---
name: al-577-log-every-repair-on-your-rentals-by-texting-a-bot-from-yo
description: "Small landlords lose track of repairs and costs because nobody writes them down when they happen. On Nov 1, 2026, real estate investor Tanya Zorov (@TanyaZorov, co-living rooms in Jacksonville plus a long-term rental in Philadelphia, per her profile) said the hardest part of using AI for her houses was writing down how she actually decides things: what counts as urgent, when she'd rather replace than repair, and what goes straight to the property manager. Once those rules lived in the software she built, she could ask a Telegram bot from her phone. Her screenshot shows her texting that a kitchen sink was unclogged; the bot asked which house and the vendor and cost, then logged it under Repairs & Opex with title, category (plumbing), status (done) and cost marked pending. You don't need custom software to start: a chat assistant plus a shared sheet works. Use when the user wants help with rental repair log by chat with your own decision rules (operations) for a small business."
---

# Log every repair on your rentals by texting a bot from your phone: write down how you decide what's urgent, when to replace instead of repair, and what goes to your property manager, then let the bot ask for missing details and file it

Small landlords lose track of repairs and costs because nobody writes them down when they happen. On Nov 1, 2026, real estate investor Tanya Zorov (@TanyaZorov, co-living rooms in Jacksonville plus a long-term rental in Philadelphia, per her profile) said the hardest part of using AI for her houses was writing down how she actually decides things: what counts as urgent, when she'd rather replace than repair, and what goes straight to the property manager. Once those rules lived in the software she built, she could ask a Telegram bot from her phone. Her screenshot shows her texting that a kitchen sink was unclogged; the bot asked which house and the vendor and cost, then logged it under Repairs & Opex with title, category (plumbing), status (done) and cost marked pending. You don't need custom software to start: a chat assistant plus a shared sheet works.

## Inputs to collect first
Ask the user for anything below that they haven't already given you. Don't guess missing facts.

- The material the task is about (pasted text, notes or data)

## Instructions

Do the task below with the user's inputs in place of each [bracket].

1. Write your decision rules on one page: what counts as urgent (no heat, active leak, lockout), repair vs replace (for example, replace if the repair is over half the cost of new or it's the third repair this year), and what always goes to your property manager.
2. Make a repairs sheet with columns: date, property, unit, title, category, vendor, cost, status, notes.
3. Give your AI assistant the rules and the sheet (or connect it to the sheet with Zapier, Make or n8n). Tell it: "When I describe a repair, ask only for what's missing (property, vendor, cost), then add a row. If cost is unknown, mark it pending. Apply my rules and tell me if this should be urgent, replaced, or sent to the property manager."
4. Text it right after each repair, from your phone.
5. Once a month ask: "List pending costs and repeat repairs by property." Fill in the gaps and update your rules when you disagree with its call.

## Safety checks (share these with the user)

- Check every figure, price and total against your own records before anything is sent, posted or booked. A person approves refunds, discounts, payments and price changes.
- Check names, dates, numbers and any claim against your own source material before you use the answer. AI can misread or invent details.
- Say clearly which parts need a person to review or approve before anything is sent, paid, posted or filed.

## About this skill

- Works with: Telegram, ChatGPT, Claude, Google Sheets
- Based on this real-world example: https://x.com/TanyaZorov/status/2117022117262753841
- Free prompt from AgentPlaybook Real Estate: https://agentic-library.netlify.app/prompt/al-577-log-every-repair-on-your-rentals-by-texting-a-bot-from-your/
- To install in an agent that supports Agent Skills, save this file as SKILL.md in a folder with the same name as `name` above (for example in your skills directory). Install steps for Claude.ai, Claude Code, Cursor and Codex: https://agentic-library.netlify.app/skills/