She built a Claude shopping assistant to stop buying cheap junk
TL;DR
Claude became her anti-Amazon filter: Nicole Ruiz feeds Claude a trusted vendor list and rules like "avoid trendy direct-to-consumer brands," then asks for recommendations that surface price, materials, care notes, return policies, and why a brand has a trustworthy history.
She uses AI to spot quality decay before buying: One of her favorite checks is asking Claude to investigate brands, which recently caught a company that had been acquired two years earlier and then saw reviews turn "abysmal" after the takeover.
The workflow is built around real parent pain, not gadget novelty: Ruiz describes parents as the "human link" between hard-to-navigate systems, and uses Claude to handle repetitive household tasks like shopping, sizing checks, returns, and warranty-style refund requests.
Claude Co-Worker handles the refund grind: From a photo of worn-through J.Crew kids pants, Claude pulled the receipt from Gmail, found the item number and order details, and drafted a refund email designed to get a yes-or-no answer without back-and-forth.
This is also a discovery tool for small artisans and old brands with bad websites: Claire and Nicole both point out that AI can route around terrible ecommerce UX, helping century-old manufacturers and smaller shops compete with Amazon's convenience.
The goal is fewer junk purchases, not hands-off parenting: Ruiz pushes back on the idea that "robots are raising her kids," arguing that automating online admin lets her focus on the human parts of parenting while buying fewer disposable products.
The Breakdown
A Brooklyn mom built a Claude project that vets can openers, toddler quilts, and kids shoes against decades-old brands, natural materials, repairability, and return policies, then uses Claude again to draft refund emails when products fail. Her pitch is simple: automate the admin work of parenting so you spend less time fighting websites and more time with your kids.
Was This Useful?
Share
Keep Reading
Make Alcreon Yours
Tune your feedFive quick questions, and the feed ranks what matters to you first.Or just get notified
The weekly Echo. Signal worth keeping in your inbox.
Every new piece, announced on X.
Read Next
See all
Playbook
Tasteful Skills
“Tasteful Skills” argues that the best agent skills are not documentation or best-practice lists.

Playbook
The Art of Tasteful Prompting
Learn how tasteful prompting helps you move beyond generic AI output by shaping context, style, and judgment from the start.

Playbook
The Codex /goal Playbook
OpenAI shipped /goal for the Codex CLI. It turns a prompt into a persisted, self-continuing contract.