Nouveautés

Most AI tools start from a blank box. You paste in a paragraph, it answers from whatever it learned somewhere else, and it has never seen your file.

Sage in Juris starts from the case. Its case modes work from the documents you uploaded to that matter and leave out anything you flagged privileged. The citations it gives are checked and linked, or labelled when they could not be confirmed, so you can open them yourself.

An answer about your client should come from your client's file.

juris.kwatateam.com

It's tax time. Where is the receipt from March?

Kwata Books is bookkeeping for small businesses and sole proprietors in Canada. Receipts, expenses, invoices and tax reports in one place.

Snap a receipt with your phone, even a long till receipt, and it is read into your books. The original copy is kept. Expenses are sorted into categories for CRA tax time, and anything personal is kept out of your business deductions.

Ask Lex a question about your books and the answer comes from your own records. When Lex is not sure, it tells you to check with your accountant.

A lot of good practices run on Gmail and a shared Drive. It works, until someone asks a simple question about one matter.

Who can open this folder? Which version did the client see? Was that attachment forwarded on, and to whom? Is the privileged memo sitting next to everything else?

None of these are hard questions. They are hard to answer when the case lives in forty email threads.

Juris keeps each matter in one place. Documents can arrive by email at the case's own address or from a Drive folder you connect, and a privileged file can be flagged as you upload it.

Every practice has a folder called later. The attachments you meant to file. The notes from the call. The scan that is still on your phone.

Nothing goes wrong on the day you put something there. It goes wrong on the day someone asks for it, and you are searching three inboxes and a downloads folder while the other side waits.

Later does not stay the same size. It grows by one matter at a time.

juris.kwatateam.com

You sent the application, then another, and another, and heard nothing. Not a no. Nothing.

Aya is a career management platform. Search for jobs, get alerts when new ones match, and track every application on one board.

The jobs it finds are scored against your resume, with a plain answer: apply or skip. Pick the country you are applying in, and Aya rewrites the weak parts of your resume and scores it against that country's rules, with what to fix. It writes a matching cover letter and helps you prepare for the interview.

Then you apply yourself. Aya never sends an application for you.

Flag a document privileged as you upload it to Juris and it is kept out of all AI processing. No text is taken from it and it is never indexed, so Sage, drafting and case summaries have nothing to draw on, and it never appears in the client portal.

Juris does not decide what is privileged. You do. A document nobody flags is treated like any other.

Flag one later and Juris deletes the text it already took, and the search entry with it. The file stays in the case.

The order matters. Text is read when a document arrives, so the flag at upload is the one that keeps it out entirely.

The most dangerous citation in your brief is the one that looks perfect.

Juris is case management and legal research in one place. Your matters, documents and deadlines live together, and Sage, the assistant inside Juris, works from your own case file.

Ask Sage about your case. The citations in its answer are checked against a case-law database and come back with a link, so you can open the judgment yourself. When a citation could not be checked, Juris tells you, in plain words.

Every draft is marked unverified until a lawyer signs off. Mark a document privileged as you upload it, and no AI ever reads it. Your firm's data is encrypted separately, isolated from every other firm, and never used to train AI.

October is Cyber Security Awareness Month in Canada, and this year's theme from Get Cyber Safe, the Government of Canada's awareness campaign, is "Your best defence is you."

Their point is practical. AI-generated scams and phishing emails can look more real than ever, and many incidents can be prevented with everyday habits. The three they name:

1. Check suspicious messages. Pause before you click, reply or share information. 2. Turn on multi-factor authentication. 3. Use strong passwords, and a password manager to keep them.

Pick one account that holds client or customer information and do all three on it this week.

A draft stays a draft until you say otherwise.

Alberta's law society puts it plainly: treat any Gen AI output as a first draft only.

Juris is built the same way. Export a Juris draft to PDF or Word before a lawyer has approved it and every page is stamped UNVERIFIED, with a banner saying it has not been reviewed by a lawyer and is not for filing or service until it is.

The stamp comes off when you approve the draft, or when you confirm at export that you have checked it yourself.

The big legal suites are built for a hundred lawyers, three practice groups, and a procurement committee that signs off on seat licenses. Somewhere in that sales deck is a slide about "enterprise scale."

You are one lawyer. Maybe two. You do not have a procurement committee. You have a filing due Thursday and a client who wants to know where their case stands.

What you actually need is smaller than what they are selling you. You need to know a citation is real before it goes in front of a judge. You need the deadline caught before it catches you. You need a draft you can trust enough to edit, not rewrite. You need one place to talk to your client without another app open.

None of that requires the suite. It requires the parts of the suite that matter, built for someone working alone or with one or two others, without the seat count and the onboarding calls built for a firm ten times your size.

Your evenings go to drafting. That is exactly where growing firms are putting AI.

In Clio's 2025 Legal Trends Report, U.S. firms with wide AI adoption were nearly three times more likely to report revenue growth than firms that had not adopted AI. Most firms that grew revenue with AI credited the same work: document generation, workflow and client communication.

That is where Juris starts. It drafts motions, facta, appeals and letters from your case file, and every authority in the draft is marked Verified, Verify or Unverified, so you know what to check before you file.

Try it free for 14 days: https://juris.kwatateam.com Clio figures: https://www.prnewswire.com/news-releases/the-science-behind-smarter-law-clios-2025-legal-trends-report-reveals-how-technology-is-rewiring-the-way-lawyers-work-302585725.html

Before you file, know which of your citations checked out.

Juris checks each citation against the official law for your jurisdiction, links you to the original when it finds it, and tells you plainly when it cannot confirm something. Every authority is marked Verified, Verify or Unverified, so you know exactly where to look twice.

Checking against official sources is live for Canada, the United States and the United Kingdom, with more coming.

An AI you can check, rather than one you have to trust.

Snap a receipt the moment you get it, wherever you are.

Kwata Books keeps a safe copy of every receipt, sorts it into CRA categories for you, and your books are ready when tax time comes.

Free to start: https://books.kwatateam.com

The Law Society of Alberta has already drafted your firm's AI rules. You just have to adapt them.

It is a free, four-page guide for your lawyers and staff, with the firm's AI use rules already written. Download it, fill in your firm's details, and adjust the rules to fit your practice.

If you have not got to this yet, you are in good company. In Clio's 2025 Legal Trends Report, 53% of U.S. legal professionals said their firm has no AI policy, or that they do not know of one.

While you adapt it, add two questions for every AI tool your people use: 1. Is our client information used to train it? 2. Can privileged documents stay out of it?

Use AI on the whole case file, without putting privilege at risk.

Most lawyers think it's one or the other. Sort out the privileged documents by hand before any tool sees the file, or don't use the tool.

In Juris you mark a document privileged once. From then on, Sage leaves it out of every answer, every summary and every draft it builds for that case, and works through everything else.

The speed on what you can share. The documents you can't stay yours. And every privilege mark is logged with who made it, so you can show it was handled.

You know your file too well. That is the problem.

By the fourth read you are not reading any more, you are recognising. The date you glanced past on the second read is the one you will glance past on the tenth. The other side finds it on their first.

A twenty-lawyer firm hands the file to someone who has never seen it. Solo practice has nobody to hand it to.

Juris is that person. Point it at the documents and it comes back with strengths, red flags, the contradictions across your own record, what is missing and who to get it from, and the opportunities you have not taken.

AI is right there and free until you hit a limit, so of course people are using it to pull a case or check a cite. Nobody is being reckless. That is just a Tuesday afternoon with a filing due.

The trouble is these tools will hand you a case that does not exist, and they will also hand you a real case that says something it never said, and both of those look exactly like good research right up until someone checks.

Lawyers have been sanctioned for it. Costs out of pocket, referrals to the law society, and a name sitting in a published judgment that does not go anywhere.

Nobody sets out to file a case that is not real. It just needs one busy week.

A lawyer filed two cases that ChatGPT invented. The court accepted she had not meant to mislead anyone. She still paid the other side's costs out of her own pocket, and the judgment carries her name.

The part worth reading twice: in the New York matter, counsel did check. He went back to the model and asked whether the cases were real, and it told him they were.

A model asked to confirm its own output will usually confirm it. Agreeing is the most plausible continuation of that conversation. It has no separate memory of what it made up.

The check takes about ninety seconds, and it is written up here.