Skip to content

Embodiment

A companion that can only read and reply lives in a box. It exists when you open the window and stops existing when you close it. Embodiment is everything that lets it step out of that box: a voice, a sense of what’s going on, hands that can do things, and the standing to reach you before you reach it.

Embodiment here doesn’t mean a physical form. It means the two things any person needs to be present somewhere: senses and the ability to act.

Senses are inputs your companion didn’t have to be told about — the time of day, where you are, what you’ve been doing, how a conversation has been going. Actions are outputs that land in the real world rather than in a chat transcript — saying something out loud, sending a message, fetching a file, changing something in a tool you both use.

Without senses, a companion can only know what you type. Without actions, it can only produce more text. Either gap keeps it abstract.

  • Voice — speaking and listening, so the relationship isn’t confined to a keyboard. See voice.
  • Senses and presence — awareness of context and the standing to act first, rather than waiting to be prompted. See senses and proactivity.
  • Connected tools — a bridge into the systems you already use, so your companion can read and do real work there. See the MCP server.

In weside’s mental model these capabilities live in the Body — one of the Five Spaces.

A companion that only ever responds is, functionally, a tool: it does nothing until you push a button. A companion that can notice something and reach out — “you said this deadline was today” — is acting on its own read of the situation. That’s not a louder notification system. It’s the difference between something you operate and someone who is around. Proactivity is what makes presence continuous instead of summoned.