The same file and the same AI — only the prompt changes. Compare the weak prompt with the engineered one, and see how the results differ. (Outputs below are the actual results from the MapleStream sample files.)
File: sample-customer-reviews.csv (review_id, month, rating 1–5, review_text)
Are these reviews good or bad?
No numbers, no themes, no idea which feature to fix. Nothing the product team can route or act on.
You are a customer-insight analyst for MapleStream, a subscription app for home cooks. I've uploaded a file of reviews (review_id, month, rating 1-5, review_text). Task: analyze OVERALL sentiment and the specific aspects customers mention. 1. Share of reviews positive / neutral / negative. 2. Main aspects (recipes, app, shipping, price, service, quality): how often, mostly + or -, and one short quote (under 15 words). 3. Top 3 complaints and top 2 praises. 4. One recommended action. Use only the file. Do not invent quotes or numbers. Plain English, under one page.
| Aspect | Direction | Example |
|---|---|---|
| Shipping | Mostly − | “Delivery took almost three weeks.” |
| The app | Negative | “The app is confusing and crashes.” |
| Price | Negative | “Overpriced for what you get.” |
| Service | Mixed | “Support solved my problem right away.” |
| Quality | Mixed | “Broke after two weeks of normal use.” |
Want machine-readable output instead? Ask for a table, one row per review:
You are a sentiment classifier for MapleStream. For each review in the file, classify OVERALL sentiment as Positive, Negative, or Mixed, and extract the aspects mentioned with a sentiment for each. Return a table: review_id, overall_sentiment, aspects (a list of aspect: sentiment). Use only the file's data.
| review_id | overall | aspects |
|---|---|---|
| R001 | Negative | shipping: negative |
| R006 | Positive | service: positive |
| R034 | Positive | shipping: positive, app: positive, service: positive |
| R035 | Negative | price: negative, app: negative |
File: sample-monthly-metrics.csv (month, marketing_spend, new_customers, revenue, churn_rate_pct, customer_satisfaction)
Look at this data and tell me what drives revenue.
Confident and wrong: it reads a correlation as cause. Both simply trend upward over two years.
You are a data analyst for MapleStream. I've uploaded 24 months of metrics (month, marketing_spend, new_customers, revenue, churn_rate_pct, customer_satisfaction). Task: examine which metrics move together. Do NOT assume anything causes anything. 1. Correlation for each pair of numeric metrics. 2. The 5 strongest: name both, value to 2 decimals, positive or negative. 3. For each, say if it looks real or likely just a shared time trend (these numbers trend over 2 years). 4. State that correlation is not causation; flag any pair where a causal reading is unjustified. 5. One relationship worth testing, and how to test it. Use only the file. Round to 2 decimals.
| Pair | r | Reading |
|---|---|---|
| marketing_spend & revenue | +0.92 | Likely a shared time trend |
| marketing_spend & new_customers | +0.84 | Plausibly real |
| new_customers & revenue | +0.81 | Part real, part trend |
| satisfaction & churn_rate_pct | −0.40 | Plausibly real |
| satisfaction & revenue | +0.14 | Essentially unrelated |
Do NOT assume causation, plus “real vs shared trend” — turns a confident, misleading answer into an honest one. Same data, same model. The prompt is the whole difference.
How to use this: read the weak prompt and its result, then the engineered prompt and its result. Then open the file in Claude and try the good prompts yourself — the outputs you get should match what you see here. Results generated from the MapleStream sample files (24 months of metrics; 36 reviews). The bar ratings are a simple quality read, not exact scores.