Track your apartment comp set every Monday with a Claude routine that reports concessions, rents, and permits
PLOT Daily built a competitive tracking routine for a 26-unit, all one-bedroom building at 3105 Bellevue Boulevard in Silver Lake, Los Angeles. Starting from a CSV of comparable properties, Claude asked four scoping questions, flagged comps that were not market rate, added unit type so a one-bedroom is never measured against a two-bedroom, and tracked seven fields: concessions, rents, availability, vacancy, renovation activity, permits, and ownership. The live baseline run used five parallel research agents across listing sites, property management sites, and LADBS permit records in about seven minutes, flagged a suspicious studio listing for a person to verify, and was then saved as a remote routine that runs every Monday at 7 a.m. Pacific.
At a glance
- Tools used
- ClaudeClaude routinesWispr Flow
- Category
- Investing & underwriting
- Audience
- investor, broker
- Difficulty
- No-code setup
- Source
- How to Build an AI Routine That Tracks Your Competitors' Properties Every Week
Jake Heller (PLOT Daily / AI for CRE Collective) · Article · Jul 22, 2026 - First step
- Put your subject property and your comp set in one CSV with address and unit mix columns, and have Claude review the comp set for non-market-rate or mismatched properties before you schedule anything.
Compliance note: The routine reads public listing and permit pages; respect each site's terms of use. The first run is a baseline snapshot, and the source flags suspect data points on purpose, so a person should confirm odd figures before rent or concession data drives a pricing or underwriting decision.
Suggested prompt
Written by this directory, inspired by the source. Replace the [bracketed] parts.
I want a weekly routine that tracks the comparable properties in the attached CSV against my subject property, [subject address, unit count, unit mix]. Before you build anything, ask me your questions and draft the routine prompt for my approval. 1. Review the CSV first. Flag any comp that looks like affordable, supportive, or other non-market-rate housing, and any comp whose unit types don't match my subject property. 2. For each remaining comp, track by unit type: concessions, asking rents, availability, vacancy, renovation activity, permit filings from [city permit portal], and ownership or for-sale listings. 3. Prioritize listing sites, property management sites, the city permit and planning portals, and Google News. 4. Output a change-only digest at the top (what moved since last week), then the full table with a source link for every figure. 5. Mark any figure you can't confirm, such as a listing that has been live for months, as 'verify' instead of logging that figure as fact.