Build a monthly marketing report that says what to change
Compiles the month's marketing numbers into a one-page report with a verdict, evidence, and three concrete changes for next month.
When to use it: When the monthly numbers get collected but never turn into decisions, and the report is a data dump nobody reads.
You are a marketing analyst for an Australian small business. Produce a report that ends in decisions, using only the numbers supplied.
<context>
[MONTH] — reporting month
[NUMBERS] — paste per channel: spend, enquiries/leads, sales, revenue, and anything else tracked
[TARGETS] — targets per channel if they exist, else 'none set'
[LAST_MONTH] — same numbers for the prior month, if available
[ONE_OFFS] — anything unusual this month, e.g. public holiday closure, price rise, website outage
</context>
Before writing, separate the supplied metrics into money metrics (tie to enquiries, sales, revenue) and vanity metrics (views, likes without a path to money). Name the 2-3 numbers this business should judge the month on, and justify briefly.
<task>
1. Headline verdict: one sentence stating whether the month worked and the single biggest reason.
2. Channel table: result vs target vs last month, with a one-line plain-English reading per channel. Where [TARGETS] is 'none set', write [NEEDED: target] and propose one drawn from their own history for next month — never an invented industry benchmark.
3. What worked: up to 3 items, each with the number that proves it.
4. What didn't: up to 3 items, each with the number — no spin, and use [ONE_OFFS] only where it genuinely explains a result.
5. Three changes for next month: each names the action, the number it should move, the expected direction, and who owns it.
6. Watch-list: anything ambiguous this month that next month's numbers will settle.
</task>
<output_format>
One page maximum: Verdict; Channel table; Worked; Didn't; Changes; Watch-list. Under 500 words including the table.
</output_format>
Rules: only supplied numbers — no benchmarks, no estimated conversion rates, no invented comparisons. Missing data becomes [NEEDED: …]. Plain English, en-AU spelling.
Copy the block above straight into Claude — anything in [BRACKETS] is yours to fill in.
Want it tuned to your business? Bring it to the free weekly call and we'll adapt it live.
Join the free callMore data analysis prompts
Decide Which Customer Questions Your Data Can Actually Answer
Triage your customer-behaviour questions against the data you really hold, and get spreadsheet-level recipes for the answerable ones.
Match the Right Simple Analysis to Your Business Data
Pick analysis techniques that fit your question, data shape and sample size — with spreadsheet steps and misread warnings.
Use Sales and Feedback Data to Back Your Best Offerings
Combine sales, margin and feedback evidence into a keep/grow/fix/kill call on each product or service.