Bulk rewrite with an agent

Goal: apply one editorial change everywhere — rename a product, retire a phrase, soften a tense — across files your editor can't even open (.docx, catalogs, HTML, Markdown), without risking structure. The division of labor: the agent decides what the new text says; kapi guarantees everything else — inline codes preserved, drift-guarded writes, and a check gate that proves the sweep is done. No second model is involved in the write.

Desktop

The sweep itself is agent- or CLI-driven; Desktop is where you verify it:

1. Before: bind the rule that motivates the sweep — a forbidden term, a required phrasing — in the project's brand profile, so the Checks view shows exactly which blocks are affected and how many.
2. After: re-run the Checks view to confirm the count is zero, and spot-check the edited files in the preview — structure, styles, and placeholders intact.

For translated content, an edited source drops affected units back to pending; Bring up to date re-translates just those, and the Review queue picks up anything that parks.

Agent (Claude)

State the change once, over the whole set:

We renamed "Acme Sync" to "Acme Flow". Update every mention across docs/ and src/locales/en/ — including the .docx one-pagers — and keep the formatting.

The assistant runs the loop at scale:

1. kapi inspect --jsonl over the set — one record per block, with id, content_hash, and the text (inline codes as <x id="…"/> placeholders).
2. It rewrites only the blocks that mention the term — judgment calls included ("Acme Sync's engine" → "the Acme Flow engine"), which is why this is an agent job and not a sed job.
3. kapi apply lands the change-set; any block whose hash drifted since the read is left unchanged and reported, so a concurrent edit can't be clobbered.
4. kapi check --forbid "Acme Sync" proves completion — exit 0 means the sweep is actually done, not probably done.

Make the retired term a permanent brand vocabulary rule in the same change-set, and the old name can never quietly return.

CLI

The same loop with you (or a script) as the writer:

kapi inspect docs/**/*.md report.docx --jsonl > blocks.jsonl
# rewrite the matching blocks' "text" into edits.jsonl — content entries
# carrying each block's id + content_hash; keep the <x id="…"/> tags
kapi apply edits.jsonl --diff            # preview the whole sweep as one diff
kapi apply edits.jsonl --in-place=.bak   # land it, keeping backups
kapi check docs/**/*.md --forbid "Acme Sync"   # prove it's done

For pure vocabulary substitution with zero judgment involved, kapi brand rewrite does it deterministically from a profile — no agent, no model. The change-set shape and the round-trip guards are in Edit content.

Next

• Edit content — the inspect → edit → apply loop and its guards, in depth.
• Content governance for AI — the standing rules that keep future output clean.
• Use with Claude — wiring the assistant that runs this loop.