Say-and-Go: Why Voice Inbox is Not an Assistant

When people see a voice interface, they often think of voice assistants like Siri. But Voice Inbox is fundamentally different. Siri functions as an agent you interact with—you speak to it and wait for its response.

Think of the typical back-and-forth: "Hey Siri, remind me to check the new API..." "What would you like to be reminded about?" "The API documentation!" "At what time?"

By the time you've satisfied the agent's requirements, your original train of thought has been derailed. This is the Say-and-Wait model.

Model	Flow	Result
Say-and-Wait	Speak → Wait → (Clarify?) → Wait → Confirm	Interrupted Thought
Say-and-Go	Speak → Go	Preserved Flow

The GTD Inbox for Your Voice

Say-and-Go is a model closer to the concept of an Inbox in Getting Things Done (GTD). In GTD, an inbox is a place to collect everything that has your attention, without judging or processing it in the moment.

Voice Inbox is the mouth of that funnel. You aren't talking to an assistant; you are talking to yourself.

There is no "What would you like to do?" There is only the recording. You dump your thoughts—messy, raw, and unedited—exactly as they occur. The goal is to get the idea out of your head and into a trusted system as quickly as possible so you can return to what you were doing.

Capture Now, Focus Later

Crucially, Voice Inbox is a capture tool, not an editor.

Phase	Activity	Environment	Goal
Capture	Voice or Text Entry	On the Go	Zero friction, get it out of your head
Process	Review & Edit	At Your Desk	Structure, refine, and organize

A mobile screen is a place for momentum, not for deep refinement. The expectation is that you capture your raw ideas on the go, and then later—when you are back at your desk with a larger screen and full focus—you perform the "post-processing." That is when you edit, organize, and turn those raw transcriptions into structured knowledge within your daily journal.

Read more about Manual Note Editing in our documentation.