2006: "This meeting could have been an e-mail" 2026: "This app could have been a prompt"
c'mon
Show HN: OfferGridAI – side-by-side comparison of real estate offers from PDFs
21–28 of 28 posts
Re: Show HN: OfferGridAI – side-by-side comparison of real estate offers from PDFs
#22Sign-up pages are not Show HNs:
Re: Show HN: OfferGridAI – side-by-side comparison of real estate offers from PDFs
#23Just a heads-up : the "about" page content doesn't seem to match what's with the rest of the website. Why is it about automated resume review when the front page is about real estate ?
Re: Show HN: OfferGridAI – side-by-side comparison of real estate offers from PDFs
#24Hello HN, I’m a solo developer building tools for real estate workflows. I built OfferGridAI after watching listing agents repeatedly struggle with the same problem during hot markets. When a property gets multiple offers, each offer usually comes in as a 10–20 page PDF. Under tight time pressure, agents have to manually dig through each document and rebuild a spreadsheet to compare things like price, net to seller,…
Tangential question: I've never owned a home and would like to try to buy one in the next year or two. There doesn't seem to be much in the way of API's/software tools that let you analyze historical data and prices of listings in specific areas. How can I get my hands on the right information to make sure I don't get ripped off?
In the US at least, your county should have an assessor that's responsible for tracking property values for tax purposes. How accessible the data is probably going to vary from county to county, and there's no common API for that, but it's a start.
Re: Show HN: OfferGridAI – side-by-side comparison of real estate offers from PDFs
#25Seriously, yesterday you posted a show HN about comparing resumes. Today you are comparing real estate offers. You are just rapid-fire fishing for a market that is willing to pay for a chatGPT wrapper around doc comparisons.
Even if this wasn't just a string of low-effort attempts, comparing real estate offers does not take hours. Deciding between them might, but the comparisons can be done quite quickly, so there is almost zero value here.
Re: Show HN: OfferGridAI – side-by-side comparison of real estate offers from PDFs
#26Hello HN, I’m a solo developer building tools for real estate workflows. I built OfferGridAI after watching listing agents repeatedly struggle with the same problem during hot markets. When a property gets multiple offers, each offer usually comes in as a 10–20 page PDF. Under tight time pressure, agents have to manually dig through each document and rebuild a spreadsheet to compare things like price, net to seller,…
Tangential question: I've never owned a home and would like to try to buy one in the next year or two. There doesn't seem to be much in the way of API's/software tools that let you analyze historical data and prices of listings in specific areas. How can I get my hands on the right information to make sure I don't get ripped off?
Others mentioned county data. If you can get that, you can build something like I did for DC -- https://colab.research.google.com/drive/1Kep_9j_PN_SxX85PYHE...
Re: Show HN: OfferGridAI – side-by-side comparison of real estate offers from PDFs
#27Earlier quoted context omitted.
Oh I didn’t know about the visual bounding boxes this is super cool! Quick question are you talking about this feature? https://docs.cloud.google.com/vertex-ai/generative-ai/docs/b... Because it’s just using structured response so it should be doable with Gemini 3 ? (We are using Gemini 3 for some docs processing and its visual understanding is just incredible)
No I'm talking about the image segmentation feature: https://simonwillison.net/2025/Apr/18/gemini-image-segmentat... But the bounding box stuff might work well enough in Gemini 3 to handle this case as well.
Hmm so that post also links back to segmentation done by structured outputs? (Though here not even enforcing the structure)
https://ai.google.dev/gemini-api/docs/image-understanding#se...
Re: Show HN: OfferGridAI – side-by-side comparison of real estate offers from PDFs
#28Earlier quoted context omitted.
No I'm talking about the image segmentation feature: https://simonwillison.net/2025/Apr/18/gemini-image-segmentat... But the bounding box stuff might work well enough in Gemini 3 to handle this case as well.
Hmm so that post also links back to segmentation done by structured outputs? (Though here not even enforcing the structure) https://ai.google.dev/gemini-api/docs/image-understanding#se...
It's not supported by Gemini 3: https://ai.google.dev/gemini-api/docs/gemini-3#migrating_fro...
> Image segmentation: Image segmentation capabilities (returning pixel-level masks for objects) are not supported in Gemini 3 Pro or Gemini 3 Flash. For workloads requiring native image segmentation, we recommend continuing to utilize Gemini 2.5 Flash with thinking turned off or Gemini Robotics-ER 1.5.