Rental Property Studio — AI Task Kit (4 Agents)

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

Works with the AI you already have. Upload one file, tell it "Start", answer a few questions — then keep one faithful Property Book built only from what you state and supply, and turn it, on your word, into a Tenant Comms Draft Pack drafted only from recorded facts, a Ledger Statement whose every computed figure is shown in parts, a Maintenance Tracker kept only in the words issues were reported in, and a Turnover Pack built only from your own stated dates, documents, and checklist.

Four specialist agents that take a small landlord's scattered records — a rent figure in a text thread, a lease excerpt in a folder, a tenant's message about a leak, a ledger line added up quickly in January — to one faithful Property Book everything else is built from — running inside the AI you already use.

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

How it works (once per agent):

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 — yourself and your signature wording exactly as you state them, your properties, units, and tenants exactly as you state them, your rents, dates, documents, and figures exactly as you supply them. That's the calibration, and it's what makes the Book fit YOUR units.

4. Save the complete updated Property Book each agent hands back to you — the agent keeps it current in the chat and returns it whole, never as pieces for you to assemble — and the next agent starts from your real record.

Use the agents in order:

1. Tenant Comms Drafter — the flagship; opens and keeps the Book: you and your signature wording as you state them, your properties, units, and tenants as you state them, your stated tone for tenant drafts, your contact facts exactly as you state them, and your own never-include list in your exact words; it files tenant messages as you paste them, verbatim and attributed, and drafts tenant messages from recorded facts only. It runs the Tenant Comms Draft Pack Check (GATE-TC).

2. Rent & Ledger Keeper — the Book's ledger desk: rents and due days per unit as you state them, late-fee figures per unit only as you state them from that unit's own documents, other charges as you state them, and payments exactly as you report them, dated — and the Ledger Statement, in which every computed figure is printed with its parts shown and every conflict is flagged in place, standing. It runs the Ledger Statement Check (GATE-LG).

3. Maintenance Coordinator — the Book's maintenance desk: issues kept in the words they were reported in, tradespeople exactly as you supply them, costs exactly as you state them, and job statuses only as you last report them, in your own status vocabulary. It coordinates the record — it dispatches, books, and contacts nobody. It runs the Maintenance Tracker Check (GATE-MC).

4. Lease & Turnover Tracker — the Book's lease desk: lease start and end dates per unit exactly as you state them, pasted lease, notice, and other documents filed verbatim and never interpreted, deposit figures only as printed in documents you supply, renewal intentions exactly as you state them, and your own turnover checklist word-for-word, in your order. It runs the Turnover Pack Check (GATE-LT).

One Property Book, nothing invented. All four agents work from the same shared Property Book — you as stated, properties, units, and tenants, rents and due days, charges and payment reports, filed documents and tenant messages, maintenance jobs and their reported statuses, lease dates, deposits as printed, renewal intentions, your checklist, conflicts, gate results, and the change log exist once, in one place. No draft pack, statement, tracker record, or turnover pack may introduce a fact that is not in the Book or supplied by you in that session. Anything missing is printed as "To confirm" or "not recorded" — never completed from a pattern, never given a plausible date, number, name, or amount, and never carried over from another unit's record.

The boundary, stated plainly — it is a design feature, not fine print. This kit keeps records and makes drafts; it is not legal advice, and it is not tax advice. It states no jurisdiction's rules — deliberately, for any jurisdiction, anywhere: landlord-tenant law varies by place, so this kit contains none of it — no notice period, no late-fee rule, no deposit rule, no entry rule, and no required wording is stated, supplied, or completed by any agent, in any wording, hedged or otherwise. It does not interpret a lease, a notice, or any other document you paste: a pasted document is filed verbatim and stays a record, and what it prints — a late-fee line, for example — exists only inside that document's reproduction and as you state it from your own documents, nowhere else. It makes no screening decision of any kind: screening material you supply is filed exactly as supplied, no tenant or applicant is ever scored, ranked, or characterised by the kit in any output, and the decision on any application is yours alone, never recorded as the kit's. And nothing is ever sent by the kit or its agents: every message for anyone else is a draft you review and send yourself, and no agent contacts a tenant, an applicant, or a tradesperson, in either mode. It is records and drafts, not a property manager, not a screening service, not a legal service, not a messaging service, and not a prompt pack.

Documents and figures, reproduced exactly — that fidelity is the point. A pasted document stands exactly as pasted — every line, never tidied, shortened, re-ordered, or "cleaned up," and never turned into an instruction, a charge, or a deadline. Your own stated texts — your instructions, your notes, your checklist, a tenant's message as you paste it — stand in their exact words, dated and attributed. Where two recorded facts disagree, both stand, flagged, in every output that touches them: never reconciled, never corrected in place, never averaged, never silently preferred because one is newer, and never blamed on anyone. Arithmetic is the kit's only computation: any figure the kit computes — a rent roll, a period total, a balance, a day-count — is printed with its parts shown, so you can check it against the entries above it; a figure the kit did not compute is printed as supplied, reported, or printed, with its source named. A payment's status, a job's status, a draft's status is what you last reported, dated to your report — a date having passed settles nothing.

Completeness is checked, by name — and "just the highlights" does not waive it. Each of the four major deliverables carries its own named check, run before it is presented as finished, with the result printed on it: the Tenant Comms Draft Pack Check (GATE-TC), the Ledger Statement Check (GATE-LG), the Maintenance Tracker Check (GATE-MC), and the Turnover Pack Check (GATE-LT). A section carrying its honest gap in place — "not recorded," "To confirm" — passes with the gap printed: a printed gap is the kit working. A gap filled by invention, a gap hidden, or a section missing fails the check by name, with the failing sections listed. If you ask for "just the highlights" or "just the totals," the check still runs: the only shorter artefact available is a separate extract labelled as an extract that failed its named gate, with the gaps named — never the deliverable itself, however often the request is repeated.

Your tenants are third parties in this record — the privacy stance. The Book holds facts about other people — your tenants, applicants, and tradespeople — all supplied by you, including their messages as you paste them and your payment reports about them. The Book holds only what you supply, exactly as you supply it. The agents never contact any of those people on their own — this kit sends nothing, in either mode. Share the Book by part: a tradesperson receives the note you choose to send, not the whole Book. Keep the Book where only the people you choose can see it, and remember that anything you paste into a chat is shared with that AI provider under that provider's terms. Every agent tells you this once, plainly, at setup. Secrets and payment details are never recorded in the Book.

Two ways to work — your choice, per session. Run an 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: it can maintain your Property Book as a real file under git, or as a Google Doc where that route verifies in that session. Same agents, same rules — what changes is what your platform lets them do. You pick the mode every time; guidance is always available and always complete.

What "connected" means here — stated plainly, with the limits named. Drafts are the ceiling: no agent in this kit sends anything, in either mode. Where a Gmail route verifies in-session, one agent only — the Tenant Comms Drafter — may create Gmail drafts of its own gated tenant-message drafts, in your own Gmail drafts, on your approval of the exact text: the route offers draft creation and no send tool exists in this kit. A created draft is never described as sent — you send it yourself from Gmail. Calendar holds belong to the Lease & Turnover Tracker only: your own calendar only, no invitees ever — no tenant, applicant, or tradesperson is ever a calendar invitee — for lease and turnover dates as you stated them only; a hold is not a notice to anyone. That maintenance tracker list, and only that list, may be mirrored to Todoist by the Maintenance Coordinator only, on your approval; the Book stays the source of truth, and no tenant name appears in a mirror title. Apple Calendar is guide-only on every platform: you receive the exact hold as finished text and add it yourself. No property-management, listing, screening, or payment platform is connected at all. There is no integration or sync with any such platform — records from a platform enter the Book only as text, documents, or exports you supply yourself, filed as supplied, and no agent in this kit will claim otherwise.

Not sure what your AI can actually do? Each agent starts by telling you which platform it is running on and what it can really do in this session — its actual tools, not the brand name. The kit also includes a short, plain-language guide to AI limitations, with a dated annex listing which platforms can act and which only guide, and what each can really do with this kit's tools — so you always know where you stand.

A realistic first session: with the Tenant Comms Drafter you answer its questions one at a time and reach the first milestone in about 10 minutes: the Book opened — the opening record checked under GATE-TC, your facts exactly as you stated them with their gaps printed — plus one faithful first filing, demonstrated live: paste in one real document, for example a lease excerpt, and receive it back filed word-for-word, with any fee line it prints kept as a record inside that document only; paste in one of your own ledger lines whose parts do not add up to its printed total, and both figures stand, flagged, rather than settled. That is the first session — not a finished property-management system. Draft packs, statements, tracker records, and turnover packs come step by step after that, from the Book you build.

The worked example: the materials walk one complete example end to end — Laura Bennett, a landlord who self-manages three units (Laura Bennett is a fictional example created for this kit — not a customer story): 214 Maple Street, Unit A (tenant James Whitaker, rent $1,450/month), 214 Maple Street, Unit B (tenant Alicia Gomez, rent $1,275/month), and 88 Cedar Avenue, a house (tenant Daniel Osei, rent $1,895/month) — James Whitaker, Alicia Gomez, and Daniel Osei are fictional characters in the same example — so you can see every format before you build your own: a Book opened on Monday 2027-02-15 with the units, tenants, and rents as stated and the gaps printed (no phone or email for Laura is recorded, so a draft prints "not recorded"; no late fee for Cedar Avenue is recorded anywhere); the monthly rent roll printed with its parts shown, $4,620 = 1,450 + 1,275 + 1,895; one pasted document, the Unit A lease excerpt, reproduced verbatim — it prints a late fee of $50, which exists in the example only inside that pasted text and as Laura states it from her own documents, nowhere else; Laura's pasted January ledger line for Unit B, "rent $1,275 + late fee $50 = total $1,355," in which the parts sum to $1,325 (= 1,275 + 50) and the printed total is $1,355 — a $30 difference (= 1,355 − 1,325), flagged, with all three figures standing, never corrected and never blamed on anyone; a January 2027 Ledger Statement in which rent due is $4,620 (= 1,450 + 1,275 + 1,895), received as Laura reports it is $4,245 (= 1,450 + 900 + 1,895), and the rent balance is $375 (= 4,620 − 4,245, agreeing with the Unit B balance of $375 = 1,275 − 900); a maintenance record for the Unit B kitchen faucet leak in which Alicia's pasted message says the leak started Tuesday (read against the timeline as Tuesday 2027-02-09) and Laura's own log note says she first heard about it Wednesday (Wednesday 2027-02-10) — both stand, attributed, never merged — with the visit on Thursday 2027-02-11, the status "Work done" as Laura reports it, the tradesperson Mike Rinaldi, Rinaldi Plumbing, exactly as Laura supplies him (Mike Rinaldi is a fictional character in the same example; the one phone number in the example is a fictional example number), and the invoice of $185 as Laura states it from the invoice, its parts/labour split printed as "not recorded"; a second job, the Cedar Avenue furnace filter Laura changed herself on Saturday 2027-02-13, at $24 in total (= 24 + 0, parts shown — $24 for the filter, no labour cost, in her own words); and a Turnover Pack for Unit A whose lease ends Tuesday 2027-08-31 as Laura states it (197 days after the Book opened: 2027-08-31 − 2027-02-15 = 197, printed as a day-count only, attached to no notice period or deadline), whose deposit is $1,450 as printed in the pasted lease excerpt and nowhere else, whose renewal intention stands exactly as Laura states it — "undecided" — and which prints every item of Laura's own five-item turnover checklist word-for-word, in her order, with the keys recorded at move-in printed as "not recorded." Your Property Book gets your own material; the example is there to show the shapes.

What's inside:

- 4 agent files, each in .md AND .txt format (identical content — one of them always works on your device, phone included)

- My Property Book — fill it in once (agents help you), paste it into any new chat, skip the interviews; it is the kit's single source of truth: your calibration for all four agents, plus the registers the agents maintain — the change log, the source index, conflict flags, gate results, the "To confirm / not recorded" list, the draft log, filed documents and messages, ledger entries, and job and turnover entries

- Prompt Sheet — the exact phrases to say to each agent, for every job, including the approval phrases for Gmail draft creation, calendar holds, and the Todoist mirror — and the plain statement that no approval phrase for a send exists, because the kit sends nothing

- AI Limitations Disclaimer (.md + .txt) — what AI can and cannot do, in plain language, with this kit's tools as the examples and a dated capability annex

- A step-by-step README that gets you running in minutes

- Troubleshooting & FAQ — a statement that came back with a total and no parts, a document that came back tidied, a draft carrying a figure from another unit, a draft reported as sent, a chat that cannot create a draft: the known rough edges and their fixes

- Changelog — what changed in this version

Who it's for:

- Landlords who self-manage 1–10 units whose records are scattered — a rent figure in a text thread, a lease in a folder, a tenant's message they cannot quite date — who want one faithful record they can answer from, in exact words

- Landlords whose figures come from more than one place and who need differences surfaced plainly, both sides standing, instead of quietly harmonised into one tidy figure

- Anyone drafting tenant messages who wants each draft built only from recorded facts — dates, amounts, recorded events — in their own stated tone and under their own never-include list, and sent by themselves

- Anyone keeping a rent ledger who wants every total and balance recomputed from the recorded entries, with its parts shown, rather than taken on trust

Who it's NOT for:

- Anyone looking for legal or tax advice, a statement of any jurisdiction's rules, a screening decision or score, a property manager, property-management software, rent collection, or a service that messages tenants for them — this kit is instruction files for your AI, plus the record work you direct and check

- Anyone who wants an agent to decide what a lease clause means, what fee or period applies, whether to accept or renew a tenant, or what a deposit deduction should be — those questions are routed to your own documents, or to your own lawyer or local advice service, and answered there

- Anyone who wants a pasted document turned into a charge, a notice, or a deadline — a document's printed line is a record, and only a figure you state yourself, from your own documents, can ever appear as your figure for a unit

What you need:

- An AI chat account of your own (ChatGPT, Gemini, Claude, Copilot, or any other — free versions work for the guided work)

- Your own material — yourself, your units, and your tenants as you state them, your rents and dates as you state them, the documents you hold exactly as you have them, your figures as you report them; the agents use only what you supply, and infer nothing

- A private place to keep the saved Property Book — it holds facts about your tenants, applicants, and tradespeople, and only the people you choose should be able to see it

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 agents never ask for, receive, or store a password or secret key, and a secret pasted into a chat gets one answer: change it now. Mode honesty holds throughout: in Connected mode the Book is kept as a file under git so a change can be rolled back, or as a Google Doc where that route verifies; Gmail work is draft creation only, by the Tenant Comms Drafter for its own drafts only, and no send tool exists in this kit; calendar work is an approved, invitee-free hold on your own calendar, for lease and turnover dates you stated only, by the Lease & Turnover Tracker only — and a copy-ready hold everywhere else, always for Apple Calendar; the Todoist mirror copies the maintenance tracker list only, by the Maintenance Coordinator only, and originates nothing. No property-management, listing, screening, or payment platform is integrated in any mode. The kit's boundary holds in both modes: records are kept exactly as supplied, documents are reproduced verbatim and never interpreted, no jurisdiction rule is stated for any jurisdiction, no screening decision is made and no person is characterised, conflicts stand flagged and are never resolved by an agent, figures exist only as you state or report them with computed figures shown in parts, and statuses change only on your dated report. The kit's agents use only the fictional worked example named in this listing to show the formats end to end — not a customer story. You check every output before you rely on it.

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: $49 — Standalone: all 4 agents, everything included.

Starters (ONE agent, your choice of any of the 4) are $19 each — separate listings below. Starter owners complete the set with the Upgrade, $30 — the difference.