Which campaign actually worked?
Listen to this lesson
Nigerian voice narration
Fictional training case. At 'Naija Fit Gear' (fictional sportswear retailer), marketing lead Funmi ran four promotions last month: Instagram ads (₦40,000 spend, 18 sign-ups), a radio spot (₦60,000, 4 sign-ups), a WhatsApp broadcast (₦5,000, 22 sign-ups) and an influencer post (₦25,000, 9 sign-ups). Management wants to know which deserved the budget. Work through the example, identify the evidence needed and practise the method with cleared or synthetic inputs. Any additional figures in the explanation are separate practice examples, not claimed rows in a downloadable file.
Worked example
Funmi prompts: 'Here are my campaign results: spend and outcomes per channel in Naira. Rank channels by cost per result, separate vanity metrics from real outcomes, and recommend where to shift budget.' The AI calculates: Instagram ₦2,222/sign-up, radio ₦15,000/sign-up, WhatsApp ₦227/sign-up, influencer ₦2,778/sign-up. Funmi double-checks the WhatsApp math herself: ₦5,000 ÷ 22 = ₦227.27, confirming the AI's figure, and notes radio is clearly the weakest performer.
The method
Rank channels strictly by cost per real outcome (sign-ups, sales, enquiries) — never by likes or impressions, which are vanity metrics that don't pay bills. Always spot-check at least one of AI's calculated ratios yourself with a quick division, since an error in channel comparison could misdirect an entire budget.
Worked practice and common mistakes
Email at ₦3,000 for 15 sign-ups costs ₦200 per sign-up; Twitter at ₦30,000 for six costs ₦5,000; TikTok at ₦50,000 for twenty costs ₦2,500. Compare a common outcome, attribution window and customer quality. Low cost does not guarantee scaling: doubling a budget does not necessarily double results. If outcomes are zero, report no conversions and do not divide by zero. Test a controlled reallocation rather than promise a linear forecast.
Review before using the result
The historical table makes WhatsApp the lowest-cost source of sign-ups in this example. Funmi proposes a limited reallocation test, not a guarantee that double spend yields double customers. She checks attribution and customer quality before recommending a larger shift.
Your workplace practice
Use the recommended free assistant with this lesson's fictional example. Here are my campaign results: spend and outcomes per channel in Naira. Rank channels by cost per result, separate vanity metrics from real outcomes, and recommend where to shift budget. Keep a copy of the input and draft. Compare the result with the verification steps above, record any correction, and retain placeholders where evidence is missing. The expected result is a checked draft for human review, not an automatically approved decision. Course examples and practice responses are fictional; amounts, dates, rules and thresholds are not official guidance or supplier quotations.
Open Google Gemini (free tier) and paste this prompt there. Compares campaign spend tables and computes cost per result.
Here are my campaign results: spend and outcomes per channel in Naira. Rank channels by cost per result, separate vanity metrics from real outcomes, and recommend where to shift budget.
Why this tool: Compares campaign spend tables and computes cost per result.
Hit a free limit? Switch to ChatGPT or Gemini and continue — the prompt works in any assistant.