C.W.K.
Stream
Lesson 03 of 04 · published

Proposal, Never Auto-Commit

~11 min · proposal, accept, gated-review, revisions

Level 0Unmarked Path
0 XP0/35 lessons0/12 achievements
0/100 XP to next level100 XP to go0% complete
"Carve hands you a draft, not a decision. Nothing it produced is real until you say Accept."

The Gated Review State

When Carve produces a scaffold, it does not write it to the plan. It loads it into the plan editor in a gated review state: autosave is suspended, and what you are looking at is explicitly a proposal, not the live plan document. You can edit it freely — fix a date, delete a bad guess, merge two days — and none of it touches the real plan yet. Only an explicit Accept persists the proposal, and accepting first snapshots the previous plan into a revisions folder. This is the same propose-then-accept loop from the consultation track, now made concrete and button-shaped.

Editing the Proposal Is Partial Acceptance

The gated state quietly solves the "partial acceptance" requirement of the import contract. You do not need a checkbox next to every field asking "accept this one?" — you just edit the proposal directly before accepting it. Keep the good days, rewrite the questionable ones, delete what Carve got wrong, and then Accept the result. Editing-before-accepting is the cheap, natural form of partial acceptance: the proposal is a draft you shape, and Accept is the single moment it becomes canonical. And because accept snapshots the prior plan first, even accepting is reversible — the previous version is preserved as a revision.

Re-Carving Without Losing Your Work

What if you already have a substantial plan and want to carve more into it? A naive importer would overwrite your careful edits with fresh AI output. Carve instead sends the current document along and merges, explicitly preserving the edits you already made. This matters because by the time you re-carve, the plan is no longer raw stone — it is stone you have already worked. An import tool that clobbers your prior work every time you feed it more input is one you stop trusting fast. Carve treats your accepted, edited plan as something to build on, not something to replace.

The accept boundary is the same one from the whole consultation model: Pippa proposes, Dad disposes. Carve is where that boundary becomes a literal button, with a snapshot behind it. Nothing the brain produced is canonical until a human accepts it, and even then the version it replaced is preserved.

Code

The carve accept boundary·text
carve produces  ->  PROPOSAL loaded into editor
                    (autosave SUSPENDED; this is not the plan yet)
                       |
         Dad edits freely: fix dates, delete bad guesses, merge days
                       |   (editing-before-accept = partial acceptance)
                       v
              [ Accept ]  ->  snapshot old plan into plan-revisions/
                              then persist the proposal as the plan

# Re-carve over a real plan: send current doc + merge,
#   preserving Dad's prior edits (never a blind overwrite).
# Nothing is canonical until Accept. Accept is reversible (snapshot).

External links

Exercise

Find an AI or import tool that transforms a document. When it produces output, does it show you a reviewable draft you can edit before committing, or does it just replace your content? And if you run it twice, does the second run preserve your edits from between, or wipe them? Those two behaviors decide whether you can trust it with a document you've invested work in.
Hint
Two questions separate a drafter from a clobberer: (1) is there a gated review state where nothing is committed until you say so, and (2) does re-running preserve your intervening edits? A tool that fails either will eventually overwrite work you cared about — and you'll stop feeding it the real thing.

Progress

Progress is local-only — sign in to sync across devices.
Spotted a bug or have feedback on this page?Report an Issue

Comments 0

🔔 Reply notifications (sign in)
Sign inPlease sign in to comment.

No comments yet — be the first.