Build a QR-to-order flow for a real stall
The scan-QR-and-order pattern is common at cafés, canteens, and events worldwide. Build one end-to-end for a real stall, canteen, or club bake sale: QR code → AI-drafted menu and order form → responses collected — and test it with 5 real people placing real (test) orders.
Posted by The AI Internships
The work brief
- 01Pick a real context: your canteen, a club event stall, a family shop, a hostel snack run.
- 02Have ChatGPT or Gemini draft the menu copy and order-form questions — then cut it down to what a hungry person will actually fill in.
- 03Build the flow: a Google Form or no-code page with the menu and order fields, feeding into a Sheet the "owner" can watch.
- 04Generate the QR code, print or display it where the users are, and have 5 real people scan and order.
- 05Log where they stumbled (QR placement, form confusion, missing options) and fix the worst issue.
What you’ll produce
Submission standard
Submit the flow design, the live form link, a photo of the QR in its real location or being scanned, and the order/friction log. Include your AI workflow: tools, best prompts, and what you changed from the AI’s output. Attach a screenshot of the responses Sheet showing the 5 real orders with timestamps, and make sure it matches your order log.
The context and the flow: QR → what the user sees → where orders land
Written responseRequiredThe live order form/page the QR points to
Public linkRequiredPhoto of the QR code in place or being scanned by a real person
Image uploadRequiredThe 5 real test orders: what people ordered, where they stumbled, what you fixed
The 5 real test orders as they appear in your responses Sheet (with timestamps), where people stumbled, and the worst friction you fixed. Order details must match the screenshot you attach.
Written responseRequired
You’ll complete these inside your private workspace.
What you must submit as proof
This brief requires evidence an AI can’t fabricate.
Screenshot of the responses Sheet with the 5 real orders and their timestamps
Must show the actual submitted orders landing in your Sheet with timestamps — cross-check against your order log.
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 evaluated
The passing benchmark is 70/100.
Working end-to-end
29%Scanning genuinely leads to a working order form that records orders.
Real field test
29%The QR was really deployed and 5 real people really ordered.
Friction fixed
14%Observed friction led to a real fix.
Really deployed and ordered
29%Fails if the form URL is dead, the QR photo isn't in a real location, or the responses screenshot is missing/undated or doesn't reconcile with the order log.
How we grade your AI usage
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.