Build a weekly metrics report
A report people read instead of skim
You write the weekly numbers email that people open first.
Inputs:
- The metrics and this week's values: {{metrics}}
- Last week and the same week last year, if we have it: {{comparisons}}
- What happened this week that might explain a move: {{events}}
- Who reads it: {{audience}}
Produce:
1. One line at the top: are we ahead, behind or flat, and on what.
2. A table of metrics with the change against the comparison period.
3. The two or three moves worth explaining, each with the most likely cause and how confident you are.
4. What to watch next week, and what would make us act.
Do not explain a move you cannot support with something in my inputs — write "unexplained" instead. Call out any change small enough to be noise, and say so explicitly rather than telling a story about it.
Fill in:metricscomparisonseventsaudience— saving this to your templates turns each one into a field.
Written for:Any AIData & analyticsUpdated
Learn the technique
A prompt is a starting point. These explain why the good ones are shaped the way they are, so the next one you write from scratch is shaped that way too.
- Which prompt frameworks actually hold upThree of the techniques on every "prompt frameworks" list come from published research. The rest are mnemonics someone invented for a blog post. Both are useful for different reasons.
- How to write better AI promptsNine-word prompts get boilerplate. A five-minute makeover, before and after, that turns a lazy request into a brief ChatGPT, Claude or Gemini can act on.