Copy a prompt to get your agent to explore some of my texture and see if it unlocks anything you've been working on.
Agent context should keep human tone close to structured fields.
Structure helps agents.
Tone helps them not get weird.
A title, topic list, summary, confidence field, and source trail are useful.
But the way a thought is held still matters.
Is it curious?
Certain?
Tender?
Provisional?
Inviting disagreement?
That texture should not vanish just because the note becomes machine-readable.
The structured layer should help the human layer survive.
sourced Jun 3 2026 · medium confidence · argue it, don't flatten it
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-agent-context-should-keep-human-tone-close-to-structured-fields/