GrasShopper: time to move on

Last summer, I wrote about building GrasShopper, an AI shopping assistant that started with a very simple frustration: why does buying a pair of running shoes sometimes turn into three hours of research?

The idea was to describe what you need, let AI go through the options and reviews, and get a useful buyer’s guide. I still think that’s a problem worth solving. But looking at what’s already available, I don’t think GrasShopper needs to be another product solving it.

A few examples:

• OpenAI’s shopping research in ChatGPT, introduced in November 2025, asks clarifying questions, researches products across the web, and puts together a personalized buyer’s guide. That’s very close to what I wanted GrasShopper to do.
• Perplexity’s shopping assistant combines product research and recommendations, with checkout for selected products and merchants for Pro users in the US.
• Google’s shopping experience in AI Mode, announced in May 2025, brings conversational guidance and product comparisons into Search.

The overlap is pretty obvious. These products have different strengths and availability, but together they make very strong competition for a small side-project. Especially when the buyer’s guide can happen inside a tool people already use instead of asking them to discover another app.

Could I find a narrower angle and keep building? Probably. But I don’t feel strongly enough about that direction to make it my next focus. For the general-purpose shopping assistant I had in mind, my honest feeling is that GrasShopper isn’t needed anymore.

It was a great experience to work on it for a short while. I got to explore an agentic system around a problem I actually cared about, and take an idea beyond just thinking about it. That was worth doing even if it doesn’t become a lasting product.

So I’m putting GrasShopper aside and focusing on other things. Still glad I built it. And hopefully the next time I need running shoes, I’ll spend less time comparing them and more time actually running. 🙂