L
LawToolBox
LawToolBox is court-rules deadline calendaring and matter management from LawToolBox.com, Inc. of Englewood, Colorado, built to live inside Microsoft 365. A user enters a trigger date and the platform calculates the dependent deadlines from the vendor's own rule sets, covering thousands of state and federal courts across the United States and Canada and practice areas from bankruptcy and patent to family law, probate and administrative rules, then syncs them to Outlook, Google or Apple calendars or to a case management system.
Each matter provisions its own Microsoft group, calendar, Teams space, SharePoint folder structure and OneNote. LawToolBox AI, licensed separately and running on Azure OpenAI inside the customer's own Microsoft tenant, reads emails and attachments including handwritten court orders, extracts deadlines and appointments for the user to review before they reach a calendar, maps them to the civil rules behind them, summarises documents and runs custom prompt libraries.
The company also publishes Model Context Protocol connectors that let a firm's own assistant, in Microsoft 365 Copilot, Claude or ChatGPT, reach its matters and deadlines. Named integrations run to Clio-adjacent and plaintiff systems alike, among them Actionstep, Caret, LEAP, MyCase, Neos, PracticePanther, Rocket Matter, Smokeball, Centerbase, ECFX, Filevine, iManage, InfoTrack, NetDocuments, Soluno and SurePoint. Rates are published by firm size, and the agreement, unusually, conditions use on the firm keeping a second independent deadline system.
Capability grades
All 15 axes, graded from public sources on the date shown. 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 AI is real, it is the vendor's own, and it sits on top of a product that predates it by a quarter of a century. The core is a rules-based deadline engine: enter a trigger date and the platform calculates the dependent deadlines from rule sets the vendor's own attorneys build and maintain, covering thousands of state and federal courts, under a patent the company filed for online deadline management in 1998. No model is involved in that.
LawToolBox AI is a separately licensed add-on that requires Azure OpenAI to be enabled in the customer's own Microsoft tenant, and what it adds is a way in: reading an email, an attachment or a handwritten court order, pulling the dates out, mapping them to the civil rules behind them and summarising documents. Useful, and removable without touching what the firm bought. A buyer should read the AI as an intake layer on a deterministic calculator, not as the calculator. Verified 20 September 2026.
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 is measured, and the vendor is unusually blunt about why that matters. The agreement warns that the deadline charts and forms the product generates may be out of date or built for a different state or jurisdiction, may not match local court rules, and carries an express disclaimer of any warranty that the information is correct, complete or current. The AI ethics page says plainly that AI hallucinates and makes mistakes and that a licensed person must review everything it produces.
Against that, the pricing FAQ says a dedicated team of attorneys monitors court rules daily so deadlines are always up to date and accurate, which is the opposite claim in the opposite register; both are on the estate and a buyer should notice the gap. What grounding exists is structural rather than published: deadlines derive from named rule sets listed in a public catalogue, and the AI maps extracted dates to the rules behind them. No error rate, sample or test of the extraction is published. Verified 20 September 2026.
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 constraint is categorical, it is the vendor's own, and it is in the contract rather than the marketing. The agreement states that the application is intended to be used in conjunction with other deadline reminder and calendaring systems, and conditions use of its reminders on the firm representing that it has at least one other independent method of calculating and being reminded of its deadlines; the firm also agrees to verify the algorithms independently against the needs of the matter.
The vendor says that condition is priced in. Around it sits a described review structure: extracted deadlines are presented in Outlook for the user to check and edit before they go anywhere, the privacy policy states that no calendar event is ever added without the registered user's prior consent, and the agreement requires a licensed attorney competent to manage the case to review and modify all deadlines and pleadings.
What the system does alone, what it may not be relied on for, where a person checks it and how a matter returns to human judgement are all published. Verified 20 September 2026.
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.
There is customer material, and none of it is about the AI. The case studies index carries nine items dated between 2015 and 2021, every one of them written by a platform or a publication rather than the vendor: Microsoft Azure and Microsoft Office customer stories, a Microsoft Teams story for legal departments, a LexisNexis case study on LawToolBox with Time Matters at the Los Angeles Unified School District, and a LegalTalk Network episode on rules-based docketing.
The most recent predates the AI features by two years. A separate customer story on Microsoft's partner site names an attorney at Marrache Law. The vendor's own testimonials carry first names and job titles only, three of them paralegals, with no firm named and no figures. Awards are from 2018. So a buyer can see that the deadline platform has been deployed and written about for a decade, and cannot see a single account of the AI in production. Verified 20 September 2026.
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, one of them a warning the vendor did not have to publish. The agreement limits use of Confidential Information to performing the vendor's obligations, and its anonymous aggregation clause states that no client file information is ever available or accessed. The privacy policy says matter data sits in dedicated databases on dedicated servers and that personal information there is never shared with third parties, that every employee signs a confidentiality undertaking and passes a background check, and that a firm administrator controls who reaches which matter, can grant read-only access and can withdraw a departing user from every matter.
The AI adds a strong position: processing happens inside the customer's own Microsoft container and no result is stored by the vendor. Two things hold it here. The agreement states that emails sent by the application are not encrypted and asks the firm to weigh what that means for privileged material it chooses to store in reminders. And privilege is addressed in that warning rather than in any commitment. Verified 20 September 2026.
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 clearest treatment of the advice line on this index, and it sits in the agreement. A section headed Duty to Consult a Licensed Attorney states that what the product generates is legal information of the kind found in a legal publication or a retail legal form, that the user is not receiving legal advice, that the material is general in nature and may not fit the user's circumstances, and that the output must be verified by an attorney licensed to practise in the applicable state or venue.
It goes on to require that a licensed attorney competent to manage the cases loaded onto the platform review and modify as necessary all deadlines and pleadings, and describes the product as generating a first draft and saving time rather than supplying judgement. Competence, supervision and jurisdiction are each named. The AI ethics page adds the same point for the machine: a person licensed to practise must review all AI-generated work, the way they would review a paralegal's. Verified 20 September 2026.
AI Governance and Bias Disclosure
Published governance over model behaviour: who owns it inside the vendor, what is tested before release, and what is disclosed about disparate output across matter types, parties, or populations.
A stated commitment with nothing behind it that a buyer could audit. The vendor says it is committed to responsible AI and publishes a Responsible AI Guarantee: results are generated through Microsoft Azure AI and Copilot, which by design do not train on customer data; the vendor does not and cannot store AI-generated results; nothing goes into a Microsoft or LawToolBox model. Its ethics page also addresses bias, though as a duty it places on the reader, telling attorneys they are obliged to understand any bias embedded in AI results and the data set behind them, and noting in its own case that the data set is always defined by the end user, who points the AI at a specific file or URL or at files in their own tenant.
That is an architecture argument rather than a governance one. No owner inside the company is named, nothing is published about what is tested before a change ships, and no finding about uneven output has been disclosed. Verified 20 September 2026.
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.
Access and handling are described in real detail; the ends of the data's life are where it thins. Published: matter data in dedicated databases on dedicated servers, https in transit, passwords stored as PBKDF2 hashes with the iteration count and key sizes given, single sign-on through OpenID, firm administrators controlling per-matter access with read-only options and full revocation when someone leaves, OAuth tokens for integrators that a Microsoft global administrator can revoke from their own Azure portal, background checks and confidentiality undertakings for every employee, and server request logging kept inside the company.
For the AI specifically, nothing is retained because processing stays in the customer's Microsoft container. The gaps: no subprocessor list, no incident response or breach notification practice, no encryption-at-rest statement, and a retention position that runs the other way, since a subscriber's data is not deleted until all statutes of limitation have expired. Verified 20 September 2026.
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.
Published, specific, and pointed entirely away from the vendor. The agreement sells the product as is with all warranties disclaimed, invokes the economic loss doctrine, and carries an exculpatory clause in which the user releases the vendor from all liability for negligence, including negligent misrepresentation. The sole and exclusive remedy for any claim of harm or economic loss, however framed, is a refund: the amount paid for the specific matter where the firm pays per matter, or no more than six months of that user's fees.
The vendor ties this back to the firm's own non-delegable duty to have every deadline reviewed by an attorney. Alongside it sits a real service level agreement with a 99.9 per cent monthly uptime target and credits of 10 or 25 per cent of that month's fees, claimable within 30 days and capped at the month's fees. That answers downtime. Nothing answers a deadline calculated wrong. Verified 20 September 2026.
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.
This is the deepest integration estate in the pull, and it is documented rather than listed. Sixteen named systems each have their own page, split into direct integrations with Actionstep, Caret, LEAP, MyCase, Neos, PracticePanther, Rocket Matter and Smokeball, and Microsoft 365 integrations with Centerbase, ECFX, Filevine, iManage, InfoTrack, NetDocuments, PCLaw and Time Matters, ProfitSolv, Soluno, SurePoint and TagMyFav.
What moves is stated: deadlines sync to Outlook, Google and Apple calendars and to case management platforms through published APIs; each matter provisions its own Microsoft group, calendar, Teams space, SharePoint folder structure and OneNote; a document management system can be connected to deadlines or Microsoft itself used as one. Configuration is described in the subscription terms, from administrator rights and application permissions to Outlook rules and calendar filters, and the connector surcharge is published at four dollars per user. Third-party integrators authenticate with their own OAuth tokens. Verified 20 September 2026.
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.
The tenancy story is stated clearly and in two halves that a buyer needs to hold together. On one side, every plan carries the promise to keep data in the customer's own tenant, and that is literally true for the Microsoft artefacts the product creates, the matter groups, calendars, Teams spaces, SharePoint folders and documents, and for the AI, which runs on the customer's own Azure OpenAI inside their Microsoft container and returns nothing to the vendor.
On the other, the privacy policy states that matter and personal information submitted to LawToolBox is stored in dedicated SQL databases on dedicated LawToolBox servers, which is a separate estate under the vendor's control. No region is published for those servers, no residency option is offered, no single-tenant or on-premises alternative is described, and nothing addresses where a customer outside the United States would sit. Verified 20 September 2026.
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 attestation was located and none is claimed. There is no security page and no trust centre in the navigation or the footer, no SOC 2, ISO or penetration test reference in the agreement, the privacy policy or any product page, and no report offered on request. What appears instead is the phrase Enterprise Security listed as a feature included in every plan, with nothing behind it, and a detailed self-description of security measures in the privacy policy which is a statement of practice rather than an audit.
The vendor does lean on Microsoft's posture, noting that AI processing happens behind Microsoft's enterprise-grade security inside the customer's own tenant; that is the host's assurance, not the vendor's. The absence is recorded rather than inferred: the navigation and footer were run to the bottom and one search for an attestation returned nothing from the estate. Verified 20 September 2026.
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 is named without hedging and the architecture is the disclosure. All AI features run on Microsoft Azure OpenAI, and the vendor states that the processing happens inside each customer's own Microsoft 365 cloud, interpreting only data that user can already reach, with prompts and responses never used to train models that benefit other legal professionals. Activating the feature requires Azure OpenAI to be enabled in the customer's own tenant, and a firm can bring its own Azure OpenAI licence and run its own prompts against its own documents or a URL.
That answers whose models, where they run and on whose account more completely than most records in this index manage. What is not published is the rest: no model or version is identified, nothing states which Azure region serves the deployment, and nothing commits to telling customers if the underlying model changes beneath a prompt library they have built. Verified 20 September 2026.
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.
A buyer can work out the bill without speaking to anyone. Rates are published for every firm-size band in both cadences: billed yearly, $35 per user per month at 2 to 9 users, $33 at 10 to 19, $23 at 20 to 79 and $19 at 80 or more; billed monthly, $42, $40, $30 and $22. The unit is stated as a licence for every Microsoft 365 licensed mailbox in the firm or department, the commitment is a minimum of one year, and cancellation carries no refund for the current term.
What implementation adds is published too: four dollars per user to activate the NetDocuments, iManage, ECFX or InfoTrack connectors, additional training and consulting at $225 an hour, up to 20 published rule sets included for firms of 20 or more with further jurisdictions quoted on request, and onboarding quoted separately. One figure is withheld, and it is the one this index cares about most: LawToolBox AI is described only as an additional fee. Verified 20 September 2026.
Firm and Practice Coverage
Who the product is actually built for. AmLaw, midlaw, small firm and solo, in house departments, government and courts, and which practice areas are supported rather than merely claimed.
Who this is for is documented segment by segment, and so is what it does not cover. Four buyer pages sit in the navigation: law firms, corporate legal departments, enterprise firms, and government and agencies, and the pricing bands run from two users to eighty and above, so a solo practice and an enterprise deployment can each see themselves. Practice coverage is stated rather than claimed: thousands of state and federal courts across the United States and Canada, with bankruptcy, patent, family law, probate, estate and administrative rules named, and a published rule set catalogue a buyer can read before subscribing.
The limits are stated in the agreement itself, which is rarer: a subscription includes up to 20 published rule sets for firms with 20 or more licensed users, rule sets outside the catalogue are quoted on request, and those marked private preview are excluded unless agreed. Custom rule sets are built on request at extra cost. Verified 20 September 2026.
5 public documents
The public pages on file for LawToolBox, with the recorded signals each one supports and the date it was last read. Open any of them and check the reading against the record.
-
lawtoolbox.com/ai-legal-ethics5 signals
Client Data in Training, Prompt and Output Retention, Bar Guidance Alignment and 2 more
Read Sep 20, 2026
-
lawtoolbox.com/privacy-policy3 signals
Ethical Walls and Matter Segregation, Third Party Request and Subpoena Notice, Outside Counsel Guideline Readiness
Read Sep 20, 2026
-
lawtoolbox.com/lawtoolbox-ai1 signal
Refusal and Uncertainty Behaviour
Read Sep 20, 2026
-
lawtoolbox.com/pricing1 signal
Good Law Verification
Read Sep 20, 2026
-
Primary Law Corpus Provenance
Read Sep 20, 2026
From $19 per user per month billed yearly at 80+ users; $35 at 2–9 usersUSD, as published, never converted
- LawToolBox publishes its prices, in full, for every firm size.
- Billed yearly, per user per month: $35 for 2 to 9 users, $33 for 10 to 19, $23 for 20 to 79, and $19 for 80 or more.
- Billed monthly, per user per month: $42, $40, $30 and $22 across the same bands.
- You buy a licence for every Microsoft 365 licensed mailbox in the firm or legal department, not just for the people who do the docketing.
- The minimum commitment is one year. You can cancel at any time, but there is no refund for the term you are in.
- Add-ons that are priced: $4 per user to turn on the NetDocuments, iManage, ECFX or InfoTrack connectors, and $225 an hour for extra training or consulting.
- Add-ons that are not priced: LawToolBox AI, which is the part of the product this index grades, is described only as an additional fee. Onboarding and training are quoted separately.
- Rule sets: up to 20 published rule sets are included for firms with 20 or more licensed users. Anything outside the published catalogue, or a custom rule set, is quoted on request.
- A reseller may quote a different price from these published rates.
Fully published per-user subscription pricing, ungated, with both cadences on a toggle and four volume bands. **Billed yearly: $35 per user per month at 2–9 users, $33 at 10–19, $23 at 20–79, $19 at 80+.** **Billed monthly: $42, $40, $30, $22** across the same bands. Every band lists the same four inclusions: the rules-based calculator across thousands of state and federal courts, automated calendaring with sync to any calendar, matter management provisioning a shared inbox, folder structure, calendar and notebook in Microsoft 365, and document management either connecting an existing system or using Microsoft as a lean one. **The unit is a licence for every Microsoft 365 licensed mailbox in the firm or legal department**, stated on the page and repeated in the agreement. **Minimum one-year commitment**, billable annually or monthly; cancellation permitted at any time with **no refund for the current term**.
Every plan is listed as including customer support, enterprise security and keeping data in the customer's tenant. **Add-on fees:** $4 per user to activate NetDocuments, iManage, ECFX or InfoTrack; $225 per hour for additional training or consulting; **LawToolBox AI and other integrated options are an additional fee, not published**; onboarding and training quoted separately. Partner pricing is published separately for integrated products, and the agreement notes a reseller's price may vary from this MSRP.
Implementation: Partly published. **Connector activation is $4 per user** to switch on the NetDocuments, iManage, ECFX or InfoTrack integrations. **Additional training, consulting and configuration support is $225 per hour**, with an annual maintenance contract available at a reduced rate on request. Unpaid onboarding support outside application fault-fixing is capped at 2 hours unless a customer agreement says otherwise. Onboarding and training one-time or annual maintenance fees are quoted separately, and the subscription terms describe what onboarding covers: project kick-off, licence purchase and account provisioning, application permissions and deployment of the Outlook add-in and Teams app, configuration of a central docketing account and practice calendars, user import, Outlook rules and calendar filters, then expert and end-user calendaring training and a Q&A session. Building new rule sets is not included in the quote. Professional services such as custom coding, data modelling and data import from other applications are separately engaged and priced.
Confidentiality and data terms: No Business Associate Agreement is offered or referred to anywhere on the estate, and none would ordinarily be expected: the platform holds matter names, case numbers, trigger dates and deadline charts rather than health information. Worth recording for a reader who assumes otherwise: the product provisions a document management workspace and lets firms store documents and email attachments against a matter, so a firm running personal injury, medical malpractice or employment work will have protected health information pass through it. Nothing on the estate is sold or certified as a health system, and the agreement's own warning that application emails are unencrypted bears on the same point.
Note: Every figure read directly from the vendor's own pricing page on 20 September 2026, which publishes all eight rates ungated behind a yearly and monthly toggle. entryPriceUsd is recorded as 19, the lowest published paid rate, which is the annual rate at 80 or more users; the entry rate for a small firm is 35 and both ends are carried in the display and the basis so neither misleads. There is no free tier, so neither zero nor null applies. The commercial structure in the agreement corroborates the page: a licence per Microsoft 365 licensed mailbox, a minimum one-year commitment, and pricing that may vary from this manufacturer suggested retail price where a reseller or value-added reseller is involved. One figure is withheld and it is the one this index grades: LawToolBox AI is an add-on described only as an additional fee. Commercial Transparency is graded A on this evidence, with that gap recorded on the row.
Legal Signals
What each signal meansA signal records what public sources say on the date shown. It is not a grade and it is not a recommendation. Where a signal reads Not addressed, it means the index did not locate the material in public sources on that date, which is a statement about disclosure rather than about the product.
Client Data in Training
Can material a lawyer puts into this product be used to train a model?
A public policy or trust page states no training on customer content, with no matching term located in the published agreement.
Never, stated as a guarantee on a policy page, with a contract that stops short of saying it. The AI ethics page carries a Responsible AI Guarantee: results are generated through Microsoft Azure AI and Copilot, which by design do not train on customer data, the vendor does not and cannot store any AI-generated result because processing stays inside the customer's own Microsoft container, and none of the customer's data is ever used to train a Microsoft or LawToolBox model.
The agreement never uses the word training. What it does is narrower and still useful: the customer grants a right to use Confidential Information for the sole purpose of performing the vendor's obligations, and a separate clause permits aggregate anonymised reports on system usage and content trends with five named safeguards, including that no personally identifiable information is extracted and no client file information is ever available or accessed.
Prompt and Output Retention
How long does the product keep what a lawyer typed, and can that be set to zero?
A specific retention period is published and the customer cannot change it.
For the AI the window is zero, and the vendor explains why rather than asserting it. Prompts and results stay inside the customer's own Microsoft container: the feature runs on Azure OpenAI in the customer's tenant, interprets only data that user can already reach, and the vendor says it does not and cannot store any AI-generated result. That is a definite position, not a vague one. Matter data is the opposite case and a buyer should read the two together.
The privacy policy states that a subscriber's account can be disabled but the data will not be deleted until all possible statutes of limitation have expired and all potential claims against the vendor are released; only trial accounts can ask for deletion outright. So nothing the machine produces is kept, and what the firm typed into the platform is kept for a period measured in years and defined by litigation risk rather than by a retention schedule.
Ethical Walls and Matter Segregation
Does retrieval respect the firm’s ethical walls, or can the model read across them?
The product maintains its own permission model, documented, requiring the firm to keep it aligned.
Segregation is described at the level this product works at, which is the matter. Every firm gets a firm administrator who controls user permissions matter by matter, can limit a user's access to a shared case to read only, and when someone leaves can withdraw their access to every matter they were granted and then remove them from the firm entirely. Matter data sits in dedicated databases on dedicated servers, and each matter provisions its own Microsoft group, calendar, Teams space and SharePoint folder structure, so the wall a firm builds in Microsoft is the wall the product inherits.
Third-party integrators authenticate with their own OAuth tokens, and a Microsoft global administrator can revoke the add-in's token directly from their own Azure portal. What is not addressed is conflicts: nothing describes screening a named user from a matter for ethical rather than administrative reasons.
Third Party Request and Subpoena Notice
If someone subpoenas the vendor for a firm’s data, does the firm hear about it first?
Published terms or policy address disclosure to authorities or in response to legal process, and no commitment or reservation regarding customer notice is located anywhere. The vendor has told the customer that data can leave and has said nothing about whether the customer hears of it.
Disclosure is provided for and no notice attaches to it. The privacy policy says personal information is not disclosed except as described there, to comply with applicable laws or valid legal process, or to protect the vendor's rights or property, and elsewhere lists sharing with third parties when required by law or in response to legal process or lawful requests from law enforcement or government agencies. Nothing commits to telling the customer a demand has arrived, to waiting before complying, to narrowing what is produced, or to helping the firm seek a protective order, which matters more than usual here because the data in question is a law firm's matter list and deadline chart.
The agreement contains no confidentiality clause of the kind that normally carries a compelled-disclosure notice; its confidentiality language runs the other way, limiting what the vendor may do with the firm's information. No transparency report is published.
Primary Law Corpus Provenance
Where does the law in this product come from, and does the vendor have the right to use it?
Sources are identified without stating the licence or rights basis.
The corpus is court rules, the jurisdictions are published, and the basis on which the rule sets are built is the vendor's own work. A public rule set catalogue lists what a subscriber gets, covering thousands of state and federal courts in the United States and Canada and naming practice areas including bankruptcy, patent, family law, probate, estate and administrative rules; the subscription includes up to 20 published rule sets for firms of 20 or more users, anything outside the catalogue is quoted, and custom rule sets are built on request.
The vendor says a dedicated team of attorneys monitors the courts daily for rule changes. The deadline algorithms are asserted as the vendor's own intellectual property under a patent and a copyright, and the agreement forbids reusing them elsewhere. What is not stated is which text each rule set is derived from or on what licence, court rules being public.
Good Law Verification
Does the product tell you when the authority it just cited has been overruled?
The vendor computes and surfaces subsequent history itself, with the method described.
No case-law citator, and a currency mechanism of the vendor's own doing the same job for court rules. The pricing FAQ states that a dedicated team of attorneys monitors daily for changes to court rules, a blog post explains how the rule sets are kept current, and dated posts track specific amendments, such as the California summary judgment rule changes effective 1 January 2025. Release notes are published. That is a treatment signal for procedural rules rather than for authority, and it belongs to the vendor rather than a licensed source.
One contradiction a buyer should carry: the agreement says the opposite in the register that binds, warning that the forms and deadline charts the product generates may be out of date or built for a different jurisdiction and disclaiming any warranty that the information is correct, complete or up to date. Nothing published says how quickly a rule change reaches a live rule set.
Refusal and Uncertainty Behaviour
What does the product do when the answer is not in the corpus?
No located public material addresses what the product does when it cannot ground an answer.
Nothing published describes what the extraction does when it cannot tell. The AI reads an email, an attachment or a handwritten order and proposes deadlines for the user to review, but no confidence signal, threshold or abstention is described, and nothing says what a reviewer sees when the model has found a date it is unsure of, or an order it cannot parse, as distinct from one it has read cleanly. The vendor's answer to uncertainty is structural rather than behavioural, and it is a serious one: the agreement conditions use of the product on the firm keeping a second independent method of calculating deadlines, and the ethics page states that AI hallucinates and makes mistakes and that a licensed person must review everything it produces.
That is recorded on the oversight row. Checked the AI page, the ethics page, the agreement and the privacy policy on 20 September 2026.
Fabricated Citation Record
Does a public court record exist addressing fabricated or hallucinated legal citations in output from this product?
No court order, opinion or disciplinary record addressing fabricated or hallucinated legal citations produced by this product has been located as of the date shown. This is a statement about the public record on that one subject, not a finding about the product, and this signal is not a litigation history.
No record was located of this product's output being found fabricated or inaccurate in a proceeding, a regulatory action or a published account. Searches on 20 September 2026 across the vendor's estate, press and directory profiles returned nothing of the kind. The exposure here is not an invented citation: the product calculates dates and extracts them from documents, so the failure that would matter is a missed or miscalculated deadline, which is also the malpractice risk the vendor's own marketing names. Nothing published describes such an incident, and no account of one was found.
Bar Guidance Alignment
Has the vendor engaged in public with the ethics opinions its buyers are bound by?
Public materials refer to professional responsibility in general terms without naming guidance.
Professional responsibility is engaged at length, and not one rule, opinion or bar is named. A dedicated page of 23 February 2024 sets out seven duties it says are emerging as ethics rules on AI are promulgated around the United States: never submitting privileged work product to a model that trains on it, understanding how any third-party AI handles firm data, understanding embedded bias and the data set behind a result, treating generative AI as a higher bar than the semantic search offered by the large research providers, having a licensed lawyer review all AI-generated work as they would a new associate's, disclosing to a court the extent of AI use where a jurisdiction requires it, and addressing AI use and billing in the client engagement agreement.
The agreement adds a duty to consult a licensed attorney in the applicable state or venue. Substantial, and entirely generic: no model rule, no formal opinion, no state bar guidance is cited.
Billing and Fee Posture
Does the vendor address what happens to the bill when the work takes an hour instead of six?
Public materials claim time savings without addressing billing or disclosure, and the product sits inside a fee relationship between a lawyer and a client where those savings would change the bill.
The fee question is addressed squarely, as advice, with no record behind it. The ethics page tells attorneys to set out in their client agreements whether they will use AI and how they will bill for it, states that they cannot bill an hour for work the AI did in five minutes, allows billing for the time spent drafting and revising prompts, and points to flat or contingent fee arrangements as a way to capture the value instead.
That is more than most vendors say. What does not exist is the record that would let a firm act on it: the vendor states it does not and cannot store any AI-generated result, so nothing marks which deadlines or summaries the machine produced, and no export exists to show a client. The published commercial case is time saved, through an ROI calculator and claims about hours recovered from hand-calculating deadlines, with nothing addressing what a client is told.
Outside Counsel Guideline Readiness
Can a firm get this vendor through a client’s AI clause without a bespoke negotiation?
No located public material supports a client side disclosure obligation.
A buyer would answer some of a diligence checklist from published material and would have to ask for the rest. What is published, and readable before signing, is the full agreement including the service level terms, the security practices in the privacy policy, and the model provider: Microsoft Azure OpenAI, running inside the customer's own tenant. What is absent is the pack itself. No subprocessor list exists; the privacy policy refers in general terms to other companies employed to provide hosting, network services, IT support and customer service without naming any.
There is no security certification, no penetration test summary, no data processing addendum, no business associate agreement and no stated incident response or breach notification practice, and nothing is offered on request. Checked the agreement, the privacy policy, the full navigation and the footer on 20 September 2026.
Court Disclosure Support
If a judge’s standing order requires an AI disclosure, can the product produce one?
The vendor publishes disclosure guidance or a template without product support for producing the record.
The vendor raises court disclosure itself, and leaves the firm to produce the record. Its ethics page tells attorneys that if they use AI to generate any portion of a document filed with a court they may have an obligation to disclose the extent of that use, that some jurisdictions go further and require certification that confidential information was not disseminated, and that some require every section generated with generative AI to be identified to the court.
Raising the duty in that much detail is unusual. Nothing in the product answers it. The vendor states it does not and cannot store any AI-generated result, so no log exists of what the machine produced, nothing distinguishes an extracted deadline from one a paralegal typed once both sit on the matter calendar, and no export or format is offered for a filing. Guidance, then, without an artefact.