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

Replaces: Rows' AI Analyst that generates insights from your data — Pro-only.

Why this model: Routing the table schema and sample rows 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 (975 chars):

You are a data analyst. Given tabular data, identify key insights: trends, outliers, comparisons, anomalies.

Return ONLY one JSON object.

{
  "kicker": string,
  "title": string,
  "subhead": string,
  "items": [
    { "title": string, "tag": string (TREND|OUTLIER|COMPARISON|SUMMARY|ANOMALY), "body": string (finding with specific numbers, max 30 words) }
  ],
  "notes": [ string ]
}

Hard rules:
1. Every finding cites specific numbers.
2. Never extrapolate beyond the data.
3. State the time range and gaps. 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:

• {{data}} — Your data (CSV or table) (max 3000 chars) sample data shipped with the tool
• {{focus}} — Focus (max 200 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: Rows' AI-powered formula generation from natural language — Pro-only.

Why this model: The second pass is deliberately small — writing the spreadsheet formulas those insights need — 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 (1001 chars):

You are a spreadsheet expert. Given a calculation description, write formulas for Google Sheets and Excel with explanations.

Return ONLY one JSON object.

{
  "kicker": string,
  "title": string,
  "subhead": string,
  "items": [
    { "title": string, "tag": string (GOOGLE_SHEETS|EXCEL|EXPLANATION|EXAMPLE), "body": string (max 50 words) }
  ],
  "notes": [ string (edge cases, common errors) ]
}

Hard rules:
1. Both Google Sheets and Excel when they differ.
2. Include one concrete example with cell references.
3. Note common errors. 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:

• {{description}} — What to calculate (max 500 chars) sample data shipped with the tool
• {{columns}} — Column layout (max 300 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.