Track 10 products’ prices for 5 days — who’s really cheaper?
Every retailer claims to be cheaper. Prove it: track the same 10 products at two real retailers or marketplaces for 5 days, build the dataset, and use AI to crunch the verdict — with numbers you’ve verified yourself.
Posted by The AI Internships
The work brief
- 01Pick 10 specific products (exact model/size/brand) and two places to compare (two marketplaces, online vs. a local shop, or a delivery app vs. a neighbourhood store).
- 02Record prices for all 10 on both platforms daily for 5 days — same time-ish each day. Note stock-outs and coupon effects.
- 03Build the CSV: date, product, platform, price, notes.
- 04Hand the CSV to AI: who wins overall, by category, and over the week? Verify its three headline numbers against the raw rows, then chart the most interesting pattern.
What you’ll produce4 deliverables
Submission standard
Submit your product list + method, the 100-row-ish CSV (10 products × 2 platforms × 5 days), findings, and a chart. Real price data has quirks — flat invented data fails. Include your AI workflow — tools, best prompts, and what you changed. Include at least one dated screenshot of each platform's price page for a tracked product, and make the prices match your CSV rows.
Your 10 products (exact specs), the two platforms, and how you recorded daily
Written responseRequiredThe price dataset as CSV: date, product, platform, price, notes
date, product, platform, price, notes — real price data drifts and has stock-outs/coupon effects; note them. Prices and dates must match your source screenshots.
CSV dataRequiredWho’s cheaper — overall, by category, and over time (with numbers)
Written responseRequiredA chart of your most interesting price pattern
Image uploadRequired
You’ll complete these inside your private workspace.
What you must submit as proof1 proof item · Required
This brief requires evidence an AI can’t fabricate.
Dated screenshots of the same product’s price page on each platform (one per platform — store/app page showing the price and the date)
Show the real store/app interface with a visible price and date for at least one product on each platform — must match rows in your CSV.
Image uploadRequired
Submissions without this evidence cannot be submitted.
Protect other people in your proof. Blur faces, names, phone numbers and email addresses before you upload, and refer to anyone you worked with by role or number ("Listener 1", "the stall owner"). Your proof is only ever used to check your work — it is never published, never appears on your certificate, and is never shown in your public portfolio.
How your work is evaluatedPass mark: 70/100
The passing benchmark is 70/100. Final score: Output 50% · AI process 30% · Evidence 20%. Required proof checks must also pass before certification.
Output criteria
Real collection
40%The dataset shows real multi-day tracking: price movements, stock-outs, honest notes.
Analysis
40%The verdict is numeric, segmented, and follows from the CSV.
Chart
20%The chart honestly shows the chosen pattern.
Required proof checks
Dated source ↔ CSV consistency
The dated store screenshots must match prices/dates in the CSV, and the chart must reconcile with the CSV. Flat data with no stock-outs or coupon quirks and no dated source holds certification for review.
How we grade your AI usage30% of your score
Using AI is the point — it’s the skill this certificate proves. You’ll answer three short questions about how you used it: what you asked, what was wrong with its first answer, and what you changed. Specific, honest answers score high. “I pasted the brief and submitted the answer” scores near zero.