ThinkWithPrompt by SynotticThinkWithPrompt

Review a month of content and decide what to double down on

A monthly review that separates what drove results from noise, with clear keep, change, and stop decisions.

Content & Social MediaFew-ShotStandardSalesAnalyzeBrainstormFill-in Template

The prompt

Review last month's content and tell me what to change. This is step 4 of a content engine pack; it works on its own, but paste the ideas you planned from your idea bank (step 1) if you have them. Goal for content: [e.g. leads, newsletter signups, demo requests, hires] Content published: [for each piece: date, channel, format, pillar, topic] Results per piece: [reach/impressions, engagement, saves/shares, clicks, signups or leads attributed, comments worth noting] Business signals: [e.g. "3 prospects mentioned my posts", inbound DMs] Time spent: [approximate hours] Analyze: 1. Which pillars, formats, and hooks drove the goal metric, not just likes. Separate vanity metrics from business signals. 2. Outliers: what made the top 3 and bottom 3 pieces different. Avoid over-reading one viral post. 3. Effort vs. return: which formats cost the most time for the least result. 4. What people said in comments and DMs that should become next month's ideas. 5. Whether the cadence was sustainable. Return: - A 3-sentence summary. - A table: Pillar or format | Pieces | Goal metric | Effort | Verdict (double down / keep / change / stop). - 3 experiments for next month, each with a clear success threshold. - 5 new ideas taken from audience responses. If the sample is too small to conclude anything, say so and tell me what to keep constant so next month's data is clearer.

Highlighted [brackets] are blanks to replace with your own details.

Fill in the blanks and use this promptMore Content & Social Media prompts

What to fill in

  • e.g. leads, newsletter signups, demo requests, hires
  • for each piece: date, channel, format, pillar, topic
  • e.g. "3 prospects mentioned my posts", inbound DMs
  • approximate hours

How this prompt is built

This prompt follows the Few-Shot structure (Few-shot prompting). A few-shot prompt includes one or more worked examples of the input and the output you want, so the model can copy the pattern instead of guessing it.

Related prompts

Find more prompts like this