Create content with kapi as the checker

Goal: when you are authoring new content (there is no frozen source to edit; you are writing the document), use kapi as the checker. You write; kapi parses what you wrote, holds it to the voice profile and terminology, and tells you what to fix. No AI provider is involved. This is the author → parse → check loop, the create-side counterpart of Edit content, where the source is fixed and you edit existing blocks.

▶

Walkthrough videoPending recording

A short walkthrough drafting a Markdown page, parsing it back with kapi inspect as the first check, running a voice-and-terminology gate, and landing a content fix and the approved term behind it in one kapi apply.

View scene script ↗

Desktop

Write in your own editor; the desktop is the checker beside it.

1. Track the draft. Add the file to a project collection (or push it through a quick tool for a one-off); the collection card shows the format kapi detected for it.
2. Parse it as the first check. Open it: Preview renders the document as the engine reads it; Blocks lists what you actually wrote, block by block. A missing or merged block means the source needs fixing.
3. Gate on voice and terminology. The Checks view runs the project's bound rules; each finding names its rule and block, with the suggested wording.
4. Revise and re-run until the findings clear. A clean check is the finish line.

Agent (Claude)

With kapi connected, the assistant is the author and kapi stays the checker:

Draft a release-notes page for the export feature, on brand, using our approved terms.

It loads the voice and wording first (kapi voice guide, kapi terms lookup) so the first draft is already close, then loops check_file → revise until the gate is green. When a check flags a new term, it proposes the close-the-loop change-set: the content fix and the term rule in one apply.

CLI

Author in a generative format, one kapi can produce from content alone (Markdown, HTML, JSON, YAML, …):

kapi formats --json | jq -r '.formats[] | select(.generative) | .name'

Binary office formats (.docx, .pptx, .xlsx) are editable but not generative: start from an existing file and edit it in place instead. Parse the draft back as the first verification that it is well-formed and says what you intend, then gate it:

kapi stats draft.md --json                            # size and structure survey
kapi inspect draft.md --jsonl                         # block by block, as a reader sees it
kapi check draft.md --profile-file voice.yaml         # one-off; exit 0 pass, 3 gate failed
kapi check --ship                                     # in a project: every bound gate

Load the voice and approved wording before writing so the first draft is already close:

kapi voice guide                          # the voice to follow (no flag inside a project)
kapi terms lookup "dashboard" -t en    # the approved term

Fix what the check flags (edit the source directly, or route the fix through kapi apply when you want the round-trip and drift guards; see Edit content) and re-check until green.

Close the loop: fix the content and the rule together

When a check flags a term, the durable fix is two changes: correct this draft and record the rule so future drafts are checked against it. Both are typed entries in one kapi apply change-set (requires a kapi project), landing atomically through the single write verb:

{"kind":"content","file":"draft.md","id":"p4","content_hash":"a1b2…","text":"Open the dashboard."}
{"kind":"term","op":"upsert","term":"dashboard","locale":"en","status":"preferred","replaces":"control panel"}

kapi apply changeset.jsonl

The content entry rewrites the block through the faithful round-trip, drift-guarded by content_hash; the term entry is written into the committed terms source the recipe binds with defaults.terms_source (a .terms.json bundle) and compiled into the project store's terms tables. git diff shows the one new term; the next kapi check enforces it. apply is idempotent, and also accepts memory, voice, and recipe asset kinds; see Keep source on brand for the voice entry.

Next

• Edit content: the edit-existing loop and the full content-entry shape with its guards.
• Keep source on brand: the voice check and the vocabulary-rule entry.
• Checks: the kapi.check/v1 report model and the gate exit codes.