L

LawToolBox

The core is a rules based deadline engine: enter a trigger date and the platform calculates dependent deadlines from rule sets the vendor's 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 needs Azure OpenAI enabled in the customer's own Microsoft tenant.

It adds a way in: reading an email, attachment or handwritten court order, pulling out the dates, mapping them to the civil rules behind them, and summarizing documents. It can be removed without touching what the firm bought. The AI is an intake layer on a deterministic calculator, not the calculator.

Deadline charts and forms the product generates may be out of date or built for a different state or jurisdiction, the agreement warns, and may not match local court rules. It expressly disclaims 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. The pricing FAQ says a team of attorneys monitors court rules daily so deadlines are always up to date and accurate, the opposite claim.

The grounding is structural: deadlines come from named rule sets in a public catalog, and the AI maps extracted dates to the rules behind them. No error rate, sample or test of the extraction is published.

The agreement says the application is meant to be used alongside other deadline reminder and calendaring systems. It conditions use of its reminders on the firm stating that it has at least one other independent way of calculating and being reminded of its deadlines, and the firm also agrees to check the algorithms independently against the needs of each matter. The vendor says that condition is priced in. Around it sits a described review structure.

Extracted deadlines appear in Outlook for the user to check and edit before they go anywhere, and the privacy policy says no calendar event is ever added without the registered user's prior consent. The agreement requires a licensed attorney competent to manage the case to review and modify all deadlines and pleadings.

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. The deadline platform has been deployed and written about for a decade, and no account of the AI in production is published.

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.

For the AI, processing happens inside the customer's own Microsoft container and no result is stored by the vendor. 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. Privilege is addressed in that warning rather than in any commitment.

A section of the agreement headed Duty to Consult a Licensed Attorney says the product generates legal information of the kind found in a legal publication or a retail legal form. It says the user is not receiving legal advice, and that the material is general and may not fit the user's circumstances. It says output must be checked by an attorney licensed in the relevant state or venue. It also requires a licensed attorney competent to manage the cases on the platform to review and modify all deadlines and pleadings as needed, and describes the product as producing a first draft and saving time rather than supplying judgment.

Competence, supervision and jurisdiction are each named. The AI ethics page makes the same point for the machine: a licensed person must review all AI generated work, as they would a paralegal's.

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; and nothing goes into a Microsoft or LawToolBox model. Its ethics page addresses bias as a duty of the user, telling attorneys they must understand any bias in AI results and the data behind them.

It notes that the data set is always defined by the end user, who points the AI at a specific file, URL or files in their own tenant. That is an architecture argument, not governance. No owner inside the company is named, nothing is published on what is tested before a change ships, and no finding about uneven output has been disclosed.

LawToolBox publishes 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 access to each matter 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. No subprocessor list, incident response or breach notification practice, or statement on encryption at rest is published, and the retention position runs the other way, since a subscriber's data is not deleted until all statutes of limitation have expired.

Sold as is with all warranties disclaimed, the product comes under the economic loss doctrine and 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 percent monthly uptime target and credits of 10 or 25 percent of that month's fees, claimable within 30 days and capped at the month's fees. Nothing covers a deadline calculated wrong.

Sixteen named systems each have their own page. Direct integrations cover Actionstep, Caret, LEAP, MyCase, Neos, PracticePanther, Rocket Matter and Smokeball. Microsoft 365 integrations cover 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 gets its own Microsoft group, calendar, Teams space, SharePoint folders and OneNote, and a document management system can be linked 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.

Every plan carries the promise to keep data in the customer's own tenant, and that is literally true for the Microsoft artifacts 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. The privacy policy, though, 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.

No independent attestation is published and none is claimed. There is no security page or trust center in the navigation or footer, no SOC 2, ISO or penetration test reference in the agreement, privacy policy or any product page, and no report offered on request. Instead, Enterprise Security is listed as a feature of every plan with nothing behind it, and the privacy policy describes security measures, which is a statement of practice, not an audit.

The vendor leans 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.

All AI features run on Microsoft Azure OpenAI. The vendor says processing happens inside each customer's own Microsoft 365 cloud, reads only data that user can already reach, and never uses prompts or responses to train models that benefit other legal professionals. Turning the feature on requires Azure OpenAI to be enabled in the customer's own tenant, and a firm can bring its own Azure OpenAI license and run its own prompts against its own documents or a URL.

So whose models run, where and on whose account is published. Not published: the model or version, which Azure region serves the deployment, or any commitment to tell customers if the underlying model changes beneath a prompt library they have built.

Rates are published for every firm size range in both billing cycles. 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 a license for every Microsoft 365 licensed mailbox in the firm or department, the minimum commitment is one year, and cancellation brings no refund for the current term. Implementation costs are published too: four dollars per user to activate the NetDocuments, iManage, ECFX or InfoTrack connectors, and extra training and consulting at $225 an hour.

Up to 20 published rule sets are included for firms of 20 or more, with other jurisdictions quoted on request, and onboarding is quoted separately. One figure is withheld: LawToolBox AI is described only as an additional fee.

Four buyer pages sit in the navigation, for law firms, corporate legal departments, enterprise firms, and government and agencies. The pricing ranges run from two users to eighty and above. Practice coverage is stated: 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 public rule set catalog that can be read before subscribing.

The limits are stated in the agreement itself. A subscription includes up to 20 published rule sets for firms with 20 or more licensed users, rule sets outside the catalog are quoted on request, and those marked private preview are excluded unless agreed. Custom rule sets are built on request at extra cost.