Occasional
You paste notes into an assistant when a conversation matters. The relay makes the useful context available before you remember to move it.
A new context layer
Your agent knows what you tell it. A relay lets it know what you are doing.
A context relay is a live channel that carries the context of your work to your agent, so the conversation you are in and the thing you just said do not have to be explained again by hand.
01 / Closing the gap
The missing layer is not intelligence. It is continuity.
Your assistant can reason over almost anything you give it. The problem is the giving.
A useful exchange happens in a call, at a desk, or while walking between rooms. Later, you select the relevant passage, copy it, switch applications, add a caption, and ask the question you wanted to ask in the first place.
The relay removes that transfer step. It does not ask you to develop a new habit. It takes friction out of the habit you already have.
Ritual
You already do this every day. The relay removes the repeated selection, labeling, and handoff that have become invisible overhead.
On demand
You start every session. The relay gives your agent a bounded, current view only when you choose to capture and connect it.
02 / The keystroke argument
Context should not need to be retyped to become usable.
A short conversation can contain hundreds of words. Moving it into an agent should not require hundreds of keystrokes and a six-step detour.
The saving is not just typing. It is the attention spent deciding what to select, where to put it, and how to explain what it is. That small interruption is repeated every time the physical world needs to meet the model.
Without a relay
- Select the relevant passage.
- Copy it.
- Switch to the assistant.
- Paste it.
- Explain who said what.
- Write and send the actual request.
6 transfer actions · hundreds of characters moved by hand
With a relay
The context is already there.
0 copy-paste actions · 0 transfer keystrokes
Next
A relay is useful when it stays on your side of the table.
See the work it supports, and the boundary that keeps augmentation honest.