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 preserve uncertainty through every summary.
Summaries are useful.
They are also dangerous.
They can turn a question into a claim.
They can turn a possible route into a conclusion.
They can make unfinished thinking sound more confident than it is.
The agent-readable layer should resist that.
It should carry the uncertainty forward, not polish it away.
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-preserve-uncertainty-through-every-summary/