Help

Getting started

SourceSecure is a browser extension for Chrome, Firefox and Safari. Install it from the Chrome Web Store for Chrome, Firefox Add-ons for Firefox or the Mac App Store for Safari. In Microsoft Edge, install it from the Chrome Web Store. A link cannot install an extension on its own, so you will land on the store's page and press its install button yourself. In Safari it arrives as a small Mac app: open it once, then switch SourceSecure on under Safari, Settings, Extensions.

Then click the SourceSecure icon in your browser's toolbar and choose Sign in. Use the email address your firm added, either through Google or through a link we email you. There is no password to remember or to lose.

If you had a chat site open before you installed it, or before an update, that tab needs a reload before it is protected. The popup says Refresh this tab when that is the case, so you are never left guessing.

Which sites it works on

ChatGPT, at chatgpt.com and chat.openai.com. Claude, at claude.ai. Microsoft Copilot, at copilot.com, www.copilot.com, copilot.microsoft.com, copilot.cloud.microsoft and m365.cloud.microsoft. Google Gemini, at gemini.google.com. Perplexity, at perplexity.ai and www.perplexity.ai. Grok, at grok.com. DeepSeek, at chat.deepseek.com. Meta AI, at meta.ai and www.meta.ai. Mistral, at chat.mistral.ai, which the app itself calls Vibe. NotebookLM, at notebook.google.com and notebooklm.google.com, which the app itself now calls Gemini Notebook.

Nowhere else. The extension cannot read any other page on its own, which is deliberate: it is the difference between a tool that watches a short list of chat sites and one that watches you. On a Guard Enterprise seat, when you pick a capture item from the SourceSecure right-click menu, it reads that one page, that once. If you are on a supported site and nothing seems to be happening, open the popup, which says whether it can see the page.

What happens when you press send

SourceSecure reads what you are about to send and looks for things that should not leave the firm: client names, account numbers, SINs and SSNs, card numbers, addresses, postal codes, phone numbers, email addresses, company names and places, plus any terms your firm has added.

If it finds nothing, your message goes as you typed it and you never see SourceSecure at all. That is the usual case.

If it finds something, the send pauses and a card opens listing what it found, with a redacted version beside what you typed. There are two buttons. Send redacted version sends the cleaned copy. Send as typed sends exactly what you wrote. The choice is yours, and it never sends anything until you press one of them.

The pause is a fraction of a second. If the check itself cannot finish, because the name model did not answer in time or the check failed, your message is held rather than sent unchecked, and a card says why: Check again tries once more, and Cancel send leaves your message in the box. Nothing is sent until it has been checked. A Guard Enterprise team head can change this for their firm, so that such a message is sent with a warning that it was not checked. If an attached file could not be read, the card opens and you decide.

It flagged something that is not sensitive

This happens, and it is the honest cost of catching names at all. A name is recognised by judgment rather than by a rule, and judgment goes wrong in both directions.

Each item in the card has its own buttons. Not this time leaves it out of the redaction for this message only. Never means stop flagging this exact value on this computer from now on. Always does the opposite and adds it to your watched terms so it is caught every time.

Everything you have silenced is counted in the settings (More settings in the popup, then Your data) under Items you marked not sensitive, with a Forget all button if you change your mind. That list lives on your computer, and your admin cannot see it.

It missed something

It will. SourceSecure is a safety net, not a guarantee, and the terms say so in those words. Account numbers and SINs are matched by shape, so an unusual format can slip past. Names and companies are recognised by a model, and a model is sometimes wrong.

Please tell us when it happens. Email support@sourcesecure.ca with the shape of what was missed rather than the real value. Every miss we hear about is a pattern we can add.

Attachments

Attach a file to a message on a supported site and SourceSecure reads it before it goes: PDFs, Word documents, spreadsheets, PowerPoint decks, plain text, and scanned images.

You see what it found page by page, with black boxes over it. Drag across anything else you want covered, or click a box to undo it. When you send, a redacted copy is attached in place of the original. The file on your own disk is never changed.

It also cleans what you cannot see. Author names, tracked changes that were deleted but never accepted, comment authors and document properties all travel inside an Office file, and they are removed from the copy it attaches.

What your firm can see

Not your messages. No message text and no document is ever stored by us or shown to your firm, so there is nothing for an admin to read even if they wanted to.

Once a day your browser sends a small report of counts: how many items were caught, of which kinds, how often a redacted version was sent, and how often each feature was used. Numbers only. There is no field in that report through which a sentence could travel.

On the team page an admin sees the firm's figures, or one person's. For each person they see what was caught and what that person did about it, with the detail masked on their computer first (like •••• 4242), and when they paused or switched off protection. Never the message. The masked form keeps a little of the detail, such as the last four digits of an account number or the initials of a name, so the record can be recognised.

Prompting tips, on Guard Pro, Guard 360 and Guard Enterprise seats

Guard Pro, Guard 360 and Guard Enterprise seats can suggest how to ask a better question. That needs a model we run rather than the one on your machine, so a redacted copy of the conversation is sent to us and passed to OpenAI, with the client details SourceSecure found already replaced by stand-ins such as [PERSON_1]. We store nothing from it, and it is sent to OpenAI with its storage option off.

Help me starts reading as soon as a tip appears, so it is ready when you click. Sharpen my prompt does the same when your pointer rests on it for a moment with something typed: that starts preparing it, which sends the redacted conversation then, before you click.

It is the switch for coaching. Open the popup and turn off Prompting tips. With it off, coaching sends nothing: no tips, no Help me, no Sharpen my prompt, no reply marks, and the rest of SourceSecure carries on exactly as before. Your firm still receives the counts and the masked record of what was caught. On a Guard Enterprise seat two things are separate, each sent only when you press it and redacted first: a question you put to Ask SourceSecure, which is sent whether tips are on or off, and Write background in Add notes, which is sent only while tips are on. Pausing SourceSecure stops all of them.

Tips are rare on purpose. The conversation is looked at every five messages, and most of the time there is nothing worth saying. The popup tells you when it last checked and what came of it, so that working and broken do not look the same from the outside.

Reply marks, on Guard 360 and Guard Enterprise seats

A Guard 360 seat checks each AI reply once it finishes and faintly underlines the places worth a second look: a decision made for you, an assumption, something stated too surely, or something that contradicts what your firm has told it. Point at an underline to see why. Ask about this puts a follow-up question in the message box for you to edit; nothing is ever sent for you. A reply with nothing worth saying gets nothing.

To check a reply, your message and the reply are sent the same way as tips, redacted first. When your message says something about your work or firm, a few short facts are kept in your vault, in this browser only, so later replies can be checked against them. Switch on Remember personal details too in the popup and it keeps lasting things about your own life as well, like an allergy; those are never offered to your firm, and are sent, redacted, only while the switch is on; switched off, the ones already kept stay on your computer until you delete them. When something changes, such as a move to a new tool, the newer fact replaces the old one and the old wording is kept beneath it; a fact you saved yourself is only replaced once the change comes up again, or when you choose Use this instead. Open the popup and choose See what your vault knows to see, change or delete any of them. Select text on a chat page to save it to your vault yourself.

A fact about your firm can be suggested for the firm's profile, which your admin keeps and every Guard 360 seat is checked against. Your admin sees what was suggested and by how many people, never by whom.

Your firm's Guard 360 seats share a number of checked replies each month. Past it, only the most important marks are shown until the 1st, the popup says so, and Check this reply fully beside the marks checks one reply for everything, up to 20 a day.

Turn off Mark AI replies in the popup to stop reply marks. Turning off prompting tips stops them too.

If your firm chose the two-week trial when it bought, your seat works as Guard 360 for two weeks from when you connect, and the popup counts the days. When it ends, SourceSecure says what it did for you and lets you ask your admin to keep it; your admin sees your name if you do. Your vault is paused, not deleted.

The Living Vault, on Guard Enterprise seats

A Guard Enterprise seat keeps a private memory of your work, encrypted in this browser: notes, files, saved replies, and short summaries of the chats and meetings you save. It is never uploaded or synced. Open it from the SourceSecure icon, or in the side panel beside your chat, which has two tabs, Ask and Settings.

On an AI chat page, beside the status pill in the corner, one pill reads Sharpen, Add notes and Ask. Add notes finds notes that bear on what you are writing; tick the ones you want. Write background sends the ticked notes, your draft and your own last few messages, redacted, through our server to OpenAI, to write a few sentences of background that you can change before adding. It is sent only when you press it, and only while prompting tips are on. Add the notes as they are puts them in with names as stand-ins and sends nothing to us.

Ask answers questions from your own vault. Your question, an overview of the vault and the passages found for it are sent redacted, only when you ask, and you can see what was sent under each answer. Asking works with prompting tips on or off. It stops while SourceSecure is paused: the box says “SourceSecure is paused. Resume it to ask.” and nothing is sent. Reading and searching your vault carry on, because they happen on your computer.

Saving a chat sends it once, redacted, to be summarised. A meeting transcript is sent to be summarised as soon as you add the file, with names and client details replaced by stand-ins first; the transcript itself stays on your computer, and the place you add it says so. Search, the people and company pages and the map are worked out on your computer.

Switching off prompting tips stops chat and meeting summaries and Write background. Switching off Use my Living Vault on the vault page stops Ask as well. Your firm cannot see your vault, or whether you use it.

For admins

Your team page is at sourcesecure.ca/admin, signed in with the address that bought. It has up to six tabs. Activity shows whether the firm is actually using it. People is where you add and remove members, choose which kind of seat each person has, and move somebody to another kind; adding somebody emails them straight away. Habits shows which habits the team is building. Report, with Guard 360 seats, is a monthly page on how the firm worked with AI, against the month before, ready to print. Settings is where you add terms everyone must always redact, such as the firm's own name or a client company, where you can require that the high risk kinds stay switched on for everybody, and, with Guard 360 seats, where you keep the firm's profile and approve what people suggest for it. Billing is how many seats of each kind, this month's reply marks, invoices and cancelling.

A change in seats is charged or credited for what is left of the month, on your next invoice. Prices are before tax: sales tax (GST/HST in Canada) is worked out from your firm's billing address and shown as its own line on every invoice, and if you gave a GST/HST number at checkout it is printed there too. Seats of a kind can only go down to the number of people who have that kind, so nobody is thrown off because a number changed.

Every firm has one owner: whoever bought, until they hand it on. The owner gets the monthly report, and is the one person who can delete the firm. On the People tab the owner can pass it to another admin with Make owner; if the owner has left the team, it passes to the admin who has been there longest. A firm with Guard Enterprise seats that pays monthly can switch to yearly on the Billing tab: it takes effect at the next bill, nothing is charged or credited before then, and it can be undone until it does.

If people ask to keep Guard 360 after their two weeks, you see who at the top of the team page, and SourceSecure tells you next time you use AI. Give them Guard 360 opens Billing with the seats added; once you have changed seats, move them on the People tab.

A term you add on the Settings tab reaches every browser in the firm with the next daily check, which means within a day rather than instantly. Removing one travels the same way.

For your IT team

The trust page sets out what runs on the computer, what is sent and to whom, what we never store, where the data lives, and how your IT team can check all of it themselves by watching the network. To report a security problem, see the security page.

The legal documents

Your firm agrees to the Terms of Service, the Data Processing Agreement and the Acceptable Use Policy when it buys, and everybody who joins a team agrees to the Acceptable Use Policy. The Privacy Policy says what is collected and why, and the subprocessors page lists every company that handles anything for us. Each page shows its version, so you can tell which wording your firm agreed to.

A firm that wants a signed order rather than the tick box at checkout can use the Order Form; write to support@sourcesecure.ca and we will send one filled in, with the DPA, to sign. Payment is by card either way. Every earlier version of each document is kept at its own address, and the Billing tab of your team page shows which versions your firm agreed to, when, and who ticked the box.

Two more documents sit beside them. Our incident and breach response policy says what we do if the security of your firm's information fails, and how fast you are told. And because admins can see what was caught on each person's browser and when they paused protection, there is an electronic monitoring policy template your firm can adapt to tell its people so; Ontario employers with 25 or more employees must have such a policy in writing.

If your firm cancels, its records are deleted 30 days after the subscription ends, as the terms and the DPA promise. Your admins are emailed when it is cancelled, when it ends, and a week before the records go, and the team page shows the date. Until then an admin can resubscribe from the team page and keep everything. Invoices stay with Stripe, as the law requires.

Your firm does not have to wait, or to write to us. Any admin can download everything we hold for the firm, as one file, from the Billing tab. The firm's owner can delete the firm there too, by typing its name: that cancels the subscription at once, with no refund for the time left, deletes the records straight away, and emails the admins that it was done. It cannot be undone.

Something is wrong

Nothing happens when I send. Open the popup. It will tell you if you are not signed in, if the subscription has lapsed, if the tab needs a reload, or if you are not on a supported site.

A payment did not go through. SourceSecure keeps working while the card is tried again. Your firm's admins are emailed, the team page says so, and the card can be updated from the Billing tab. Nothing is deleted while that is sorted out.

It says the subscription is not active. The subscription has ended: it was cancelled, or a payment failed and every retry did too. Protection stops for the whole team until an admin resubscribes from the team page, and the firm's records are kept for 30 days in case they do.

I cannot sign in. One person belongs to one team. If you already belong to another firm's team, signing in will say so by name. Otherwise check that the address your admin added is the one you are signing in with.

It is slow, or the model will not load. The settings (More settings in the popup, then Protection) have a Name detection line saying whether the model is ready. If it says name detection is unavailable, the pattern checks are still running, so account numbers and SINs are still being caught while names are not.

Anything else, write to support@sourcesecure.ca. Please say which site, which browser, and what you expected to happen. Do not paste a real client detail into the email; the shape of it is enough.

Getting in touch

Email support@sourcesecure.ca. SourceSecure is operated by JOLIVE Labs Inc.