Sayli runs one loop the whole time you are on a call. You do not see the machinery. You see a window that knows what is happening and helps when you ask. Here is the loop, in plain English.
It listens
A desktop app listens to the call through your system audio and your microphone. Both streams stay on your machine until you are in a session. Nothing dials into the meeting. The host sees no extra participant and no recording banner, on Windows, macOS, and Linux alike.
How the system audio reaches Sayli differs by operating system, and so does whether the Sayli window can be kept out of a screen capture you start yourself. What each platform delivers is the exact statement.
Because Sayli captures two channels, it can tell you apart from the other person. You are one voice. The call is the other. That separation is what makes the brief say who said what.
It transcribes
The words appear on Sayli's side as the call runs, a moment behind the speaker. Before any of that text reaches a language model, Sayli redacts the sensitive parts: card numbers, social security numbers, phone numbers, emails, IP addresses, and long account numbers. The model sees the conversation, not the secrets inside it.
PII is scrubbed before the text is stored, before it is shown, and before any model reads it. See Privacy and security for the full list and the reasoning.
It thinks
When you ask a question, Sayli gathers what fits it and reasons over all of it together:
The call so far, weighted to what was just said, so the answer fits the moment.
The most relevant passages from the docs and notes you gave Sayli, so the answer cites your facts.
When the question reaches back, the part of a past call that answers it.
Whatever you attached to this call.
When an answer needs something current, a short search built from what was just said. Privacy and security explains what that sends.
Connected tools are deliberately not in that mix during a call. A tool round trip costs more time than a live answer can afford, so they are switched off for the whole recording and run afterwards instead, on the brief and on questions you ask about a finished call.
The answer streams back as it is written, so you can start reading before it finishes. Ask in your words. Sayli answers in the language you set, even if the call is happening in another.
It remembers
When the call ends, Sayli writes the brief: a headline, a summary, your to-dos with owners, and a follow-up email. The full transcript sits under it, so any line can be checked against what was actually said.
Then the call joins your memory. Past conversations are chunked and indexed, so weeks later you can ask one question across everything you have discussed and get an answer grounded in what actually happened. Memory is the part that compounds. The product gets better the longer you use it.