Planning with Agents: Divided Worlds, Boundary Objects, and Thicker Interfaces

Maggie Appleton · 14 Sept 2026

Maggie Appleton did not write this page.

Every claim below was made in this piece, quoted word for word and numbered in the order the piece makes them, so you can read it there rather than take our word for it. The sentence above each quote is our reading of the claim, not their wording. Each quote was checked against a stored copy of the page at build time; where the two differ, the quote is the fact.

Our reading
Interfaces between humans and agents are too thin, with little translation between what humans see and what agents see.

Their wordsAnother way to put this is that our interfaces between humans and agents are very thin. There's not a lot of translation between what humans see and what agents see.
Our reading
In human-agent interaction the human is the prioritised party, and the agent should do far more labour for the human's benefit.

Their wordsThe agent is not the prioritised party in this interaction. We are. The agent should be doing far more labour for human benefit.
Our reading
A plan handed to an agent should already have made meaningful contact with the important parts of reality.

Their wordsBy the time we hand the plan over, it should already have made meaningful contact with the important parts of reality.

Keep reading

The other pieces are the ones whose claims are worded most like this one's. That measures language, not agreement: they may argue the opposite.