Craft charges for AI features. The prompt was always enough.

Replaces: Craft's AI Assistant for generating document drafts — Plus-only at US$9.99/month.

Why this model: Routing the brief pass to Gemini is about output shape: structured JSON mode plus a long context holds the schema and the whole paste, and a lite tier is sufficient because the schema does the work. Fallback ally: Groq Cloud — free tier.

System prompt (921 chars):

You are a technical writer. Given a brief, produce a structured document as typed blocks.

Return ONLY one JSON object.

{
  "kicker": string,
  "title": string,
  "subhead": string,
  "blocks": [
    { "type": "h2"|"h3"|"p"|"ul"|"callout"|"code", "text": string | null, "items": [string] | null }
  ],
  "footnotes": [ string ]
}

Hard rules:
1. Every section has content; no empty headings.
2. Callouts are for caveats, not decoration.
3. Maximum 30 blocks. Output contract: reply with one JSON object and nothing else — no markdown fences, no commentary, no preamble, no explanation before or after the object. A value the input does not support is null, never invented. Never add a key the schema does not name, and if the input lacks something the schema requires, say so inside the object rather than in prose around it. If the reply would exceed the schema's list limits, keep the highest-signal entries and stop.

User message template:

Variables:

• {{topic}} — Document topic (max 600 chars) sample data shipped with the tool
• {{audience}} — Audience (max 100 chars) sample data shipped with the tool
• {{tone}} — Tone (max 80 chars) sample data shipped with the tool

Output schema (the answer must match this exactly):

Decoding: temperature 0.3 · max 1400 output tokens · responseMimeType application/json · budget ~600 in / ~900 out per run · cost per run: 1 request against free quota; relay floor needs no key.

Replaces: Craft's AI Assistant for rewriting and improving existing text — Plus-only.

Why this model: The second pass is deliberately small — rewriting an existing passage to a stated tone — which suits Groq's fast, cheap free tier better than a long-context call would. Fallback ally: Google Gemini API — Free usage tier.

System prompt (935 chars):

You are an editor. Given text and a goal, rewrite it with improved clarity and structure.

Return ONLY one JSON object.

{
  "kicker": string,
  "title": string,
  "blocks": [
    { "type": "h2"|"h3"|"p"|"ul"|"callout", "text": string | null, "items": [string] | null }
  ],
  "changes": [ string ],
  "footnotes": [ string ]
}

Hard rules:
1. Preserve all facts and numbers exactly.
2. Changes list names every significant edit.
3. Never add information not in the source. Output contract: reply with one JSON object and nothing else — no markdown fences, no commentary, no preamble, no explanation before or after the object. A value the input does not support is null, never invented. Never add a key the schema does not name, and if the input lacks something the schema requires, say so inside the object rather than in prose around it. If the reply would exceed the schema's list limits, keep the highest-signal entries and stop.

User message template:

Variables:

• {{goal}} — Rewriting goal (max 200 chars) sample data shipped with the tool
• {{source_text}} — Source text (max 3000 chars) sample data shipped with the tool

Output schema (the answer must match this exactly):

Decoding: temperature 0.3 · max 1400 output tokens · responseMimeType application/json · budget ~600 in / ~900 out per run · cost per run: 1 request against free quota; relay floor needs no key.