Building (https://estan.ai), an AI that reverse-engineers real estate listings by pulling not just from public records, but also social media, neighborhood forums, historical sales, and user reviews. It flags red flags—like crime trends, sketchy development patterns, neighborhood trends, and so on—then presents them in plain, opinionated language.
Goal: replace the vague boilerplate of listings with something closer to a paranoid friend who's done way too much research. Curious if this kind of subjective, context-heavy analysis adds real value—or just noise.
Think this is a great idea, I would have paid for this when we were buying our house. Especially for one feature: let me give you a list of properties (perhaps forwarded from my agent, or e.g. a Zillow search) and get back the "enriched" listings with your added insights. It'd be great if I could then weight different factors (local schools, walkability, etc.) to stack rank them.
With a once-in-a-century shakeup in commission structure for Realtors, you're building this at a very interesting time.
Happy to chat more if you'd like to bounce ideas around.
edit: Also, I think you could easily monetize this by charging agents (or their brokers) for it.
I’ve thought about something similar, after having been burned twice by rosy outlook from real estate agents (USA). The issue is there’s no incentives for a tool like this. A pre-sale inspection is really just to protect “the deal” from being unwound, and to check boxes where there is regulation or if one or the other party could be sued post-sale. Neither the selling or buying agent would want a tool that will prevent a deal, and a homeowner may not see the value given they are already paying a ton of cash to their agents. You would need to monetize via some side channel, or convince the buyer to pay you - the non-competitive MLS status quo of US realty would never permit you to partake in a transaction. Or, sell to those who have been burned (Id be a client if I ever can stomach buying a new home again).
Some ideas for your tool:
- noise - neighbors with farm animals (increasingly popular in suburban areas, and local regs haven’t caught up wrt noise), or neighbors who have been reported or fined for animal neglect or noise violations (for example, pets that live outside where homes are close enough for this to be a meaningful noise problem). Problem neighbors in general, which is subjective but probably easy to find outliers.
- traffic patterns, utilization by Waze drivers, speeders, prevalence of stop signs per intersection, if the street is used by emergency personnel or is close to a fire or police station
- frequency of nearby construction via permit applications
- inspector reviews - US inspectors have little oversight and typically protect themselves from damages contractually, it would be good to know which ones regularly flag things like roof leaks or don’t have exclusive relationships with real estate agents (which queers their incentives wrt buyers - “use my guy, he’ll give you a deal” gets contracts signed quickly)
- prevalence of rentals or Airbnb in the area, renters aren’t bad of course but a buyer may want to know there’s a higher density of residents than appears, and all the knock on effects this could cause like traffic, trash, noise, new faces, non-owner residents engaging in risky behavior etc.
I’d considered a device that could be nailed to a nearby telephone pole, like a raspberry pi with a sensitive mic and some presence sensing, with a few days of battery life. A technology version of “hang out in this neighborhood for a bit and give me the low-down that the sellers may want to hide”.
Goal: replace the vague boilerplate of listings with something closer to a paranoid friend who's done way too much research. Curious if this kind of subjective, context-heavy analysis adds real value—or just noise.