All micro-internships
Micro-internship brief ≈8h across 2 days — shop trips + analysisno-codeIndia edition

Same basket, three shops: who really costs less?

Everyone in your house has an opinion about where groceries are cheapest. Price a real 15-item family basket at three genuinely different outlets — kirana, supermarket, online (with delivery fees) — then let AI crunch the comparison and settle it with a verified true-cost verdict.

Business AnalysisUX Design

Posted by The AI Internships

The work brief

  1. 01Build the basket from what your family actually buys: 15 items with exact brands and sizes (Aashirvaad atta 5kg, not "flour").
  2. 02Price all 15 at three outlets: your local kirana (ask or check price tags), a supermarket (DMart/More), and online (Blinkit/JioMart/BigBasket — include delivery and handling fees).
  3. 03Photograph or screenshot evidence from at least two of the three outlets.
  4. 04Paste your priced CSV into AI to compute totals, category winners, and per-outlet patterns — then recheck every total by hand, because AI fumbles arithmetic.
  5. 05Deliver the verdict: overall winner, category winners, and when convenience is actually worth the premium.

What you’ll produce

3 deliverables

Submission standard

Submit the priced basket as CSV, your price evidence, and the verdict with real totals. Include your AI workflow: your prompts and any totals you had to correct. Your price photos must show the store name or app UI and a date, and the visible prices must match the matching rows in your CSV.

  • The basket as CSV: item (brand+size), kirana price, supermarket price, online price + fees

    Paste comma-separated data with one header row and one record per line. Use consistent column names and remove private information.

    CSV dataRequired

  • Price evidence: photos/screenshots from at least 2 outlets (one image)

    Photos/screenshots from at least 2 outlets that clearly show the store name or app UI, a date, and specific item price tags/cart lines that appear in your CSV.

    Image uploadRequired

  • The verdict: true totals, category patterns, and when each outlet wins

    Written responseRequired

You’ll complete these inside your private workspace.

How your work is evaluated

The passing benchmark is 70/100.

Real price collection

29%

Prices are real, current, exact-item-matched, with fees included online.

Comparison rigor

29%

Same brand+size across outlets; substitutions honestly flagged.

Useful verdict

14%

The verdict is numeric and genuinely useful to the family.

Prices match the evidence

29%

The prices visible in the photos (with store/app and date shown) match the corresponding rows in the CSV. Invented prices, missing store identity, or photo numbers that don't reconcile with the CSV = fail regardless of how clean the verdict reads.

How we grade your AI usage

30% 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.