Work out why new running shoes felt wrong and find the old model second-hand with Gemini
- Posted
- by Kevin R. Kosar (Substack)
- Last checked
- Method:
- How we verify
Evidence: Described by posterThe person describes what happened in words, without screenshots or video.
Beginner-friendlyNo logins, payments or coding needed. Low risk: paste the prompt and you should get something useful.
Outcome
Kevin R. Kosar replaced a favourite pair of New Balance 880v11 running shoes with a similar-looking $100 Fresh Foam X 860v14, and two test runs left their lower back slightly sore. Kosar asked Gemini to compare the two. It explained that the new shoe is a little heavier and built for overpronators, while the 880v11 is a neutral shoe. Gemini then pointed to second-hand retailers, where Kosar bought two pairs of slightly used 880v11s; the new pair became around-the-house shoes.
Agent
Prompt Original prompt
Exact prompt as published in the source.
compare the New Balance Fresh Foam X 860v14 to the New Balance 880v11
Try this in:
Sends the Original prompt shown above. ChatGPT and Grok open with it filled in, and ChatGPT may send it straight away. Gemini opens empty, so we copy the prompt for you to paste. Every button also copies it.
Opens in a new tab. We don't see what you send.
These links are only a shortcut. We're not affiliated with OpenAI, Google or xAI, and your results may not match the source.
Optional stronger version
Our rewrite with extra checks. The poster didn't test it.
Before you start, ask me 1–3 short questions about anything important that's missing below. Keep them quick. Then do the task, checking in with me at the key points. Goal: Compare the product I used to have with the one I just bought, explain the differences that matter, and help me find the old one if it's better for me. What I can give you (ask for whatever's missing): - The old product I liked - The new product that feels wrong - What feels different Rules: - Compare the specs that matter for my complaint (for example weight, support type, fit). - Say plainly whether the difference could explain what I'm noticing. - If the old model is discontinued, suggest reputable places to buy it new or second-hand, and the closest current model. - Ask for my OK before you pay, book, send, submit or cancel anything. - Check facts that can change (prices, opening hours, dates, availability, rules) against the official source, and tell me anything you couldn't verify. - If pain continues, tell me to see a professional rather than relying on shoe changes. Output: A short side-by-side comparison, a verdict and where to buy. You'll know it worked when: I understand what changed and end up with a product that suits me. Before you finish: re-read my goal and constraints, check your answer against each one, and list anything you assumed or couldn't confirm.
Source
https://beveragesbooksandmore.substack.com/p/how-gemini-helped-me-figure-out-why
Related cases
- Send four AI agents to get real car insurance quotes: Gemini and ChatGPT got none, Claude and Muse got five eachRecreated promptEvidence: Described by poster
Thy Toeung needed to review their car insurance before their son turned 16. They made a data sheet listing every driver, vehicle and the cover they wanted, and asked Claude, ChatGPT, Gemini and Muse to act as their insurance-shopping agent and get real quotes from six reputable insurers. Gemini's auto-browse explained it couldn't use the websites and handed back a comparison table to fill in. ChatGPT took 2 hours and 279 messages across 12 attempts and got no quotes; Toeung believes sites such as Allstate, Nationwide and Liberty Mutual block AI agents. Claude ran for 3.3 hours and got 5 real quotes. Muse, on its free tier, used several sub-agents and got 5 quotes in about 20 minutes. Toeung switched insurer and got about twice the cover for around 40% of the previous price.
Claude, ChatGPT, Gemini, Muse · Shopping · Source date:
- Build a reusable Gemini shopping-assistant prompt with live product linksRecreated promptEvidence: Article or interview
A tech columnist asked Gemini 2.0 to write him a shopping-assistant prompt (role, workflow, follow-up questions and web search), loaded it into a chatbot wrapper with web browsing on, and fine-tuned it to return live product links. He says it delivered almost exactly what he needed in early tests, and lets him weight three key features, e.g. 'wet and dry', 'cheap' and 'rotary' for a men's shaver.
Gemini · Shopping · Source date:
- Find furniture on Facebook Marketplace for a new apartment with Meta's Muse, while Dots got the accounts locked (partial)Recreated promptEvidence: Article or interviewPartial
Scientific American's Mary Randolph was moving apartments and tested Meta's Muse (named Mark) and OpenAI's Dots (named Sam) for a week. Muse logged in to their Facebook account, searched Marketplace for couches, lamps and rugs, and could draft and send messages to sellers with their approval, managing the replies while they did other things. They now own a Muse-sourced dining table. When they gave Dots their Facebook login to do the same, Meta flagged it as a bot and temporarily locked their Instagram, Facebook and WhatsApp. Later, Muse pushed them seven times in three days to join Target's membership program and buy a lamp on sale.
Muse, ChatGPT Dots · Shopping · Source date: