Set up an apartment-watching agent for your search
Andrew Kordampalos used Zapier and Vercel to make an agent that found an NYC apartment for about $20.
- What they did
- Andrew Kordampalos put together an AI agent with Zapier and Vercel to look for an apartment in New York City. The post says the agent handled the search and turned up a listing, though no step-by-step build details were shared.
- How it went
- The agent found an apartment. Some replies pushed back on where the inventory came from and said the result might have been fabricated.
- Tips
- If you try this, make the source of listings explicit and have the agent confirm each match is still live before it alerts you. Keep the system in read-only mode until you approve any action that would contact someone, submit something, or make a payment.
Try it yourself with Zapier Agents
Help me build a listing-watching agent for apartment hunting. Monitor [site, feed, or inbox source] for new apartments in [city/neighborhood] that stay under [monthly rent] and match [bedrooms, pets, commute, or other needs]. When you find a possible match, verify that it is still active, then send me a short summary with the link to [email or Slack]. Before you do anything that would contact a landlord, submit a form, or make a payment, pause and ask for my approval. After setup, give me a test alert so I can check the format.
Fill in the [brackets]. Agents can make mistakes, so review anything before it is sent, paid or deleted.
Get 3 agent uses like this every morning
With the day's top AI news. Free, and one click to unsubscribe.
Related agent uses
Convert chat messages into Google Calendar events
They used n8n to read a chat request, extract the event details, and add the meeting to Google Calendar.
Set up a car helper that works without internet
A Raspberry Pi in a car used a local model to answer manual questions and read live diagnostics, while some vehicle controls ran through Home Assistant.
Build a Claude Code agent with memory and identity
A developer kept a Claude Code agent persistent across sessions by loading memory and identity at start and saving updates at the end.
Sort saved recipes and track nonstop flight prices
A writer used Meta Muse to turn saved social posts into a recipe list and to compare nonstop flights with a price watch.
Tidy email, verify a refund, and arrange HVAC maintenance
Meta Muse helped clear a crowded Hotmail inbox, checked refund status through support, and set up an HVAC tune-up from old service records.
Use a scanner to figure out a check engine light
OpenClaw helped a driver buy a code reader, identify a sensor fault, and turn off the warning.