Frankly, the idea was born of my own lawn care struggles. Endless lawn care company fees without any actual improvement. Googling problems and finding generic solutions without regional considerations. One time I overseeded my grass not realizing I had to actually put soil down too.
One day, I decided to run lawn pictures through AI and found some pretty helpful information. So I decided with my clinical background (the idea of treating the cause, not just the symptoms), as well as tech savvy, I would create an AI tool where homeowners can upload pictures of their lawn, enter their ZIP code, and get a diagnosis tailored to their location with actionable next steps in just 15 seconds.
Completely free. The platform is monetized with affiliate sales (if a user elects to purchase through one of our Amazon or other links) and by selling exclusive rights to individual ZIP codes to lawn care companies seeking warm leads. Users can pursue their own DIY plan, purchase a lawn care subscription service, or contact a local lawn care system.
I'd love if you'd test it out, toy with it, try to break it, and give me your feedback. Any feature requests would be super helpful.
Thanks! Excited to hear your thoughts.
Andrew
It's saying "I'm an unnatural, non-native monoculture that does little to support biodiversity but will gladly suck up your time and money."
Sorry to speak negatively of the thing you're working on Andrew, but the subject matter is one I feel strongly about. Having a short cut lawn area has many recreational uses, but most people don't do anything except maintain most of their lawn. On top of that, many people become focused on a particular aesthetic that usually requires non-native grasses and harmful pesticides. In some places, scarse water supplies are used just to maintain a certain color.
I encourage everyone to look into replacing grass lawns with native plant landscapes, and where you do want it short cut, look into a mix of plants like clover that require far less work to keep alive than most grass monocultures.
That said, plenty of people _do_ actually use their lawns, especially those of us with children. My actual grass lawn is surrounded by native and low water use plants, but my small patch of green (around 2k sqft), will stay green until my kids move out.
I think it's much more useful to target the endless industrial and commercial parks that have far more grass than a normal size neighborhood. Let people have some joy in their lives.
Technique developed by the Japanese botanist Akira Miyawaki: planting seedlings close together makes them compete for sunlight, thus growing tall quickly. Get a forest in under a decade!
https://www.creatingtomorrowsforests.co.uk/blog/the-miyawaki...
I think offering a range of options and leaving it up to people could go a long way. Especially since people could just try out all options to see what it would involved, how they might imagine (and like) the results, before committing to anything.
As in, here's the lawn, I want it to a.) keep it trim and green, b.) keep it decent looking and still human friendly, but also make it low maintenance and better for biodiversity c.) turn it into a jungle of flowers.
I’d highly recommend telling Claude something like (untested myself): redesign the website, remove all emojis and all letter-spacing CSS, use non conventional typefaces, no italic serifs, limited cream/beige colors
Something along those lines.
Fun idea, good luck!
Did you craft a rich prompt template that's untuitively helpful? If so, what did you see go wrong before you had that figured out? How did you determine it was a positive improvement? How will you make sure that your prompt's benefits hold up as your original model is retired and it needs to be run against whatever new model you're left to use instead?
Or is it just that your website acts like a kind of inspiration a la "Hey, did you ever think to ask AI about your lawn problems?"? If so, how do expect people to find this inspiration when link-delivering search is being agressively retired in favor of synthesized chatbot responses already?
> Veterinarian turned founder, AI lawn diagnosis
My point being - your UX doesn't ask what people's goals are. Not everyone wants a "perfect lawn". Even people who do want grass may have different priorities for their grass - low maintenance vs. low water usage vs. really green, etc.
If you want your product to be different than what the lawn care guys will say, then you need to actually let people do different things in the app. Or, if you are dead set on making this into lead gen for lawn care guys, well... I personally find that somewhat disheartening, but clearly I'm not your audience.
It's not "just" for lead gen. I'm actually trying to help people and solve a problem. I want the tool itself to be free. It monetizes by means other than making it a paid tool.
Please ignore most of the people on hacker ews, most of them are losers who complain about everything.
When I'm planting, site selection is important but I'm really slow at it, even when using AI.
I also use AI for some plant diagnosis but that hasn't led to any meaningful action, except that I'll be more thoughtful about site selection for some plants in the future.
Most of this could just be a collection of documents in a Claude project, but hey if more people are working on it I'm all for that even if there are competing tools.
What I don’t know yet is if the DIY I’m doing with the help of Claude is going to materialize into a lush lawn.
It has me doing pre-emergent spray, broad leaf weed killers, and moss killer.
It’s a lot of work and I’m sure there is a much better UX than saved chats.
We do home property and inventory services using AI on photos as well and the key thing we've found so far is that the biggest rival to those features is just people dragging photos into chatgpt and asking away. So the key here is differentiating from that and making something better and more accurate. What we did was to basically build a better and deeper prompt and history, e.g. context is king in a vertical. So that means the other info the user has put about the property, the memory of previous things asked or seen, combining with publicly available property info we already gather - this would make the information more valuable than straight gpt usage.
So what more can you bring to the bare prompt on the photos to help? What can you build in terms of info about the zip, so you do more 'vertical stuff' before the api call.