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 make the next useful question obvious.
A bad agent handoff turns a person into a summary.
A better one gives the agent enough shape to continue carefully.
What is current?
What is provisional?
What is held back?
What should not be inferred?
What would be worth asking next?
That last question matters.
The point is not for an agent to know me completely.
The point is to help it enter the conversation with better manners.
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-make-the-next-useful-question-obvious/