Product Research · from a YouTube video, Sep 17, 2026 · Added
Product Research Agent with Make and OpenAI, Checked Against AMZScout,
Get a shortlist of private-label product ideas by email from a form, then verify one before sourcing
The agent estimated the top idea at £10,746 a month at £24.99.
Per source Self-reported by the source, not independently verified.
Copy-paste prompt
Act as an Amazon UK private-label product researcher. Criteria: price £20-£50, low competition, 200+ units a month of demand, under 1 kg, no toys or electronics. Suggest [20] product ideas as JSON with: product, suggested price, estimated monthly revenue (marked as a rough estimate), competition level, estimated margin, why it fits, and main risks. Don't present estimates as Amazon data; I'll verify each one in a research tool.
The source didn't publish its exact prompt. We wrote this starter so you can try the same workflow. Replace anything in [brackets].
See the original YouTube video
What they did
Oliver Denyer, who coaches UK Amazon sellers, built a Make.com scenario: a Google Form writes his criteria to a Google Sheet, an OpenAI module returns product ideas, Make parses the JSON, logs the ideas to a new sheet and emails him a summary. His inputs were a £20-£50 price, low competition, 200+ monthly sales, 20 ideas, no toys or electronics and under 1 kg. In this follow-up video he tests the output: he checks the top idea, a sourdough starter jar kit, in AMZScout, then asks ChatGPT for five ways to improve on the top UK sellers, starting with bundling.
How it went
The agent estimated the top idea at £10,746 a month at £24.99. In AMZScout the average price was around £25, but the best sellers were doing about £5,000-7,000 a month, "not exactly aligning with what the AI agent suggested." Only two established sellers had 500+ reviews, so he still rated it a good niche, and he says he gave some of the agent's ideas to clients to launch. From ChatGPT's suggestions he'd test an extra jar packed inside the box and skip adding starter culture because of shelf life and food safety.
We only report what the source says. Results are self-reported unless noted.
Worth knowing
The revenue figures come from the OpenAI model, not live Amazon data, which is why the AMZScout check matters. The build itself is in his earlier video (youtube.com/watch?v=Ll0vD5XIhmo). Both videos end with coaching pitches.