The gap between what you meant to write and what you wrote
A planning board is a record of intent. A manuscript is a record of what actually happened. Put them side by side and the difference is not a mess. It is the single most useful thing you can see as an author: your frontier.
Every writing tool eventually grows a corkboard: a freeform canvas of cards you push around while you think. Ours is no different. What's different is what happens when you ask a second question about it: not "what's on the board?" but "how much of the board is real yet?"
Because a board is a record of intent. Loose cards, half-ideas, a connection you drew between two scenes that don't exist yet. And the manuscript is a record of what actually got written. Most tools keep those two things in separate rooms. The interesting stuff is in holding them up against each other.
Three states, not two
When you line the board up against the manuscript, every card sorts into one of three buckets:
- Done: the card names a scene that exists and is written. Intent, delivered.
- Seeded: the idea is present in the prose but hasn't become its own scene yet. A line, a mention, a plant. Real, but not yet load-bearing.
- Frontier: the card has no counterpart in the manuscript at all. This is what you meant to write and haven't.
That third bucket is the whole point. Your frontier is the answer to "what do I write next?", not a vague sense of being behind, but a concrete, finite list of the intent you've recorded and not yet discharged. It's the most motivating thing a planning view can show you, because it's the only one that's about the future.
Why an assistant should read the board, not just the prose
We recently gave the reading engine permission to see the board (read-only: skim the cards and connections, drill into one if it needs to). Not so it can plan for you. So it can tell the difference between "the story doesn't mention the coup" and "the story doesn't mention the coup yet, and you have a card that says it's coming."
Those are opposite notes. The first is a plot hole. The second is a to-do. An assistant that only reads the manuscript flattens them both into "missing." An assistant that reads your intent alongside your prose can hand the first back as a problem and the second back as a nudge: you meant to write this; want to now?
That's the quiet thesis: a planning board isn't scaffolding you throw away once the "real" writing starts. It's a running statement of intent, and the gap between it and the page is the most honest map of the work you have left.
Internal draft. The board and its read-only skim are built; this framing is being refined before it goes anywhere public.