Works where your team already types.
No new app to adopt. The assistant answers inside the platforms your team lives in, the messengers on their phones, your website, your own software. The same identity, permissions and numbered citations follow each person through every doorway.
One assistant, answering everywhere
Same identity · same permissions · same citations
Recognised from the first message.
Identity is what keeps channel answers safe. A linked colleague gets their own document access on every platform; an unknown sender gets the guest groups you chose, which are empty until you choose them. Nothing about a person's access depends on which doorway they used.
Linking is quiet: workspace platforms match colleagues by work email on their first message; a phone number registers in advance, or links itself with a one-time code from the web chat.
Register a phone number, username or email, recognised from message one
Workspace platforms match colleagues by their work email, silently
Self-service one-time codes (10-minute expiry) issued from the web chat
The same person, permissions and conversation history on every channel
Explicit guest groups only; nothing is open by default, anywhere
Text surfaces, by design.
A voice note or attachment receives a polite "please type your question" rather than a wrong answer. Every exchange, on every platform, lands on the same tamper-evident audit log, and every doorway stays optional, off until you open it.
Whatever the doorway, the conduct is the same: recognise the person, answer inside their permissions, cite the sources, log the exchange.
An explicit policy you choose, answer with the member's access, answer as guest, or stay silent
Nothing until a guest group is explicitly opened, on every channel alike
Each platform's own signature scheme verified; unsigned calls rejected before any processing
Several channels connect outward-only, nothing of yours is exposed
One assistant on every channel, answered
Which messaging platforms can the assistant answer on?
Every channel ships with every deployment: the workplace platforms your team lives in, the messengers on their phones, email, the web console, an embeddable website widget and a plain HTTP API for your own software. Each one is optional and off until you turn it on.
Does the team need to install a new app?
No, that is the point. The assistant lives where your team already types. Nobody adopts a new tool; they message the assistant the way they message a colleague.
How does it know who is writing to it?
Colleagues are recognised from their first message: work accounts match automatically, phones link with a pre-registered number or a one-time code. From then on the same identity, permissions and citations follow the person everywhere. The exact mechanics per platform are in the docs.
What can an unknown sender get out of it?
Nothing, until you decide otherwise. A sender the deployment cannot match is a guest, and guests see only the groups you explicitly opened to them, which are none by default, on every channel.
What about group chats?
Group chats follow an explicit policy you choose: answer with the member's own access, answer as guest, or stay silent. Nothing is inferred, and every exchange lands on the same audit record.
Is connecting Slack or WhatsApp safe for our side?
Yes. Nothing gets processed unless the platform itself proves the message really came from it, and several channels connect outward-only, exposing nothing of yours. The security page holds the full record if your IT lead wants it.
Message it like a colleague.
The demo answers on the web chat the moment you open it, the same brain that would answer in your Teams or WhatsApp.