Law Ruler vs Lead Docket: how they compare in 2026
Law Ruler, part of ProfitSolv, and Lead Docket, part of Filevine, both manage intake for law firms that advertise at volume, from first contact to signed retainer. The difference is what each does with AI. Law Ruler's AI drafts emails and intake forms through the OpenAI API, and Law Ruler states that OpenAI keeps that data thirty days and does not train on it. Lead Docket's LeadsAI scores every lead for viability as it opens. Law Ruler also publishes a usage rate card in its customer agreement. Lead Docket's counterweight is its agreement's data terms and its link into Filevine. Its agreement sets deletion thirty days after termination with written certification, and signed leads move into Filevine matters without rekeying.
Which one fits
Choose Law Ruler if
- You need to tell a client exactly which AI touches its intake data. Law Ruler names the OpenAI API and ChatGPT as its AI, states that uploaded documents pass through that API, that OpenAI does not train on API submissions and keeps API data thirty days, and lets an administrator switch the feature off.
- You want to know what calls, texts and signatures will cost. Law Ruler's customer agreement publishes usage rates in full, including 5 cents a minute for local calls, 5 cents a text, $1 per electronic signature and $10 a month per extra gigabyte, and the AI is included on every paid tier.
- You run a high volume personal injury, mass tort or disability practice. Law Ruler publishes dedicated pages for eight practice areas, a softphone that matches the local area code on outbound calls, two way texting, and intake forms that qualify or disqualify an inquiry as it is completed.
Choose Lead Docket if
- You want the AI to tell your team which leads to work first. Lead Docket's LeadsAI reads intake documents, summarizes lead details, messages and notes, and shows a viability assessment on every lead the moment it opens, so the queue is not worked only in arrival order.
- You run Filevine or plan to. Lead Docket is a Filevine product under the same subscription agreement, and signed leads transfer natively into Filevine matters to create one client record without double entry, with retainers and payments collected in Lead Docket first.
- You want deletion terms you can enforce. Lead Docket's agreement lets a firm choose within twenty days of termination whether its files are destroyed or returned, offers written certification of deletion, limits Filevine's own access to providing the service and support, and commits to 99.5 percent monthly availability.
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.
The models are a feature layer on a product whose value stands entirely without them. A firm buys the CRM, the pipeline, the softphone with local presence dialing, the drip campaigns and the marketing source reporting; the AI is an OpenAI API integration that drafts emails, replies and intake questionnaires. Three published facts place it. The AI is included at no separate charge on every paid tier, so nobody pays for inference. An administrator can switch it off entirely in global settings, and the product still does everything it is sold for. And it is limited to eighty messages per hour per user, the shape of an add on rather than a mechanism. The capability is real, shipped and usable today.
The models drive the prioritization feature and sit on an intake CRM that works without them. The AI functions are described in present tense and are specific: LeadsAI reads intake documents, generates automatic summaries of lead details, messages and notes, and surfaces a Lead Viability assessment on every lead the moment it opens. The product is now marketed as Lead Docket with LeadsAI, and the home page leads with the reading and scoring rather than the pipeline. Underneath sits a lead management system that predates the AI and still delivers most of what buyers describe. It covers capture from web forms and calls, automated follow up emails and tasks, referral tracking with accept and reject templates and scheduled chasing, marketing source and ROI reporting, payment collection and native transfer into Filevine. Remove the models and a firm still has a working intake CRM.
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.
Nothing published on accuracy or grounding, on a product whose own published prompt library invites legal analysis. The AI page carries no accuracy figure, no test set, no evaluation, no method, no description of how an output relates to any source, and no statement about hallucination in either direction. That matters more than it would on a pure marketing tool because the vendor's own sample prompts include asking for the key provisions of a named law or regulation, the potential risks and liabilities of a legal issue, and guidance on handling a legal situation. One phrase touches accuracy: uploaded PDF, Word and JPEG files are said to inform requests and generate more accurate responses. That describes why to attach a file, not a position on accuracy.
Nothing is published on the accuracy or the grounding of the assessments this product makes. Lead Viability decides which prospective clients a firm pursues, and the marketing states that the AI knows the next best lead and that a team can see which cases are worth taking. No accuracy figure, evaluation, test set, error rate or statement of failure modes accompanies any of it. The grounding is not described either. Nothing says what the score is derived from, which fields or documents it reads, how a summary ties back to the underlying message or note, or whether a user can see why a lead scored as it did. There is no accuracy page, benchmark page or research post on the site. The subscription agreement runs the other way, disclaiming all warranties of accuracy and providing the service as is with all faults. An unexplained score that suppresses a viable claimant stays hidden, because the firm never works that lead.
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.
Real review surfaces are published, and the point at which the system acts alone is not. The drafting workflow puts a person in it, telling the user to review, send and move on, and the outputs are described as communications ready to send, not sent ones. Three controls exist: an administrator can disable the AI in global settings, the integration keeps the last thirty messages so a user can review or clear the conversation, and an hourly cap per user bounds throughput. Against that, the same page promises automated responses to new inquiries and instant response to every lead across channels, which cannot both be true of a system that always waits for review. The point at which the system sends without a person is never stated. No confidence signal, abstention behavior or supervision policy is published.
Oversight is implied rather than described as a control. The published account is that AI assesses every lead the moment it opens so the team knows which cases are worth taking. No human decision step is described. No review step is specified and no threshold is stated. Nothing says whether a lead with a low score is deprioritized, or closed automatically, and nothing addresses what happens when a score is wrong or how a user would find out. Real unattended automation runs alongside it and is marketed as the point. Personalized emails and tasks fire automatically on capture, and automations described as AI enhanced summarize information and follow up with potential clients. The system therefore communicates with prospective clients without a person in the loop. The agreement allocates responsibility rather than describing controls. It makes the subscriber solely responsible for its own data entry and for maintaining its own deadlines, and disclaims responsibility for misuse of the calendar. No written commitment is published that the models work alongside a supervising human with real review surfaces.
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.
Named customers at named firms, with roles, and no figures. Three testimonials repeat across the pricing and integrations pages with full attribution: Adam Smallow, Managing Partner of the Law Offices of Adam M. Smallow; Samantha Stone, Supervising Paralegal at Hansen and Rosasco LLP; and Jennifer Gore-Cuthbert, Founder and Owner of Atlanta Personal Injury Law Group Gore LLC. None is dated, no case study is published, and the claims are qualitative: more leads captured, data entry errors eliminated and better visibility of which marketing works. A Happy Clients page exists in the navigation and was not opened; it may say more.
Named firms carry figures, undated and without method. Four customers are named with attributed individuals. David Brauns of Brauns Law is quoted against 250,000 dollars a year saved in advertising costs. Kendall Knecht of Whitley Law Firm is quoted against a 49 percent increase in converted leads, which also has a dedicated case study. Ryan McKeen of Connecticut Trial Firm is cited as being named the tenth fastest growing firm in the country by Law Firm 500. Joe Fantini of Rosen Injury Lawyers describes the product as the single most important software the firm has purchased. A named customer and a figure are joined on two of the four. Nothing is dated, and no method is published for any figure, so the basis of the 49 percent and the 250,000 dollars is unstated. The Law Firm 500 growth ranking is an award to the firm rather than an outcome of the product. A customers page and further case studies exist and were not opened; they may say more.
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.
Substantive commitments a buyer can read before signing, and nothing on privilege or separation. Section 10 of the published Software Licensing Agreement defines Confidential Information to include any and all client and client related information. It binds each party to use it only to perform the agreement, limits disclosure to those with a need to know under equivalent duties, and lasts forever for client information against five years for other material that is not technical. Section 4 limits Authorized Users to the subscriber's employees and contractors and states expressly that clients may not be Authorized Users. On the model provider, the AI page says documents pass through the OpenAI API, that OpenAI does not train on API submissions, and that it keeps API data for thirty days. No privilege or work product treatment appears anywhere, and nothing describes tenancy, separation by matter or a permission model.
Substantive commitments sit in a published agreement, with one clause pointing the other way and no privilege treatment. Section 2.8 commits Filevine to maintain administrative, physical and technical safeguards for subscriber data and not to disclose it except under the privacy policy or as expressly permitted in writing. It also bars access except to provide the service, address technical problems, or answer the subscriber's support requests. Section 6 adds a mutual confidentiality regime surviving seven years, and section 6.4 requires third party service providers to keep information confidential and bars them from using it for any other purpose. Against that, section 7.2 reserves to Filevine a right to collect and analyze subscriber data and to use, store, copy, display and transmit it to improve and enhance the service and for other development purposes. It may also use and share the data in aggregate or deidentified form in its business, and that right survives termination. Two things are missing. No privilege or work product treatment appears anywhere, on a product that holds prospective client intake material where privilege attaches from first contact. Nothing describes separation between firms or matter level walls inside a firm's own workspace.
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.
A real published position on the advice line, short of supervision and competence. Section 11.14 of the agreement says Law Ruler Software is not a law firm, does not provide legal advice whatsoever, and does not provide legal advice or legal services through its website or by any other means. Those last words reach the software, not only the marketing site. The audience is limited by contract as well: the recital defines the subscriber as a law firm authorized to provide legal services as defined by the state bar association where it is located, and section 4 bars clients from being Authorized Users, so there is no consumer facing surface. Nothing goes past the disclaimer: no rule of professional conduct, no ethics opinion, no jurisdiction limit beyond a license to display within the United States, and nothing on competence or supervision of AI output. The AI page publishes sample prompts asking for the legal implications of a business decision and the risks and liabilities of a legal issue, which describe the product in advice terms; the agreement governs where the two conflict.
A real published position, undercut because its worked example belongs to a different product. Section 8.2 of the subscription agreement states that Filevine is not a law firm or legal services provider and does not and cannot provide any legal advice, explanation, opinion or other recommendation. That is an express position a buyer can read before signing, and more than a marketing disclaimer. Section 8.5 makes the subscriber solely responsible for its own calendar entries and for maintaining statutory deadlines. The limitation is scope. The operative sentence ends with contract strategy and the meaning of terms in any contract generated by the services. That describes Filevine's contract product rather than intake and lead scoring, so the clause reaches this product only through its general wording. Nothing engages professional responsibility itself. No bar guidance, rule of professional conduct or ethics opinion is named. Nothing addresses a firm's obligations where an automated system communicates with a prospective client or where a viability score shapes who gets representation.
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.
No governance position of any kind is published. There is no responsible AI page, principles statement, management system, named owner accountable for model behavior, testing regime before release, or anything on uneven output across matter types or populations. The navigation and footer were checked across six pages and carry no governance page; the only policy documents published are the terms of use, the privacy notice and a disaster recovery procedure, none of which addresses model behavior. The nearest statement is an assurance about what OpenAI does not do with API data, which is a confidentiality commitment about a supplier, covered under confidentiality and supply chain. The absence matters more on a product used for Social Security disability, immigration and mass tort intake, where qualification logic decides which inquiries a firm pursues.
No governance position of any kind is published. There is no responsible AI page, no principles statement, no accountable owner or function named, no testing regime before release and no management system on the surfaces read. Nothing addresses uneven output, and the omission is pointed rather than formal on this product: Lead Viability scores prospective clients and determines which of them a firm pursues, so any systematic tilt in that score falls on people seeking representation rather than on the buyer, and nothing published states whether the scoring has been tested for it or what it is derived from. The subscription agreement is silent on the subject throughout.
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.
Specific on continuity and nearly silent on the rest, and the privacy notice does not reach the product at all. The disaster recovery procedure is the strongest document: hosting on Azure across regions, Azure Blob Storage redundancy for client documents, and exact restore schedules. SQL server backups are taken daily at 07:30 UTC, with instant recovery snapshots held two days, daily points fifteen days, monthly points three months and an annual point one year, and the team rehearses the runbook in scheduled tabletop exercises. Exhibit B adds daily backups, a free export and a one time full export within ten business days for 250 dollars. What governs client data in normal operation is absent. The privacy notice says in its first line that it covers only information collected by the website, so nothing published covers intake records, documents or prompts in the platform. No retention period, deletion certification, subprocessor list or breach notification commitment is published. A data request hub run by ProfitSolv is linked in the footer and was not opened.
The agreement covers most of the ground and names no supplier. On retention and deletion it is concrete. Filevine has no obligation to hold uploaded data files more than thirty days after termination, and the subscriber elects within twenty days whether files are destroyed or returned in an agreed format. Written certification of deletion is available on request, and retained copies are permitted only for archival, legal or regulatory purposes and for no other use. Migration copies are held ninety days and then hard deleted. On access, section 2.8 restricts Filevine's own access to providing the service, fixing technical problems and answering support requests. Section 6.1 touches incident practice indirectly, requiring prompt notice of any unauthorized disclosure of confidential information. Availability carries a 99.5 percent monthly commitment. What is absent is the supplier picture. Section 6.4 discloses that third parties perform hosting, backup and recovery, email delivery, customer service and data analysis, and names none of them. A buyer knows the kinds of company touching intake data but not their identities.
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.
A real published allocation of loss, with scope, a cap and an exception, and nothing that reaches the output. Section 8(b) gives an indemnity from the vendor, defending the subscriber against third party claims that its use of the service infringes a registered patent, trade secret, copyright or trademark. Section 9 caps liability at the amount paid in the twelve months before the event, excludes indirect and consequential damages, and carves intellectual property infringement out of the cap, so a buyer can read the scope, the ceiling and the exception before signing. None of it addresses what the product now does. Section 7 provides the service as is and disclaims all warranties including fitness, there is no warranty on output, no insurance position is published, and the indemnity covers infringement, not a drafted communication being wrong. The agreement does not mention the AI feature.
The agreement allocates real loss through a vendor indemnity and a warranty, and nothing reaches output. Section 8.1 warrants that the service will function in substantial accordance with its written specifications and documentation. The remedies end in termination and a pro rata refund of prepaid fees. Section 9.2 commits Filevine to indemnify and defend the subscriber against third party claims that authorized use infringes United States patents of which Filevine is aware, copyrights or trade secret rights. Named exclusions cover combination with software from outside Filevine and trial subscriptions. Against that, section 8.2 provides the service as is with all faults outside the express warranty and disclaims accuracy expressly. Section 8.3 caps total liability at fees paid in the six months before the event, and claims are barred after twelve months. Nothing addresses the exposure the AI creates. There is no warranty on the correctness of a viability score or a generated summary, no service credit and no insurance position.
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.
A logo wall with no documentation an implementer could use. The integrations page was last modified 29 December 2023 while the rest of the site carries 2026 dates. It shows roughly thirty marks with no text: Tabs3, TimeSolv, CosmoLex and Rocket Matter among the sibling products, then HelloSign, Smith.ai, ApexChat, Gmail, Zapier, Twilio, Office 365, CallRail, Scorpion, Ngage, Thomson, Nolo and Lawyers.com alongside lead generation vendors. Nothing states what syncs, in which direction, on what trigger or what a firm must configure. The page body describes dozens of integrations while its metadata claims hundreds. Two fragments of depth exist elsewhere: the pricing FAQ says data from contact and intake forms imports automatically into case management systems, and Exhibit B provides an open API on all tiers, with a request limit scaled to user licenses and no API fee. The support knowledge base at support.lawruler.com was not opened and may say more.
One integration is described at the level of what it moves, and no implementer documentation is published. The Filevine connection is native rather than a partnership. The subscription agreement defines the Filevine Services to include products delivered through filevine.com, leaddocket.com, getoutlaw.com and vinesign.com under one agreement. The product material states that lead data transfers natively into Filevine to create a unified client record and eliminate double entry, with retainers and payments collected inside Lead Docket. That names both the counterparty and the object moved. Lead capture is described as reaching web forms, live chat and after hours calls, and outbound SMS and email are sent from the platform; the telephony and messaging connections behind them are not specified. What is missing is depth. No document management, calendaring or electronic billing system is named, and no API documentation is published on the surfaces read. Nothing states what fields map, in which direction, or what a firm must configure. A dedicated integrations page exists in the navigation and was not opened; it may say more.
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.
Residency is stated with the provider named, and tenancy is not addressed. The disaster recovery procedure says the platform is hosted on Azure, using regions to spread where stored data sits, with Azure Blob Storage redundancy for client documents and backups stored with geographic redundancy. A second region is identifiable, since the same page schedules weekly backups for an Azure SQL Canada database. Exhibit B says prices are for hosting at the vendor's United States cloud provider unless otherwise specified, and section 1.1 licenses access and display within the United States. Nothing states whether the platform is single or multi tenant, no dedicated or isolated option appears at any tier, and no region choice is offered. No location is given for the OpenAI leg, where documents are passed for the AI feature. The residency material sits on a page last modified 23 January 2024.
Cloud delivery is settled; tenancy and data region are not stated. The subscription agreement defines the service as software as a service delivered through named web properties. It requires only a browser supporting HTTP/2 and TLS 1.2 or 1.3 at the customer end and offers no on premises or self hosted option anywhere. Beyond that nothing is published. No statement says whether the platform is single or multi tenant, no dedicated or isolated option appears, no region is named for storage or processing, and no cloud provider is identified. Section 6.4 confirms that hosting is performed by unnamed third parties. The only geographic facts published are corporate and procedural: Utah governing law, exclusive venue and arbitration in Salt Lake County, and a Salt Lake City notice address. Those locate the company and the forum, not the data. Nothing in the material read addresses residency for a product holding intake records on prospective clients.
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.
No independent security attestation of any kind is published, and no security or trust page exists to hold one. The navigation and footer were checked across six pages and carry no security, compliance or trust center entry; the three policy documents published are the terms of use, the privacy notice and the disaster recovery procedure. None carries a SOC 2 report of either type, an ISO certification, a penetration test summary, a named auditor, a report period or a scope statement. The badges on the site are review directory marks from Software Advice, Capterra and GetApp, not security claims. The disaster recovery procedure is real operational disclosure, covered under stewardship and deployment; a continuity description the company publishes itself is not an independent attestation. Nothing is gated, and there is no portal to request a report from.
No independent security attestation is published on the surfaces read. There is no SOC 2 of either type, no ISO certification, no penetration test summary, no named auditor, no examination period and no certification claim of any kind on the Lead Docket site. No trust center or security page appears in its navigation or footer, which carry only a privacy policy, terms of service and the subscription agreement. The agreement commits to commercially reasonable administrative, physical and technical safeguards without referencing any external examination. One point matters for a buyer. Section 1.8 of the agreement defines the Filevine Services to include products delivered through leaddocket.com by name, so a Filevine attestation whose own scope covers that service would cover Lead Docket too. Filevine's own trust material was not opened and may say more.
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 provider and the model are both named, and change notice is absent. The AI page identifies OpenAI as the provider and ChatGPT as the model, refers to ChatGPT version 4 in setting the hourly limit, and describes the architecture. The feature runs through the OpenAI API, not the consumer product, and uploaded documents pass through that API for analysis. OpenAI does not use API submissions to train its models, and keeps API data for thirty days for abuse monitoring, accessible to a limited number of authorized employees and contractors under confidentiality. Where the models run is not stated for the OpenAI leg, and no commitment to notify customers if the model, version or provider changes is published. Azure appears on the disaster recovery page as the host of the vendor's own platform, not as the model provider.
The vendor refers to its AI throughout and identifies nothing underneath it. The site speaks of LeadsAI, of AI enhanced automations, and of AI that reads intake documents and assesses lead viability. It names no model, version, provider or hosting arrangement, and makes no commitment to notify customers if those change. The subscription agreement does not close the gap. Section 6.4 discloses categories of third party performing hosting, backup, email delivery, customer service and data analysis, which identifies functions rather than companies. Section 8.6 contemplates third party services embedded in the product while disclaiming responsibility for them. No subprocessor list exists on the surfaces read. The vendor does describe a distinct AI layer as its own named component. A buyer still cannot learn whose model reads a prospective client's intake file.
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 marketing page is gated, and the published agreement is a rate card. The pricing page names three tiers, Pro, Premium and Enterprise, with contact limits of 10,000, 15,000 and unlimited and automation limits of 3, 100 and unlimited. The first two allow up to three users, and Enterprise has a ten user minimum. The page states an annual term billed monthly, a 15 percent discount for paying the year in advance, a one time onboarding fee and a feature table, but no subscription figure, and all three plans are quoted. Exhibit B of the terms of use publishes rates for part of the range: local calls at 0.05 dollars a minute, toll free at 0.08, SMS at 0.05 and MMS at 0.06, tracking numbers at 3.00 and 5.00 a month, task routing at 0.075 a route, electronic signature at 1.00 a request, 2,500 emails per license with overage at 0.02, 5GB of storage per license with more at 10.00 a gigabyte a month, professional services at 150.00 an hour, a 250.00 full data export and a 50.00 minimum prepaid refill. The subscription cost needs a sales conversation, and there is no free version.
The pricing page carries no pricing, and the agreement carries the structure. The page at the pricing link in the navigation is a quote request form inviting a custom quote, with no rate, unit, tier or range. The subscription agreement sets out the rest. Fees are charged per Filevine License, with one named individual per license and no sharing. They are quoted and payable in United States dollars and invoiced in advance, with charges due ten days after the invoice date. Fees cannot be canceled or refunded, and the license count cannot be decreased during a term. Renewal is automatic for one year unless thirty days notice is given. Overdue interest runs at one and a half percent per month, overage fees are invoiced monthly in arrears under separately published product terms, and any increase requires 45 days written notice before the next renewal. A buyer can establish the unit, the currency, the term and the commitment before contacting the company, but not the number. One clause cuts against transparency: section 4.1 makes all prices in the sales order confidential information that the customer may not disclose to any third party without written consent.
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 documented with substance, and the boundary is left open. Eight practice areas each have a solutions page: personal injury, criminal defense, consumer protection, mass tort, business, Social Security disability, immigration and employment. The material is specific about the operating model it suits, addressing high intake volume, fast case turnover, referral and shared counsel arrangements in mass tort, and multilingual client communication in immigration. Firm size is handled through the plans, with Pro and Premium capped at three users and described as suited to small firms, and Enterprise carrying a ten user minimum. The agreement recites that the subscriber is a law firm. Not stated is where the product stops: in house and government legal are not addressed, no practice area is named as unsuitable, and the integrations page invites requests for anything not covered.
Coverage is claimed so generally that a buyer cannot tell whether their practice is served. The product is addressed to law firms throughout and to intake teams within them. The workflow described applies to any practice: capture, follow up, vetting, referral in and out, marketing source reporting and conversion. No practice area is named on the surfaces read, no firm size band is stated, and nothing says where the product stops or which kinds of matter it does not suit. The published customer names are personal injury and plaintiff firms, but the vendor makes no coverage statement to that effect. Jurisdiction is never addressed. Nothing distinguishes what the product does for a consumer facing practice from an insurance defense or in house function. A features page and a customers page exist in the navigation and were not opened; they may say more.
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?
Public product material says training does not occur, and the published agreement has no matching term. The AI page says ChatGPT does not train on the customer's information, that client data stays within the Law Ruler environment, and that OpenAI does not use data submitted through its API to train its models or improve its services. The Software Licensing Agreement was read in full on 4 September 2026 and contains no training, machine learning, deidentification or aggregate use clause, so no term grants or withholds the right.
The commitment is scoped to the model provider: nothing published says whether Law Ruler itself uses customer content to develop or improve its own product. The nearest contractual language, section 8(a), refers to content the subscriber provides and the vendor uses in providing the services, which frames a purpose rather than a prohibition.
Training on intake material has no stated position, and the closest clause does not mention it. Section 7.2 of the subscription agreement reserves to Filevine a right to collect and analyze subscriber data and content, and to be free during and after the term to use, access, store, copy, display and transmit it to improve and enhance the service and for other development, diagnostic and corrective purposes. It may also use and share the data in aggregate or deidentified form in connection with its business, with anonymized data expressly excluded from the customer's confidential information.
That is a broad and durable improvement right over intake material. It does not amount to a training permission, because it names neither training, machine learning nor models, and reading those into a general improvement right would go beyond what the clause says. No statement anywhere on the site says that customer content does not train models, and no opt out or configuration setting is described.
Prompt and Output Retention
How long does the product keep what a lawyer typed, and can that be set to zero?
Fixed periods are published for the AI path and nothing covers the platform around it. The AI page states that OpenAI retains API data for thirty days for abuse and misuse monitoring, accessible to a limited number of authorized OpenAI employees and specialized contractors under confidentiality and security obligations, and that the integration itself saves the history of the last thirty messages, which a user may review or clear at any time.
Documents uploaded to inform a request are passed through the same API. This is a disclosed fixed position rather than a configurable one: clearing a conversation is a manual action and disabling the feature is an administrator toggle, but no retention setting is offered. Retention of the underlying CRM records, intake submissions and stored documents is not stated anywhere. The disaster recovery page publishes backup retention, at two day snapshots, fifteen day daily points, three month monthly points and a one year annual point, which governs restore copies rather than how long client data is kept.
Fixed periods are published, and they cover less than the full question. The subscription agreement states that Filevine has no obligation to retain uploaded data files more than thirty days after termination or expiry. The subscriber elects within twenty days whether those files are destroyed or returned in an agreed format, and written certification of deletion is available on request. Any copies Filevine keeps are permitted for archival, legal or regulatory purposes only and for no other use.
Migration copies are held ninety days and then hard deleted. Two limits apply. Those periods apply at the end of the relationship, not during service: nothing states how long generated summaries, lead viability assessments or the prompts behind them persist while a subscription is live. And the deletion terms attach to uploaded data files. That is narrower than the agreement's own definition of data, which expressly includes material generated by the service in response to customer input.
Ethical Walls and Matter Segregation
Does retrieval respect the firm’s ethical walls, or can the model read across them?
Separation between matters or between customers has no described control in the product. Nothing states whether the platform is single or multi tenant, and no role, permission or access model inside the product is described on any surface. The nearest provisions govern who may hold an account rather than how work is partitioned: section 4 of the agreement restricts access to Authorized Users and states that clients and others who are not employees may not be Authorized Users, and section 1.2 limits the license to a single authorized application per user desktop.
The integrations page describes case syncing between two separate Law Ruler portals where both firms are customers, which is a sharing feature rather than a segregation control. Searched the home page, the AI page, the pricing page, the integrations page, the terms of use including all three exhibits, the privacy notice and the disaster recovery procedure on 4 September 2026.
Customers and matters have no described partition from one another. The agreement is strong on who may reach data and for what purpose. Section 2.8 limits Filevine's own access to providing the service, addressing technical problems and answering support requests, and section 6.4 binds third party providers to confidentiality. Purpose limits on the vendor's staff are a different control from a partition between one firm's data and another's. Nothing states whether the platform is single or multi tenant, no permission or role model inside a firm's workspace is described, and no matter level walls are addressed.
The agreement contemplates authorized users including third parties with whom the subscriber transacts business. The referral workflow is built to pass a prospective client's details to a receiving firm, so material crosses organizational boundaries by design with no published account of how it is fenced.
Third Party Request and Subpoena Notice
If someone subpoenas the vendor for a firm’s data, does the firm hear about it first?
The confidentiality section commits to notice before compelled disclosure, in the agreement rather than in a policy page. Section 10 carves required disclosure out of the confidentiality obligation only on condition that the receiving party immediately notify the disclosing party of the requirement and provide reasonable assistance in any efforts to protect the information from disclosure. Confidential Information is defined to include any and all client and client related information, so the commitment reaches the customer's own client material held in the platform, and the obligation survives termination in perpetuity as to that category.
The commitment is mutual, binding each party as receiving party. What is absent is the reporting half: no transparency report, no statistics on requests received, and no stated practice on what happens where a court order bars notification. No exception is reserved for emergency disclosure or for national security process.
A notice commitment sits in the confidentiality section of the published agreement. Section 6.1 provides that nothing restricts disclosure of confidential information as required by law, court order or other governmental order or request. In each case the party asked to disclose must timely inform the other party, use all reasonable efforts to limit the disclosure and keep confidentiality so far as possible, and permit the other party to try to limit the disclosure by appropriate legal means.
The commitment reaches customer data, since the same clause treats data constituting confidential information as within the regime. Two limits apply. The obligation is mutual and generic rather than a law enforcement policy addressed to customers, and no transparency report or record of requests received is published. A separate exception in the same clause permits Filevine to disclose data in accordance with its privacy policy. That is a different route and is not conditioned on notice.
Primary Law Corpus Provenance
Where does the law in this product come from, and does the vendor have the right to use it?
Legal content is never retrieved, so the product has no corpus to source. Law Ruler is a client relationship management and intake platform, and the AI feature drafts communications from prompts and from files the user attaches rather than from a body of legal material. No case law source, statutory database, form library license, publisher or reference set is named anywhere, and the question does not bite on this product class.
Recorded as the honest absence rather than a penalty. Searched the home page, the AI page and its FAQ set, the integrations page and the legal documents on 4 September 2026.
Intake records are the only material the AI reads, so the question does not bite on this product class. The material the AI works on is the firm's own intake record: web form submissions, uploaded documents, messages and notes belonging to the firm and its prospective clients. The product does not retrieve or present legal content, so there is no case law source, statutory database or licensed reference set behind anything it produces.
Recorded as the honest absence rather than a finding against the vendor. Searched the home page, the pricing page, the subscription agreement and the footer inventory on 4 September 2026.
Good Law Verification
Does the product tell you when the authority it just cited has been overruled?
Nothing on any located surface addresses checking authority for subsequent history, and the product does not present primary law. The AI feature generates emails, replies, intake questionnaires, retainers and onboarding documents; it does not retrieve or cite cases, statutes or regulations. The one place the question comes near the product is the vendor's own published prompt library, which includes asking for the key provisions of a named law or regulation, but no citation is returned to a user in the product and no verification step of any kind is described.
Searched the AI page and its FAQ set, the client intake and CRM product pages reached through the navigation, and the legal documents on 4 September 2026.
Nothing addresses checking authority for subsequent history, and the product neither retrieves nor cites primary law. Its outputs are lead summaries, viability assessments, task and follow up automations and marketing source reporting, none of which rests on a legal authority a user would need to verify. This is an absence, not a finding against the vendor. Searched the home page, the pricing page, the subscription agreement and the footer inventory on 4 September 2026.
Refusal and Uncertainty Behavior
What does the product do when the answer is not in the corpus?
Prompts the model cannot handle well have no described fallback. No abstention path, state for having no answer, confidence or grounding score, or behavior on a prompt the model cannot support is described. The published workflow runs from prompt to draft with a review step and no checkpoint before it, and the FAQs for the integration cover rate limits, history length, file types and how to disable the feature, not output quality.
The vendor's own sample prompts invite the model to summarize the legal implications of a business decision and to identify risks and liabilities, which are the requests where uncertainty behavior matters most. Searched the AI page, the home page, the pricing page and the legal documents on 4 September 2026.
Sparse or unfamiliar leads still receive a viability assessment, with no described low confidence state. Lead Viability is presented as an output produced on every lead the moment it opens, with no abstention path, no low confidence state, no confidence score exposed to the user and nothing on how the system behaves where a lead record is sparse, contradictory or in a matter type it has not seen. Nothing describes what happens when the document reading fails or returns nothing usable.
The agreement addresses the same territory only as an allocation of risk, disclaiming accuracy and making the subscriber responsible for its own data entry, which places the burden rather than describing a behavior. The gap matters here because an unexpressed uncertainty resolves into a score that quietly reorders which prospective clients a firm contacts. Searched the home page, the pricing page, the subscription agreement and the footer inventory on 4 September 2026.
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 was searched on 4 September 2026 on the product name Law Ruler and on the corporate name Law Ruler Software. No court order, opinion or disciplinary record naming the product or the company was located. This records the state of the public record on that date and is not a finding about the product.
The AI Hallucination Cases database maintained by Damien Charlotin was searched on 4 September 2026 on the product name Lead Docket and on the corporate name Filevine. No court order, opinion or disciplinary record naming the product or the company was located. This records the state of the public record on that date and is not a finding about the product.
Bar Guidance Alignment
Has the vendor engaged in public with the ethics opinions its buyers are bound by?
Bar authority is referenced once, in the agreement, without naming any guidance. The recital to the Software Licensing Agreement defines the subscriber as a law firm authorized to provide legal services as defined by the state bar association where it is located or provides services, so admission to practice is the condition of buying. Section 11.14 adds that the vendor is not a law firm and does not provide legal advice by any means.
Beyond that, nothing engages professional regulation: no bar association, rule of professional conduct, ethics opinion or guidance for any jurisdiction is named, and there is no mapping of obligations for a firm adopting the AI feature. The reference governs who may subscribe, not how the product should be used consistently with a lawyer's duties.
Bar and ethics guidance never surfaces, even on the questions this product raises most directly. No bar association, rule of professional conduct, ethics opinion or guidance for any jurisdiction is named or referred to in general terms on the surfaces read. Nothing addresses the professional questions this product raises: solicitation and advertising rules for automated follow up to prospective clients, referral fee arrangements in the referral workflow, or the duties owed to a prospective client whose information the firm holds.
The nearest statement is the agreement's declaration that Filevine is not a law firm and does not provide legal advice. That is a position on the advice line and is covered under UPL and Professional Responsibility Posture. Searched the home page, the pricing page, the subscription agreement and the footer inventory on 4 September 2026.
Billing and Fee Posture
Does the vendor address what happens to the bill when the work takes an hour instead of six?
Efficiency and revenue claims are published, and nothing addresses what happens to a client bill. The AI page says firms see higher productivity and profitability by doing high quality work in less time, that legal staff gain more time for client matters and billable hours, and that drafting compresses from minutes to seconds; an ROI calculator sits in the resources navigation. No record of AI assisted work for each matter is described, no guidance on fee or disclosure treatment is published, and nothing addresses how a firm should account for time the tool removed.
Personal injury and mass tort work is usually paid on contingency, and Social Security disability fees need approval, so the treatment of compressed preparation time is a live question in this product's main segments.
Cost and revenue claims are published, and nothing addresses the bill. The site carries 250,000 dollars a year saved in advertising at a named firm, a 49 percent increase in converted leads at another, and a general promise to convert more callers into clients without expanding headcount. Reporting is built to show which marketing spend produces signed cases. All of it is directed at the firm's own economics. No per matter record of AI assisted work is offered, no guidance on fee or disclosure treatment is published, and nothing addresses what a client is told about automated handling of their first contact.
Outside Counsel Guideline Readiness
Can a firm get this vendor through a client’s AI clause without a bespoke negotiation?
The model provider a firm would have to name is disclosed, and no forwardable pack exists. From published material, a firm answering a client's AI clause can say that the AI runs on the OpenAI API and that ChatGPT is the model. It can also say that uploaded documents pass through that API, that OpenAI does not train on API submissions, and that OpenAI keeps API data for thirty days. The whole AI feature uses that one provider, so this answers the AI question in full.
Other suppliers are named in the vendor's own material but never gathered in one place. Azure is the host on the disaster recovery page, and Twilio, HelloSign, Groupdocs Signature and DocuSign appear across the integrations page and Exhibit B. No data processing addendum, consent or notice pack, or current subprocessor register a firm could forward is published.
Categories of processor are disclosed, but no names, models or hosting providers are. No subprocessor register is published, no model or model provider is named, no cloud or hosting provider is identified, and no consent or notification pack exists on the surfaces read. The agreement discloses categories rather than identities: section 6.4 states that Filevine may contract third parties for marketing assistance, email delivery, hosting, backup and recovery, customer service and data analysis, and binds them to confidentiality, which tells a firm what kinds of company touch intake data and not which ones.
No data processing addendum was located on the Lead Docket estate and no route to request one is offered. The forwardable material that does exist is the published subscription agreement itself, whose confidentiality, access limitation and deletion provisions a firm could send to a client, and which says nothing about who processes its data using what model.
Court Disclosure Support
If a judge’s standing order requires an AI disclosure, can the product produce one?
A tribunal or client asking how a draft was produced would find no record to examine. Two adjacent things exist and neither does this job. The integrations FAQ states that messaging, electronic signature, marketing automation and the softphone dialer create an audit trail and provide transparency to staff, which records platform activity rather than model use. And the AI integration retains the last thirty messages of conversation history, which a user may clear at any time.
A capped buffer that a user can erase and that is not linked to a matter cannot function as a disclosure record. No export of AI usage, logging of which outputs the model generated, attribution of a draft to a model or version, or template or guidance for disclosing AI use to a court was located. Searched the AI page and its FAQ set, the integrations page, the pricing page and the legal documents on 4 September 2026.
Outputs carry no attribution to a model or a reviewer, and no export would produce one. Nothing describes an export covering which model produced a summary or a viability assessment, what it drew on, or whether a person reviewed it, and nothing marks any output as machine generated. No disclosure template or guidance is published. Two adjacent facts fall short. The product keeps a lead history with status changes and communications, which records what the firm and the system did rather than attributing any output to a model.
The agreement provides for a written certification of deletion on termination, which is a record about data destruction rather than about AI use. The question is live on this product because intake records and their scoring can become discoverable in fee disputes and in bad faith litigation, and nothing published helps a firm produce that history in an attributable form.
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.
- Citation Accuracy and Hallucination Disclosure
- AI Governance and Bias Disclosure
- Security Certifications and Trust Center
- Ethical Walls and Matter Segregation
- Primary Law Corpus Provenance
- Good Law Verification
- Refusal and Uncertainty Behavior
- Court Disclosure Support
Product updates
The latest logged changes from each vendor, newest first, each linked to its source.
Lead Docket
-
Product / capability
Lead Viability shipped in Lead Docket.
Source
In summary
Law Ruler
Law Ruler, from Law Ruler Software, LLC of West Palm Beach, Florida, part of ProfitSolv, is a client relationship management, intake and marketing automation platform for law firms that take on leads in volume. It combines a softphone, two way texting and drip campaigns with qualifying intake forms, document automation and electronic signature by text. Reporting covers cost per lead and conversion. Its AI drafts emails, replies and intake questionnaires through the OpenAI API at no extra charge. According to the AI Legal Index, Law Ruler names its model provider, hosts on Microsoft Azure and publishes a usage rate card in its customer agreement. It sells three tiers, Pro, Premium and Enterprise, with contact and user limits.
Lead Docket
Lead Docket, a Filevine product sold under its own name, is intake and lead management software for law firms. It covers the stretch from a prospective client's first contact to a signed retainer, with automated follow up, referral tracking, marketing source reporting and payment collection. Its AI layer, LeadsAI, reads intake documents, summarizes lead details and scores each lead for viability as it opens, and signed leads transfer natively into Filevine. According to the AI Legal Index, Lead Docket's published agreement sets deletion terms with written certification, and it names customers with figures, such as a 49 percent rise in converted leads at Whitley Law Firm. It is quoted through a pricing form and charged per license.
Questions buyers ask
Law Ruler vs Lead Docket: which is better for a personal injury firm's intake?
Both manage intake from first contact to signed retainer for firms that advertise at volume. Law Ruler names its AI provider, publishes usage rates and has practice pages for personal injury and mass tort. Lead Docket scores every lead with AI and moves signed cases straight into Filevine, which matters most to firms already running it. From the AI Legal Index, based on each vendor's own published materials as of September 26, 2026. No vendor pays for placement.
Which AI model does Law Ruler use?
Law Ruler's AI runs through the OpenAI API, with ChatGPT named as the model and version 4 referenced in its rate limit. It states that uploaded documents pass through that API, that OpenAI does not use API submissions for training and keeps API data thirty days for abuse monitoring, and that the tool keeps the last thirty messages. From the AI Legal Index, based on each vendor's own published materials as of September 26, 2026. No vendor pays for placement.
How does Lead Docket's lead viability score work?
Lead Docket says LeadsAI reads intake documents and assesses the viability of every lead the moment it opens, so an intake team can see which matters are worth pursuing. From the AI Legal Index, based on each vendor's own published materials as of September 26, 2026. No vendor pays for placement.
How are Law Ruler and Lead Docket priced?
Both quote subscriptions on request. Law Ruler names three tiers, Pro, Premium and Enterprise, with contact and user limits, and its customer agreement publishes usage rates such as 5 cents a text and $1 per electronic signature. Lead Docket's pricing page is a quote form; its agreement sets per license charging and annual renewal, and makes the price a customer pays confidential. From the AI Legal Index, based on each vendor's own published materials as of September 26, 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.
Three points to weigh. Lead Docket's agreement reserves a broad right to use subscriber data to improve its service and to share it in aggregate form with identifiers removed. It does not name model training. Law Ruler's training statements concern OpenAI, and nothing published says whether Law Ruler uses customer content itself. On security, the detail here comes from Lead Docket's own site, and Filevine's security material sits on Filevine's. Lead Docket's agreement also makes the price a customer pays confidential. Neither vendor reviewed this page.