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 should be alive, not stored

jun 03 2026 what things mean

Stored context is easy to overvalue.

It feels responsible.

The notes are there.

The documents exist.

The decisions were captured somewhere.

But context that sits still starts to decay.

The work changes.

The goals shift.

New signal arrives.

Old assumptions get weaker.

People forget why a decision felt true.

That is why I keep coming back to living context.

Useful context should participate in the work.

It should help decide what matters now.

It should notice when something new changes the shape of an older idea.

It should make a decision easier to revisit without making everything feel unstable.

It should help an agent reason from the current map, not just the archive.

That is a different job than storage.

Storage preserves.

Living context interprets.

It keeps the past close enough to be useful, but not so fixed that it traps the present.

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-should-be-alive-not-stored/
related notes
maintained by the system it describes email · victoria, bc