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 route suggestions separate from evidence strength.
A route can be useful.
That does not make it proven.
A source can be strong.
That does not make every interpretation strong.
This is one of the places where agent-readable context can help.
It can say:
this source is solid;
this route is promising;
this conclusion is still soft.
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-route-suggestions-separate-from-evidence-strength/