Filevine vs Litify: how they compare in 2026
Filevine and Litify are the two case management platforms a plaintiff firm puts on the same shortlist, and what separates them is documents rather than features. Filevine publishes a subscription agreement, a data processing agreement updated 14 January 2026, a security addendum and an AI acceptable use policy. Those documents carry an infringement indemnity and a liability cap set at the greater of twelve months of fees or $200,000. They also carry an insurance commitment to carriers with an A.M. Best rating of A minus VI or better, an annual independent audit with a route to the report, and a destruction regime with a thirty day certification. Litify publishes no customer agreement, so none of those questions has a published answer. Litify carries what Filevine does not: a customer study with a stated baseline, a model named as the Claude 3 family reached through Amazon Bedrock, and a starting rate of $200 per user per month on its Salesforce listing.
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.
Filevine names more than a dozen AI products and sells them on top of a complete practice management system. They include MedChron for medical chronologies, DemandsAI for demand letters, Depo CoPilot, Depo Summaries, AIFields, AI Doc Review, AI Data Mapping, ValidationAI, ImmigrationAI, Leads AI, Ask LOIS, LOIS for Word and the LOIS Console. The medical chronology and the demand letter are core work in a personal injury practice, and the AI drives both. Underneath sits the platform Filevine sold before the AI: matters, documents, intake, billing, electronic signature, analytics and deadlines. Without the models, a firm keeps running on that platform. The AI is sold as packages and extensions on top of it, with its own free tier.
Litify's home page calls it the only AI native platform of action, while the Taylor King Law case study describes a 2021 deployment whose measured gains came from the analytics engine, phone tree routing and matter plans, with no AI in the account at all. Litify ACE is positioned as the AI nerve center, eight further named agents run from intake qualification through deposition preparation, and machine learning is embedded in document generation, time capture and line item invoice review. Without the models, a working intake, matter, billing and reporting platform remains, the shape of a legacy system that added an AI layer rather than one built around it.
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 claimed across products and accuracy is not measured. Ask LOIS returns grounded, traceable answers, LOIS for Word gives source linked recommendations, Depo Summaries carry page and line references, and the free LOIS Explore tier cites every result to source. A legal research opinion reader lets a user open the authority. The agreement names the failure modes: output may be incomplete, contain factual or legal errors, reflect bias, or differ for similar inputs. What is missing is any number. No accuracy figure, test set, evaluation or error rate is published, though AIFields marketing invites buyers to stop struggling with hallucinations. MedChron's output points to sources only when applicable.
The Litify AI page says being fully native to the platform ensures greater accuracy than standalone AI tools, and the Damages Assistant is described as reconciling bills against records for total accuracy. No test set, benchmark, error rate or failure mode is published. The product does not retrieve primary law, so checking citations against authority does not arise. It does draft demand letters and interrogatory responses from a firm's own medical records and matter data, and no grounding mechanism is described for that output; nothing published lets a reader trace a drafted assertion to the source page it came from.
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 review duty is in the contract, and it names the act required. Section 3.2 of the subscription agreement makes the customer responsible for reviewing and verifying output, and for confirming citations and legal conclusions before relying on it or sharing it with a client or a court. An AI Acceptable Use Policy is part of the agreement, AI drafting is described as human verified, and outputs link back to the underlying material. The agreement also warns that similar inputs may produce different output. What is missing: no abstention behavior, no confidence indicator, no threshold at which a feature declines, and no route to report a wrong output.
ACE is described as a proactive, autonomous partner that anticipates risk and executes tasks in the background, and the platform page describes autonomous AI agents that do the same. The Demand Agent drafts demand letters automatically as damages approach policy limits, and the Discovery Agent drafts interrogatory responses automatically. The only oversight position published is in the Pillars of Responsible AI Development post of 9 July 2024, which says AI is not a replacement for legal professionals and is not well positioned to engage in the art of case strategy. The product, platform and AI pages show no review point, approval step or threshold at which an agent stops, and nothing on what happens when an agent 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.
Volume claims, not customer outcomes, are what Filevine puts forward. It says customers draft about 100,000 demand letters a month, and claims the largest and most accurate personal injury case management data repository in the world. One case study headline names a shareholder who brought 125 active cases under control, without naming the firm. The agreement lets Filevine use a customer's name and logo, with a right to withdraw. No measured outcome for a named organization is published. Filevine has a customers and case studies library.
The Taylor King Law study names the firm, its size at more than 75 employees, its states and its COO, Emily Merryman, and a 2021 launch that migrated from Needles. It gives a baseline: intake conversion rose from 30 percent to 50 percent, and average attorney fees rose 46 percent. The method is described step by step. The firm identified its highest performing intake agents from captured workflow data, routed calls on existing cases away from them through a phone tree, replaced uniform follow up with conditional timing logic, and added an automated quality of life questionnaire to surface noneconomic damages. Other named studies carry their own figures: EllisDon at 100 percent faster reporting, McFarlane Law at a 10 percent lift in billing collection, and Cesar Ornelas at 33 percent more case production without added headcount. No study carries a publication date or measurement window, and none of the figures is attributed to an AI capability, so the evidence is for the platform rather than for Litify AI.
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.
Confidentiality and training are both covered by commitments in Filevine's agreement. Third party AI providers are barred in writing from training on customer data and from keeping it beyond the request, except briefly for abuse monitoring. The customer owns its data, including output, and customer data is confidential information for seven years, with trade secrets protected indefinitely. Filevine cannot reduce its confidentiality or security commitments mid term without consent. Another customer's queries and output are not the customer's data, which separates tenants. What is missing is separation inside a firm: nothing describes a wall between two matters, which is live for a plaintiff firm with adverse cases.
The Litify AI page says customer data is never retained or used to train the model. The Pillars post of 9 July 2024 describes single tenant architecture giving each client a walled off cloud environment. The security post says customer data sits in Salesforce data centers where Litify is not an authorized administrator, and support access requires the customer to run a Grant Litify Support Team Access process. It also says third parties, including Litify employees, investors, shareholders and board members, may not access customer information. No customer agreement is published, so none of these commitments is contractual. Separation is described between customers, not between matters inside a firm. Nothing addresses what Anthropic or AWS may keep when a prompt reaches Bedrock. Privilege and work product are not mentioned, and the only published legal document, the privacy policy, expressly excludes data held for customers.
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 advice line is drawn clearly in the agreement. Filevine is not a law firm and does not give legal advice, and using output creates no attorney client relationship. The customer must confirm citations and legal conclusions before relying on output or sharing it with a client or a court, which names the duty and the audience. An AI Acceptable Use Policy governs permitted uses. What is missing: no bar or ethics authority is named, including ABA Formal Opinion 512, and no jurisdiction limit is stated for a platform used in immigration, criminal defense and prosecution work across every state.
No disclaimer, statement of what the product is and is not, supervision or competence discussion, jurisdiction limit, or engagement with ABA Formal Opinion 512 or any state bar guidance is published on Litify's home page, Litify AI page, platform page, privacy policy, CA notice, responsible AI post, security post, customers section or Salesforce AppExchange listing. There is no terms of service on the property to carry a disclaimer. The shipped agents draft demand letters and interrogatory responses, and the platform is sold to firms whose staff include case managers and intake agents who are not lawyers.
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.
Fairness, reliability and safety, privacy and security, inclusiveness, transparency and accountability make up Filevine's six AI principles. The fairness principle commits to fighting bias in its legal AI tools. The agreement repeats the point where it binds, stating that output may reflect biases in training data. Governance has some structure: an AI Acceptable Use Policy is part of the agreement, Filevine keeps a list of permitted models, and it cannot reduce its confidentiality or security commitments mid term without consent. A Head Legal Futurist and a Legal Futurist are named roles. What is missing is testing: no evaluation before release, no published result, and no bias audit or fairness measure.
A governance post, Our Pillars of Responsible AI Development, dated 9 July 2024, is signed by VP of Engineering Andrew Heffernan. Most of its substance concerns the supply chain and deployment: the Claude 3 selection, Amazon Bedrock and single tenant storage, plus a value first pillar about not replacing lawyering. No accountable owner for AI governance is named, no testing before release is described, no evaluation results are disclosed, and nothing is published on bias or uneven output across matter types, claimant populations or case values, though the Case Value Agent and Policy Agent make value judgments about individual injury claims.
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 Data Protection Agreement (updated 14 Jan 2026) covers retention, return, access, subprocessors and breaches. Personal information is kept for the life of the service, then destroyed or returned on the customer's written direction. If law forces Filevine to keep something, it must tell the customer what, why and when it will be destroyed, and certify destruction within thirty days. Access is limited to staff who need it, with training and background checks where lawful. Subprocessors sign terms at least as protective, the list sits in Annex C, customers can subscribe to change notices and object within ten business days, and Filevine is liable for its subprocessors. Breaches are notified promptly, with the data affected, the number of people, the steps taken and a named contact, and Filevine bears reasonable costs. What is missing is a fixed notice deadline in hours.
Customer data sits in Salesforce data centers where Litify is not an authorized administrator, according to the security post of 30 June 2022, and documents are held on AWS behind a strict internal approval process, the support team must be granted access through a named process the customer runs, and employees, investors, shareholders and board members may not access customer information. No retention period, deletion route, subprocessor list or incident or breach notification practice is published. The privacy policy states in its opening that it does not apply to personal information held on behalf of users of the services, which removes matter data from its scope entirely. The access control material is four years old and has no current counterpart.
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.
Filevine publishes a full liability position on four fronts. It defends and indemnifies against third party claims that the service infringes a US patent or copyright or misappropriates a trade secret, with remedies of a license, a fix, or termination and refund. Total liability is capped at the greater of twelve months of fees or two hundred thousand dollars, so smaller customers get a floor. The cap reaches claims from a security breach of customer data, gross negligence and intentional misconduct sit outside it where law requires, and the infringement indemnity is uncapped. Filevine commits to insurance from carriers rated A minus, VI or better by A.M. Best. It also warrants that the service conforms to its documentation and complies with law, with 99.0 percent uptime and service credits. What is not covered: output carries no warranty and is excluded from the indemnity.
No customer agreement of any kind is published. The footer of every Litify page carries only a Privacy Policy and a CA Notice at Collection, and the Salesforce AppExchange listing carries Salesforce's own Terms of Use rather than Litify's. No master subscription agreement, order form, indemnity, liability cap, warranty on output or insurance position is published, and there is no trust portal or documents page from which to request one. Who bears the loss when an agent drafts a wrong demand is not published.
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.
Named integrations connect the platform to other tools. LOIS for Word puts drafting and redlining inside Microsoft Word with source linked recommendations. Microsoft 365 integration is reported, DataBridge gives real time access to Filevine data, Vinesign has a public API, and native and partner integrations are sold as an extension. The agreement grants API access. Deposition scheduling books court reporters and creates Zoom links. What is missing is depth: nothing says what moves, in which direction or with what setup, and nothing is published for iManage, NetDocuments or ebilling. Filevine has an integrations and API page.
Roughly thirty integration logos appear on the platform page, among them iManage, NetDocuments, Outlook, DocuSign, Aderant, Epiq, QuickBooks, Chrometa, Time by Ping, RingCentral, Vonage and Case Status. The See All Integrations link on that page leads to no page, and no integrations directory, developer index or connector documentation is published elsewhere. The page shows that a NetDocuments or iManage connection exists, but not what it moves, in which direction, or what a firm must configure. As a Salesforce managed package, Litify gains broad API reach, but that is the platform's extensibility rather than a documented Litify integration.
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.
Amazon Web Services hosts the platform in the cloud, named on Filevine's case management page and pricing FAQ, with separate US and Canadian login domains. The Data Protection Agreement names Filevine, Inc. in Salt Lake City, Utah as the data importer and names a Data Protection Officer. Transfers from Europe, the UK and Switzerland run on Standard Contractual Clauses and the UK addendum, with supervisory authorities listed. Government access requests are notified to the customer only. What is missing is a residency choice: no region list, no selectable location, no tenancy model, and no statement of where AI inference runs, which matters because third party AI providers process customer data.
Single tenant architecture gives each client its own cloud environment walled off from other organizations, extended to single tenant storage for the AI features, according to the Pillars post of 9 July 2024. The product is delivered as a Salesforce managed package that requires a Salesforce platform license. No region list, residency option, distinction between where data is stored and where it is processed, or statement of which Salesforce or AWS regions hold a firm's matter data is published. The privacy policy says servers are in the United States, but it covers only the marketing site and expressly excludes data held for customers. The tenancy claim rests on a blog post from July 2024 with no current specification page behind it.
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.
Filevine claims SOC 2 Type II, SOC 3, HIPAA, CJIS, HITECH and GDPR on a structured security page. Its Data Protection Agreement adds the route behind the claims. An independent third party audits data processing and security controls at least once a year. Audit reports are available on the customer's written request, under confidentiality, and issues are handled through a corrective action plan. If no audit happened in the past year, or Filevine declines to share reports, the customer gets a direct audit right on 21 days' notice. Filevine also answers a security questionnaire once a year within six weeks. What is missing: no auditor, report date or coverage period is published, and the certifications carry no scope.
Litify names its auditor. The security post states that Litify has completed SOC 2 Type I and Type II audits, both performed by Sensiba, and undergoes annual independent security audits. No scope, trust services categories, coverage period or report date is published, there is no trust portal, and no way to request the report short of a demo is offered. The post is dated 30 June 2022 and no current attestation is published, so whether the annual audits continued is not stated. Separately, the Litify AI page claims the product is fully configurable to meet HIPAA, GDPR and SOC II standards, a statement about configuration rather than an attestation.
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 agreement confirms third party models are used and does not say whose. Section 3.1 says AI features use models from third party AI providers, and section 4.3 commits Filevine to keep a list of permitted models. No model, provider or version is published. The AI principles page calls Filevine's AI proprietary, and nothing reconciles that with the agreement. The providers are bound not to train on customer data or keep it beyond a request, except briefly for abuse monitoring. Material changes need thirty days' notice, though nothing is specific to models. Filevine links a Subprocessors page.
Litify names its model provider on its home page, which describes the platform as built on the infrastructure of Salesforce, AWS and Anthropic, identified as its closed AI model. The Pillars post of 9 July 2024 names the model family, Claude 3 from Anthropic, reached through Amazon Bedrock and run inside closed AWS services, so client data is not exposed to the wider internet or to open models. No commitment to notify customers when the model or provider changes is published. The version named is two generations old, and the current AI page names Anthropic but no model. The supply chain reaches further than the model pages: Supio powers the Damages Assistant and Instant Demands, Billables.ai powers AI Time Capture and Salesforce Agentforce handles conflict checking, and no subprocessor list ties those parties to the customer data they see.
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.
The full shape of the pricing is public, with no figure attached. Filevine's pricing page lists the LOIS AI tier with seven components, four platform packages (Matters, Intake, Depositions and Signatures) with their features, and five Matters extensions. A free tier, LOIS Explore, needs no credit card and covers document questions, AI drafting, legal research and the opinion reader, but does not connect to case management. The agreement adds billing terms: interest at up to 1.5 percent a month after ten days overdue, suspension at ten days, a ten day window to dispute a charge, retroactive overage billing from usage telemetry, and no refunds outside warranty or breach. Implementation, configuration and data migration are done by separate certified partners for their own fees. What is missing is any number, at any tier. Every route to a price is a demo or a custom quote.
There is no pricing page on litify.com and no pricing entry in its navigation, but Litify's own Salesforce AppExchange storefront publishes a figure and a unit: a default plan at $200 USD per user per month, marked as the lowest starting price, with discounts noted for nonprofits. The listing also states that the package requires Platform Cloud, so a Salesforce license sits on top of the Litify subscription, though the size of that addition is not given. No tier names, feature splits between packages, price for the AI capabilities, or implementation cost is published, and implementation is substantial for a deployment native to Salesforce. The floor and the unit of charge are published; nothing above the floor is.
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.
Coverage runs across seventeen segment pages. By practice: personal injury, family law, mass torts, immigration, insurance defense, criminal defense and estate planning. By government tier: prosecutors, public defenders, states and municipalities, attorneys general and federal agencies, backed by agreement clauses on sovereign immunity and FAR and DFARS designations. By corporate use: in house counsel. By size: solo, small, mid size and big law. ImmigrationAI handles documents in 170 languages, and Timely generates court deadlines for any jurisdiction in the country. What is missing is any limit: no unsupported practice, matter type, jurisdiction or scale is named, and the deadline claim has no coverage table.
Four solution lines each have their own page and named buyer: personal injury firms handling high volume intake, firms doing high volume defense work for insurance carriers, consumer and business immigration practices, and corporate legal departments managing internal matters and outside counsel. The AppExchange listing adds government agencies and nonprofits, and the customer list bears out the range, from Brooklyn Defenders to the United States Postal Service. The claim of more than fifteen practice areas is not itemized. Nothing says where the product stops: no firm size limits, no unsupported practice areas, and no jurisdictions outside the United States. The platform framing and the Salesforce license requirement both point away from very small firms.
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 subscription agreement (updated 12 August 2026) bars Filevine's third party AI providers, in writing, from using customer data to train or improve their models, and from keeping it beyond the request except briefly for abuse monitoring or trust and safety. Filevine keeps a list of permitted models consistent with that. A separate clause lets Filevine use customer data in deidentified, aggregated form to improve its services and other technologies, with a commitment not to attempt reidentification, so the two clauses sit side by side.
The Litify AI page states the position twice, in a Zero Model Training panel and again in the FAQ, where it says the closed and secure model ensures customer data is never used to train the model. The Pillars of Responsible AI Development post of 9 July 2024 says the same of the single tenant AI architecture. No customer agreement, master subscription agreement or data processing addendum is published anywhere on the property, so the commitment is a policy statement on a product page rather than a term a firm could hold Litify to.
Prompt and Output Retention
How long does the product keep what a lawyer typed, and can that be set to zero?
Filevine's Data Protection Agreement (updated 14 Jan 2026) sets retention for the life of the service. On termination it destroys personal information or returns it on the customer's written direction. If law forces it to keep something, it must say what, on what basis, and when it will be destroyed, and it certifies destruction in writing within thirty days. These terms cover personal information, not prompts and AI output as a class, and nothing says whether AI conversation threads are kept separately or for how long. The subscription agreement sends retention questions to the Security Addendum.
What Litify publishes covers the model, not the platform: the quoted line and the Zero Model Training panel both address whether the AI model persists customer data, and say it does not. Nothing published states how long prompts and generated outputs are kept inside the Litify application itself, whether a firm can configure that window, or whether zero retention is available. The privacy policy states a general standard of keeping data as long as necessary but scopes itself out of data held on behalf of customers.
Ethical Walls and Matter Segregation
Does retrieval respect the firm’s ethical walls, or can the model read across them?
Nothing published describes a wall between matters: no matter level permission model, and nothing saying a user can be restricted to certain cases or that AI features respect such a limit. One clause separates customers: another customer's queries and output are not the customer's data. Users must hold unique credentials. The question is live here, since Filevine targets plaintiff firms with adverse matters and both public defender and prosecutor offices, and nothing says whether one matter's material can surface in another's AI output.
The segregation Litify describes is between customers rather than within a firm: the responsible AI post of 9 July 2024 says each client has a unique cloud environment walled off from other organizations. Nothing on the home page, the Litify AI page, the platform page, the security post, the responsible AI post or the privacy policy addresses ethical walls, matter level access restriction, or whether retrieval enforces a firm's own permissions at query time, although the ACE agent is described as working natively across all of a firm's cases and documents and the conflict checker searches an entire case history.
Third Party Request and Subpoena Notice
If someone subpoenas the vendor for a firm’s data, does the firm hear about it first?
Two documents address this. The subscription agreement allows disclosure of confidential information under law, court order or government order, with advance notice to the customer where legally permitted. The Data Protection Agreement goes further for personal information: Filevine will first tell the customer of the legal requirement and give it a chance to object or challenge, unless the law forbids notice, and will disclose only the minimum needed.
On a government access request it notifies the customer, not the data subject. Two limits: the chance to object is qualified where it would prejudice Filevine or expose it to liability, and the DPA covers personal information rather than every document in a matter. No transparency report is published, and nothing commits Filevine to seek a protective order itself.
Litify's privacy policy of 3 June 2026 says Litify may disclose personal information to law enforcement and government authorities and in response to valid requests by public authorities. It makes no commitment to notify the affected party, and there is no transparency report. The policy states at the outset that it does not apply to personal information held for users of the services, which puts a firm's matter data outside its scope, and no customer agreement exists to cover the question instead.
Primary Law Corpus Provenance
Where does the law in this product come from, and does the vendor have the right to use it?
The question arises here and nothing answers it. Most of Filevine's AI reads the customer's own case file, but the free LOIS Explore tier offers legal research and an opinion reader, so the platform retrieves primary law from some corpus. Nothing names the source, supplier, jurisdictions, license or update cadence.
The product does not retrieve primary law. Litify AI works on a firm's own matter data, medical records and documents, so there is no case law or statutory corpus behind its output and no licensing question of that kind. The Litify AI and platform pages refer to no primary law source.
Good Law Verification
Does the product tell you when the authority it just cited has been overruled?
Filevine offers legal research and an opinion reader in LOIS Explore, and its drafting tools cite results to source. No citator, treatment signal or check that cited authority is still good law is described. The agreement puts that burden on the user, who must confirm citations and legal conclusions before relying on output. Filevine also runs a webinar on checking cites and reading the opinion.
No citator function exists, and none would apply in the ordinary way, because the product does not return authority to be checked for later history. The nearest adjacent behavior is drafting: the Demand Agent produces demand letters and the Discovery Agent drafts interrogatory responses, neither of which is described as citing or verifying case law.
Refusal and Uncertainty Behavior
What does the product do when the answer is not in the corpus?
Filevine's agreement states the limits frankly: output may be incomplete, contain factual or legal errors, reflect bias in training data, or differ for similar inputs. It does not describe what the system does when it is unsure: no abstention path, confidence indicator, threshold for declining, or behavior when the case file does not support a question is described.
No published material describes what any Litify agent does when it cannot support an answer from the matter file. No way to abstain, confidence or grounding score, or behavior on missing data is described, although the Record Retrieval Agent is described as identifying missing medical records, which is gap detection in the case file rather than uncertainty about its own output.
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 held about 1,994 decisions at the time, and several independent 2026 sanctions trackers and practitioner guides record no court order, opinion or disciplinary record naming Filevine or its products. The exposure is direct, because Filevine drafts demand letters and motions and offers legal research, and the agreement requires users to confirm citations before sharing output with a client or court.
The AI Hallucination Cases database maintained by Damien Charlotin at HEC Paris, along with 2026 sanctions trackers and trade coverage, records no court order, opinion or disciplinary record naming Litify; the product name and the company name are the same word. This is a statement about the public record rather than a finding about the product. The shipped agents draft demand letters and interrogatory responses.
Bar Guidance Alignment
Has the vendor engaged in public with the ethics opinions its buyers are bound by?
No authority is cited: nothing names ABA Formal Opinion 512, state bar guidance on generative AI, or a court standing order. The agreement does state the substance: Filevine is not a law firm, output creates no attorney client relationship, and the customer must confirm citations and legal conclusions before sharing output with a client or court. Filevine also publishes an AI Acceptable Use Policy and a webinar and blog series on AI risk.
No engagement with ABA Formal Opinion 512 or with any state bar opinion on generative AI is published on Litify's home page, Litify AI page, responsible AI post, resources index or privacy policy. Litify publishes material on AI for buyers, including a Legal AI Buyer's Guide and a 2025 State of AI in Legal report, and a responsible AI post that names NIST, the Global Partnership on AI and the Partnership on AI as bodies its model providers engage with, none of which is ethics guidance binding its customers.
Billing and Fee Posture
Does the vendor address what happens to the bill when the work takes an hour instead of six?
Savings come with numbers attached. AIFields is said to cut costs by over 75 percent, demand letters take 15 minutes or less, DemandsAI is sold on per case fees with no charges for complexity or edits, and the AI page says firms can pass savings on to clients. No record of AI assisted work per matter for fee purposes, and no guidance on billing or client disclosure, is published. Billing and time keeping are core modules, so the means to record it exist. The gap is sharpest on the demand letter, which in a contingency practice is priced into the recovery.
Litify markets efficiency and realization gains without addressing the client's side of the invoice. Litify's home page says configurable workflows and autonomous agents let a firm handle twice as many matters with the same staff, and the platform page describes AI Time Capture as recommending time entries so that work such as quick emails is never left off the bill. Nothing published addresses how AI assisted work should be billed or disclosed to a client, and no record of what the AI itself did on each matter is described, though AI Time Capture is said to generate entries ready for review.
Outside Counsel Guideline Readiness
Can a firm get this vendor through a client’s AI clause without a bespoke negotiation?
What outside counsel guidelines ask is answered in Filevine's Data Protection Agreement. Subprocessors sign terms at least as protective, and the list is published at a URL reached from Annex C. Customers can subscribe to notices, object within ten business days, and terminate the affected service with a refund if Filevine cannot work around an objection. An independent party audits Filevine every year, reports are available on request, and a direct audit right applies if that fails.
Filevine answers a security questionnaire yearly within six weeks. Transfers run on Standard Contractual Clauses and the UK addendum, and a Data Protection Officer is named. A Security Addendum and an AI Acceptable Use Policy are also published.
Litify names providers on current pages: its home page names Salesforce, AWS and Anthropic, the responsible AI post names the Claude 3 family reached through Amazon Bedrock, and the Litify AI page names Supio, Billables.ai and Salesforce Agentforce as the parties behind specific features. That is a model provider disclosure rather than a subprocessor list. No formal subprocessor register, data processing addendum or consent or notification pack for clients is published, and there is no trust portal from which to request one.
Court Disclosure Support
If a judge’s standing order requires an AI disclosure, can the product produce one?
The agreement expects output may reach a court, requiring the customer to confirm citations and legal conclusions before sharing output with a judicial body. Product support is partial: drafts cite sources, LOIS for Word links recommendations to sources, deposition summaries carry page and line references, and the opinion reader opens the authority. The record is missing: no model identification or versioning, no log of AI use or of what a user accepted, and no export or template for a court's standing order on AI is described.
Nothing on Litify's AI page, platform page or responsible AI post addresses producing a disclosure of AI use or a verification certification for a court. No export of which model produced which passage, what was retrieved, or who reviewed it is described for any of the nine named agents. The conflict checker is said to create a permanent report, but that is a conflicts artifact rather than an AI disclosure record.
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
- Primary Law Corpus Provenance
- Good Law Verification
- Refusal and Uncertainty Behavior
- Bar Guidance Alignment
Which one fits
Choose Filevine if
- You want to know who bears the loss before you sign. Filevine's agreement carries an infringement indemnity, a cap set at the greater of the fees paid in the prior twelve months or $200,000, carve outs reaching security breach and confidentiality claims, and a commitment to maintain insurance with carriers holding an A.M. Best rating of A minus VI or better.
- Your clients send outside counsel guidelines with AI clauses attached. Filevine's data processing agreement engages subprocessors under written agreements, gives email notice of new ones with a ten business day objection window, commits to an annual independent audit with reports available on written request, and answers a written security questionnaire once a year.
- You need the review duty written down rather than assumed. Section 3.2 makes the subscriber responsible for independently confirming citations and legal conclusions before relying on output or sharing it with any third party including a client or a judicial body, which is the only clause on either side that names a court as the audience.
Choose Litify if
- You want a deployment figure with a baseline attached. The Taylor King Law study names the firm, its chief operating officer and a 2021 go live, and reports intake conversion moving from 30 percent to 50 percent with a 46 percent rise in average attorney fees, although none of the figures is attributed to an AI capability.
- You have to tell a client whose model sees their file. Litify names Salesforce, AWS and Anthropic on its home page and identifies the Claude 3 family reached through Amazon Bedrock inside closed AWS services, while Filevine names no model or provider.
- You want a number before a sales call and an answer on tenancy. Litify's Salesforce AppExchange listing publishes $200 per user per month as its lowest starting price and states that a Salesforce Platform license is required alongside it, and the architecture is described as single tenant with a walled off environment for each client.
In summary
Filevine
Filevine is a case management platform for contingency and volume practices, running the matter lifecycle from lead capture through settlement. Its AI layer, LOIS, covers medical chronologies, demand drafting, deposition assistance and drafting inside Microsoft Word. According to the AI Legal Index, Filevine's case rests on its contracts. A data processing agreement updated 14 January 2026 sets retention, destruction with written certification within thirty days, subprocessor objection rights and an annual independent audit. Its subscription agreement carries an infringement indemnity and caps liability at the greater of twelve months of fees or $200,000. It publishes no accuracy figure, no model provider name and no price figure.
Litify
Litify is a legal operating platform built natively on Salesforce, covering intake, matter management, document generation, timekeeping, billing and legal spend for plaintiff, insurance defense, immigration and in house teams. According to the AI Legal Index, its case rests on a measured deployment. The Taylor King Law study names the firm and its chief operating officer, gives a 2021 go live and reports intake conversion moving from 30 percent to 50 percent against a stated baseline, alongside a 46 percent rise in average attorney fees. Litify names Anthropic's Claude 3 family, reached through Amazon Bedrock, as the model behind its agents. It publishes no customer agreement of any kind, so no indemnity, cap, warranty or insurance position is published.
Questions buyers ask
Filevine vs Litify: which is better for a plaintiff firm?
The difference between them is documentary rather than functional. Filevine publishes a subscription agreement, a data processing agreement, a security addendum and an AI acceptable use policy. Litify publishes no customer agreement at all. Litify answers back on evidence and specifics, with a customer study carrying a baseline, a named model provider and a published starting price. From the AI Legal Index, based on each vendor's own published materials as of September 2, 2026. No vendor pays for placement.
Does Filevine train its AI on client data?
Filevine's subscription agreement, last updated 12 August 2026, states that it engages third party AI providers under written agreements prohibiting them from using subscriber data to train or improve their models, with temporary retention permitted only for abuse monitoring or trust and safety purposes. A separate clause permits Filevine to use subscriber data in de identified, aggregated form to improve its services, with a commitment not to attempt re identification. So the providers are contractually barred from training on subscriber data, and Filevine's own use is limited to de identified, aggregated data. From the AI Legal Index, based on each vendor's own published materials as of September 2, 2026. No vendor pays for placement.
What does Litify publish about liability if the AI drafts something wrong?
Nothing. Litify publishes no master subscription agreement, order form, indemnity, liability cap, warranty on output or insurance position, and no trust portal from which to request one. The footer carries a privacy policy and a California notice only, and the Salesforce AppExchange listing carries Salesforce's own terms rather than the provider's. A buyer reaches these terms inside a sales process. From the AI Legal Index, based on each vendor's own published materials as of September 2, 2026. No vendor pays for placement.
Which one names the AI models behind the product?
Litify. Its home page names Salesforce, AWS and Anthropic, and its responsible AI post of 9 July 2024 names the Claude 3 family reached through Amazon Bedrock and run inside closed AWS services. Filevine's agreement confirms that AI features use models provided by third party AI providers and commits to maintaining a list of permitted models, but names no provider, model or version. Litify's version naming is two model generations old. From the AI Legal Index, based on each vendor's own published materials as of September 2, 2026. No vendor pays for placement.
What do Filevine and Litify both leave unpublished?
Neither publishes an accuracy measurement: no test set, no benchmark and no error rate. Neither describes what its AI does when the case file does not support the question asked. Neither names a bar or ethics authority, including ABA Formal Opinion 512. And neither addresses matter level segregation, so neither says whether one matter's material can surface in another matter's output inside the same firm. From the AI Legal Index, based on each vendor's own published materials as of September 2, 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.
Filevine's security addendum, AI acceptable use policy and subprocessor list are named in its agreements, and this page does not draw on their contents. Litify's silence on liability and professional responsibility reflects that no customer agreement is published at all. That is an absence of documents, not a finding that its terms are unfavorable. Its security and architecture statements sit in posts dated June 2022 and July 2024, with no current counterpart. Neither vendor reviewed this page.