How a Pasadena Agent Used Claude to Build Pricing Models for a Seller
Published October 21, 2026 · Source: Dwell
Pasadena realtor Pilar Oliva used Claude to build two interactive HTML financial models. She used them to show sellers that a price cut would leave them better off than a HomeLight bridge loan. According to Dwell, the home later sold for $1.4 million.
Result, in their words: After a price reduction, the home sold for $1.4 million, $90,000 less than the original asking price, according to Dwell.
From the original
Oliva decided to use Claude to build two financial models: One that would show what the homeowners would net or end up owing if they lowered the price and sold it themselves and one that showed what it could ultimately cost them if they opted for HomeLight. The client only wanted to spend $40,000 out of pocket either way, so Oliva asked the AI assistant to create manipulatable HTML models where she could fuss with various prices and offers.
What they did
Dwell reports that Pilar Oliva, a realtor in Pasadena, California, had a listing on a corner lot facing a fairly busy street. Buyers weren't making offers. The market had shifted since she priced the home using a nearby comp. Her clients had found a new home and were deciding between two options. One was a HomeLight bridge loan, which required a sale within 120 days. The other was cutting the price from $1.49 million to $1.299 million, which the clients felt was an insult. Oliva used Claude to help her make the case for a price reduction.
How it worked
Oliva asked Claude to build two financial models as interactive HTML pages. One showed what the sellers would net, or owe, if they cut the price and sold the home themselves. The other showed what the HomeLight route could end up costing them. Each model worked within the clients' limit of $40,000 out of pocket. According to Dwell, she toggled switches, tried different prices and offers, and checked the math several times. She spent hours on it before she trusted the AI's work. She says she then used the models late at night, while traveling to a family wedding in France, to write rebuttals for her clients. "It worked the hardest I ever worked," she told Dwell. She also says she uses AI for tasks outside her own skills, such as writing and financial modeling.
The result
According to Dwell, the home sold for $1.4 million after a price reduction. That was $90,000 below the original asking price. Both the clients and the buyer were happy. Oliva's team now has a financial tool they can use again in similar situations.
How to try it on your listings
These are our suggestions, not steps from the source:
- Ask an AI assistant to build a simple net-proceeds comparison for each option a seller is considering, with the prices and costs as inputs you can change.
- Check every formula and result by hand before you show it to a client.
- Save the finished tool so you can reuse it on your next price-reduction conversation.