Rental Property Studio — AI Task Kit (4 Agents) — Starter: Maintenance Coordinator

From AGENTORY — ready-to-use AI Task Kits. Drop in. Power up.

One agent from the Rental Property Studio kit — complete, nothing cut down. Works with the AI you already have: upload the file, tell it "Start", answer a few questions, and get to work.

One specialist landlord-records agent — running inside the AI you already use.

No new app. No subscription. This agent works with any AI chat — ChatGPT, Gemini, Claude, Copilot, whichever you have (free versions work).

This kit keeps records and makes drafts; it is not legal advice, and it is not tax advice. That boundary is part of the design of every agent in this kit, in this Starter as much as in the full kit: your units, tenants, rents, and dates are recorded as you state them, a pasted document is filed verbatim and never interpreted, no jurisdiction's rules are stated for any jurisdiction anywhere — the kit deliberately contains none — no tenant or applicant is scored, ranked, characterised, or decided about, and every message for anyone else is a draft you review and send yourself. A figure the record does not hold — a late fee for a unit, a notice period, a deposit — is printed as "not recorded," never supplied from general knowledge or carried over from another unit.

The Maintenance Coordinator keeps the Book's maintenance record (6 calibration questions): how tenants report issues to you, as you state it; your reply-wording preference, in your exact words; your tradespeople exactly as you supply them; your spend-approval habit, in your own words; entry and access wording only as you state it from your own documents, or none recorded — never a "standard" wording; and your own status vocabulary, the only status words this agent may ever apply to a job. It coordinates the record: every issue stands in the words it was reported in, every job's status stands only as you last reported it, dated, in your vocabulary — never inferred from a date having passed, a visit having been booked, or an invoice existing — and no problem is ever diagnosed and no cost is ever estimated that you have not stated. Its gated deliverable, the Maintenance Tracker / Work-Order Record, runs the Maintenance Tracker Check (GATE-MC) before it is presented as finished. In the kit's fictional worked example, the Unit B kitchen faucet leak is recorded with Alicia Gomez's pasted message standing verbatim — the leak "started Tuesday," read against the timeline as Tuesday 2027-02-09 — and Laura Bennett's own log note standing alongside it, "first heard about it Wednesday" (Wednesday 2027-02-10): both stand, attributed, never merged into one timeline date, and neither is preferred (Alicia Gomez and Laura Bennett are fictional characters created for this kit — not a customer story); the visit stands on Thursday 2027-02-11 with the status "Work done" as Laura reports it, the tradesperson stands as Mike Rinaldi, Rinaldi Plumbing, exactly as she supplies him (a fictional character in the same example; the one phone number in the example is a fictional example number), the invoice stands at $185 as she states it from the invoice with its parts/labour split printed as "not recorded," and her spend-approval habit stands in her own words as a stated habit — the kit records no approval of its own. A second job in the same example, the Cedar Avenue furnace filter Laura changed herself on Saturday 2027-02-13, stands at $24 in total (= 24 + 0, parts shown) with the status "Done" as she reports it and no tradesperson attached. This agent works from My Property Book. If the Book's cover fields are missing, this agent names them and sends you to the Tenant Comms Drafter first — it does not open a Book or improvise the missing facts. In Connected mode it is the kit's sole Todoist mirrorer, mirror-only: where that route verifies, it may copy its own tracker list to Todoist on your approval of the exact list, with no tenant name in any task title — the Book stays the source of truth and nothing in Todoist writes back except as you report it. It holds no Gmail draft route and no calendar route: a note to a tradesperson is copy-ready text you send yourself, and a visit is a tracker record, never a calendar hold. It never contacts, books, or dispatches a tradesperson, in any mode. You need: the Book opened first (the Tenant Comms Drafter, full kit / Upgrade, opens one — or bring a Property Book you already have) and your issues, tradespeople, and statuses exactly as you report them.

How it works (once):

1. Add the agent file to your AI chat — upload the .md file, or on a phone, open the .txt version, copy it, and paste it in.

2. Type "Start".

3. Answer the agent's questions, one at a time. That's the calibration, and it's what makes the output fit YOUR units.

4. Done — ask for what you need.

This is the Starter edition: ONE agent, complete — the same file as in the full kit, nothing cut down. It includes the shared Property Book (fill it once, paste it into any new chat, skip the interview), a prompt sheet with the exact phrases for this agent, a plain-language guide to what AI can and cannot do, and troubleshooting help. Its gated deliverable carries its named completeness check, run before the deliverable is presented as finished: a section carrying its honest gap in place passes with the gap printed, and asking for "just the highlights" never waives the check — the only shorter artefact is a labelled extract that failed its gate, with the gaps named.

Your tenants are third parties in this record: the Book holds facts about your tenants, applicants, and tradespeople, all supplied by you, and the agents never contact them. Keep the Book where only the people you choose can see it, and share it by part — a tradesperson receives the note you choose to send, not the whole Book.

Two ways to work — your choice, per session. Run this agent in a regular AI chat (ChatGPT, Gemini, Copilot) and it works as a guide: it creates and edits the complete deliverables right in the chat — the finished documents and complete updated files themselves, never outlines, edit lists, or pieces for you to assemble — and guidance is what covers the steps inside outside tools and accounts, which you perform yourself. Run the same file on an agentic AI — Muse, Claude Code, Devin, and similar — and it can do more where the platform genuinely allows: the Book kept as a file under git, or as a Google Doc where that route verifies in-session. The kit's connected acts are fenced by agent, and the per-agent block in this listing states this agent's fence exactly: Gmail draft creation belongs to the Tenant Comms Drafter only (its own gated tenant drafts only) — draft-never-send, and no send tool exists in this kit; calendar holds belong to the Lease & Turnover Tracker only (your own calendar, no invitees ever, lease and turnover dates you stated only); the Todoist mirror belongs to the Maintenance Coordinator only (its own tracker list only, the Book staying the source of truth); Apple Calendar is guide-only — a copy-ready hold. Same agent, same rules — what changes is what your platform lets it do. You pick the mode every time; guidance is always available and always complete. No property-management, listing, screening, or payment platform is connected in any mode: records from a platform enter the Book only as text, documents, or exports you supply yourself.

What's inside:

- The one agent, in .md AND .txt format (identical content)

- Prompt Sheet for this agent — the exact phrases for every job

- My Property Book — the full Book; the sections for the other agents are already in it, so upgrading later means no new setup

- AI Limitations Disclaimer (.md + .txt)

- Starter README — step-by-step setup

- Troubleshooting & FAQ

What you need:

- An AI chat account of your own (free versions work for the guided work)

- Agent-specific notes are in the agent paragraph above

Want the rest of the set later? The other three agents complete the kit (Standalone, $49). Starter owners upgrade for $30 — the difference — and the Property Book you fill in here already covers the other agents, so there is no new setup.

Honest limits:

Each agent is a text instruction file for your existing AI — it is not a trained AI model, not a separate app, not software, not a property manager, not a screening service, not a legal service, and not a messaging service. What it can do depends on where you run it: in a chat-only AI it guides and drafts — creating and editing the complete deliverables right in the chat — and you perform only the actions inside your outside tools and accounts; on an agentic AI it can act through the tools you choose to connect — always showing you the exact action first, always with your approval before anything is created, and never unattended. Connections are made through your platform's own secure sign-in and key flows — the agent never asks for, receives, or stores a password, API key, or login, and a secret pasted into a chat gets one answer: change it now. This kit's spine holds in both modes: one shared Property Book that no output may contradict, documents reproduced exactly as supplied and never interpreted, no jurisdiction rule stated for any jurisdiction, no screening decision and no characterisation of any person, conflicts flagged with both sides standing and never resolved by the agent, figures only as you state or report them with computed figures shown in parts, and drafts that are never sent by an agent. (Agent-specific limits are in the agent paragraph above.)

One honest expectation: this kit is a plain-text instruction file, and it loads in any AI you already use — but the AI you run it on sets the quality. The agent's rules, questions, and output formats are fixed in the file; how deeply and consistently your AI follows them depends on your model and on how much it can hold in one session, so a weaker or free-tier model may shorten, skip, or drift where a strong current model stays exact. AI tools, models and context lengths all affect the final results — and trying different tools may help you find the best one for your needs; the same file, unchanged, often does better on a stronger model. The full disclaimer in your download explains this properly and shows how to get the best from whatever AI you have.

Price: $19 — Starter: ONE agent, your choice.