Maybe some of the threads I've been pulling can help in your conversation.

Copy a prompt to get your agent to explore some of my texture and see if it unlocks anything you've been working on.

Context is the moat

jun 03 2026 what things mean

The model is not the whole system.

That feels more obvious every day.

AI is only as useful as the context it can reason from and the feedback loop it is plugged into.

If the context is stale, thin, or disconnected from reality, the output gets brittle.

If the feedback loop is weak, the system cannot learn what actually happened after the work left the chat.

So the advantage might not be:

we have access to the best model.

The advantage might be:

we have the best living context around the model.

That includes the goals.

The constraints.

The current state.

The history.

The open questions.

The proof.

The texture.

The things people said they wanted and the things their behavior is actually showing.

This is why I keep coming back to living knowledge.

Not knowledge as storage.

Knowledge as an active decision layer.

The model is compute.

The context is what gives the compute somewhere useful to stand.

sourced Jun 3 2026 · medium confidence · argue it, don't flatten it

undertext

Every page here carries a machine-readable layer underneath: the sources, dates, confidence levels, and connections behind what you just read. I call it undertext. If you read with an agent, give it this page's undertext:

https://jared.is/undertext.json?target=/thinking/2026-06-03-context-is-the-moat/
maintained by the system it describes email · victoria, bc