a supervising agent that reconciles their findings, then applies playbook backed redlines in Microsoft Word or Google Docs. According to the AI Legal Index, Ivo benchmarks each clause against the customer's own executed contracts, narrowed by governing law, contract type, party role and industry. Intelligence connects to stored contracts for extraction and plain English questions, and Assistant draws on more than 100 legal sources, including EDGAR, the United States Code and the Federal Register. Named customers include Atlassian, Canva and CDW, and the company holds SOC 2 Type II and ISO 27001.
Spellbook
Spellbook gives lawyers AI drafting, contract review and legal questions inside Microsoft Word, with an Associate agent for work across several files and projects. Review proposes tracked edits against the user's instructions and playbooks for the lawyer to approve, and Compare checks contract language against market patterns. The AI Legal Index finds that its iManage connection carries existing permissions and ethical walls into Word and Associate. Legal research draws on named open databases such as CanLII and CourtListener, and OpenAI and Anthropic supply the models under zero retention agreements. Spellbook, founded in 2018 in St John's, Newfoundland, prices its suite per team member and reports use by more than 5,000 legal teams.
Questions buyers ask
Ivo vs Spellbook: which is better for an in house legal team?
Ivo is built for in house teams at large enterprises, with playbooks drawn from executed contracts, repository analysis and an intake and approval workflow across Salesforce and Slack. Spellbook also sells an in house package, priced per team member with a playbook build service, and suits teams that want drafting, review and multi file work in Word with an iManage connection. From the AI Legal Index, based on each vendor's own published materials as of October 17, 2026. No vendor pays for placement.
Does Spellbook or Ivo train AI on our contracts?
Spellbook's terms bar its model providers from training on customer content, while letting Spellbook use deidentified material to personalize features for that same customer only. Ivo's website promises that customer data never trains AI models, though its terms carry no matching clause and let it use deidentified information for any purpose. From the AI Legal Index, based on each vendor's own published materials as of October 17, 2026. No vendor pays for placement.
Which one works with iManage?
Spellbook has a named iManage connection that brings selected files into Word or its Associate agent and keeps iManage permissions and ethical walls in force. Ivo connects to contracts wherever they are stored and offers separate rooms by project or business unit, with no named document management connector. From the AI Legal Index, based on each vendor's own published materials as of October 17, 2026. No vendor pays for placement.
How are Ivo and Spellbook priced?
Neither has a public price. Spellbook prices its suite by the number of team members, includes training and online support, adds dedicated support above ten people and offers a seven day trial. Ivo routes every buyer through a demo, sets fees in USD in a Services Agreement and puts implementation at about a week. From the AI Legal Index, based on each vendor's own published materials as of October 17, 2026. No vendor pays for placement.
What gaps do Ivo and Spellbook share?
Neither product has a stated fallback for when it cannot answer from its sources, and neither shows a confidence measure. Neither flags whether a cited case has later history. Neither ties its controls to a named ethics opinion such as ABA Formal Opinion 512. As the AI Legal Index reads both, each leaves checking the output to the lawyer who accepts it.
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.
Ivo's $100 liability cap and customer indemnity sit in its standard terms of 20 November 2024. Enterprise customers sign a separate Services Agreement, so a large buyer's real position may differ. Ivo ran its benchmark of 19 contracts itself. Spellbook may use deidentified customer material to personalize features for that same customer and keep quality assurance copies for up to 90 days. Ivo is based in San Francisco and Spellbook in St John's, Newfoundland. Neither vendor reviewed this page.