01
Teams now include amnesiacs
An agent forgets everything between sessions. A human teammate forgets most things between meetings. The difference is one of degree, and pretending otherwise is how teams end up with their real state distributed across chat scrollback, one person's recollection, and a transcript nobody rereads.
Once you accept that every member of the team has unreliable memory, the design question changes: not "how do we remember?" but "where does state live so that the next session — anyone's next session — starts from it?"
02
The living handoff
The practice: a context file lives in the repository and is maintained like code. Decisions, open threads, current experiment state, and the reasoning behind reversals land there — compiled from meetings, chat, and sessions rather than dying in the app where they happened. Agent-facing context files sit beside it, so a coding agent launched cold gets the same orientation a new human collaborator would.
The file is a contract with the future: whoever picks the project up next — including you, tomorrow — starts from the same state, at the cost of a few minutes of writing at the boundary of each session.
03
Context hygiene
Long-running conversations rot: they accumulate stale assumptions and half-superseded plans. So sessions get refreshed deliberately, and the handoff document carries state across the boundary. The goal is that no single conversation is load-bearing. If a thread dies — a chat resets, a teammate leaves, an agent's context fills — the project state survives, because it never lived in the thread.
04
The same claim as the research
This is the recall-debt argument as team practice. An archive that grows without traversable paths is not memory — for a retrieval system or for a lab. The handoff document is the bridge object: the explicit path from last session's discovery to this session's starting point. Teams that maintain it compound. Teams that trust the scrollback repeat themselves.