Each day Zillow listings in your market are checked for recent price cuts and relists at a lower price, scored against nearby sold comps on price per square foot, and the top picks get an AI verdict and watch-out note posted to Slack
An n8n template by Daniel Shashko runs on a daily schedule, or from a form where you type a market, and starts a Bright Data Zillow dataset collection with your location, price ceiling, minimum beds, and days-on-Zillow filters. It drops failed and out-of-range rows, reads each listing's price history to catch explicit price changes and relists at a lower price, and builds a local price-per-square-foot benchmark from the median of comparable sales. The workflow scores each listing on discount and price-cut signals, keeps the top listings above your minimum discount, and has an OpenAI model (gpt-5.6-terra) write a structured verdict, reason, and watch-out note for each one. Results are appended to a Google Sheets Listings tab and posted as a digest in Slack. Optional unwired steps route listings by verdict, estimate a monthly payment from your rate and down payment, cap the digest length, or email the digest.
At a glance
- Tools used
- n8nBright DataOpenAIGoogle SheetsSlackZillow
- Category
- Investing & underwriting
- Audience
- investor, buyer's agent, acquisitions manager
- Difficulty
- Builder
- Source
- Find and score Zillow price cuts with Bright Data, GPT-5.6, Sheets and Slack
Daniel Shashko (n8n creator) · n8n template · Aug 19, 2026 - First step
- Set Settings to one ZIP code you know well with a low listings-per-run number to keep Bright Data costs small, run it once from the form, and compare the top three verdicts with what you already know about those houses.
Compliance note: Check Zillow's and Bright Data's terms for your use of the collected listing data, and confirm every price and history with the listing agent or MLS before you make an offer or send a listing to a client.
Suggested prompt
Written by this directory, inspired by the source. Replace the [bracketed] parts.
You review price-cut listings for [investor / buyer's agent] in [market]. For each listing below you get the address, list price, price history, price per square foot, the local median price per square foot from sold comps, the discount percent, and days on Zillow. Return JSON per listing with verdict (worth a showing, watch it, or skip), a one-sentence reason that cites the numbers given, and one watch-out note, such as repeated price cuts or a price per square foot far below the comps that may signal condition issues. Use only the data provided and never state repair costs, rents, or values you were not given. Listings: [paste]
Get 50 AI Prompts for Real Estate Agents, free
Subscribe to the Daily 5 and download the 48-page PDF right away. The prompts help with:
- Getting more leads from the contacts already in your CRM
- Faster follow-up, so no text or inquiry goes unanswered
- Less time on listing descriptions, paperwork, and showing instructions
- Copy-paste prompts tested by working agents, brokers, and landlords
- Five new real-world AI use cases every weekday morning in the Daily 5
Confirm by email. Unsubscribe in one click. Review every AI draft for accuracy and fair housing compliance before you send it.