Listing & Transaction Studio — AI Task Kit (4 Agents)

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

Not a prompt pack and not a CRM — a filled, faithful Listing & Transaction Book: your fact sheets recorded line by line, your comp sheets pasted and recomputed with the parts shown, your clients recorded in your own words, your milestones tracked with their sources, and every deliverable gated by a named completeness check, kept current every time a fact changes. Works with the AI you already have: upload one file, tell it "Start", answer a few questions, and the Book starts filling with YOUR listings and transactions.

This is not a prompt pack. Four specialist agents fill one Listing & Transaction Book with your facts — your fact sheets, your pasted comp figures, your client notes in your words, your sourced milestones — check each deliverable against a named completeness gate, and keep the whole Book current when a price is restated, a comp is corrected, or a status is reported. Nothing in the Book is invented, no price is ever opined, and nothing leaves it as a send.

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 (one agent at a time, 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 — your listing's fact sheet exactly as you have it, the price you are stating in your words, the comps as you paste them. That's the calibration, and it's what makes the Book fit YOUR practice.

4. Save the complete updated Listing & Transaction 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 listings.

Use the agents in order:

1. Listing Writer — the Book's voice, under trace discipline, and the kit's lead agent. It opens the shared My Listing & Transaction Book and its cover page, owns the fact-sheet record per listing, and writes all listing copy — every output with its claim-trace table, so each descriptive claim in the copy maps to a specific fact-sheet line you supplied, and any claim with no source line is listed as untraced instead of slipping in. It runs the fair-housing drafting screen on every output before style: the kit's guardrails are drafting rules for how the kit writes — not legal advice, and not a certification that any output complies with any law. It touches no external route at all.

2. Comp & Pricing Analyst — arithmetic only: no value opinion, no recommended price, no range — the Book's arithmetic. It keeps a register of comp figures you paste only, each with its source and recording date; $/sq ft is recomputed with the parts shown. If a sheet's printed figure disagrees with the recomputation of its own parts, both figures are printed and the disagreement is flagged — never resolved, never explained, and never attributed to any cause. A line you did not supply is printed as NOT SUPPLIED — never filled from another comp, the subject, or a pattern. It touches no external route at all.

3. Client Care Coordinator — the Book's people record. It records clients and leads in your exact words, with statuses only as you report them, dated; builds follow-up drafts only from the recorded notes you name for each draft; and builds showing-prep checklists only from the showing facts you supply. It characterises no client and infers no intention. Its one external write is creating its own approved drafts in your own Gmail drafts, where that route verifies in-session — a draft, never a send.

4. Transaction Coordinator — the Book's clock and closing record. This is an AI agent that tracks a record — not a human transaction-coordinator service. It keeps the milestone tracker — each milestone with its date, its source, and its status only as you report it — files contract excerpts exactly as pasted and never interprets them, drafts questions for your broker or lawyer, and builds the closing checklist from the items you dictate. It is also the kit's only calendar writer and its only Todoist exporter, each under its own exact-approval gate.

One Listing & Transaction Book, nothing invented. All four agents work from the same shared My Listing & Transaction Book — your calibration for all four agents, your fact sheets and stated prices with their sources, your pasted comp sheets, your client and lead record in your words, your showing facts, your milestones with their sources, your contract excerpts as pasted, your open "To confirm" list, and the change log exist once, in one place. No listing copy, comp table, queue, tracker, or checklist 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 SUPPLIED — never completed from a pattern, never given a plausible feature, figure, or date.

What this kit does NOT do — stated plainly, not in fine print. This kit books nothing, sends nothing, posts nothing, and submits nothing — no showing, no message to a client or anyone else, no listing to any portal, in either mode, at any level of insistence. Every outbound text it prepares — a follow-up, a question about a comp disagreement, a question for your broker or lawyer — is a draft: the agent shows you the exact text, you approve that exact text, and you send it yourself. Where a Gmail draft route verifies in a session, the Client Care Coordinator or the Transaction Coordinator may create a draft in your own Gmail drafts, after you approve that exact text — a draft, never a send: no send tool exists in this kit. It states no valuation opinion, no recommended list price, no asking-price range, and no adjustment to any comp — its comp work is arithmetic only, on figures you paste, and the pricing decision stays yours as the licensed agent. It gives no legal advice, interprets no contract clause, and states no jurisdiction's forms, deadlines, disclosure duties, or rules — a question like that becomes a drafted question resting on your recorded facts, for your broker or lawyer. Its fair-housing guardrails are drafting rules, not legal advice and not a compliance certification. It generates no leads and runs no campaign.

Complete, or declared incomplete — the four completeness gates. Each of the kit's four main deliverables runs a named completeness check against your recorded Book before it is presented as finished, and the result is printed with the deliverable: GATE-L for listing copy, GATE-C for the comp table, GATE-F for the follow-up queue, and GATE-T for the transaction tracker and closing checklist. The listing check requires every claim in the copy traced to its fact-sheet line, every untraced claim listed, and the drafting-screen result recorded; the comp check requires every recorded comp printed, every $/sq ft recomputed with parts shown, every disagreement flagged both ways, and every missing line shown as NOT SUPPLIED; the queue check requires every recorded client row with its reported status and date, and nothing characterised or ranked; the transaction check requires every recorded milestone with its source in its row, no status completed by a date passing, excerpts reproduced as pasted, and the To Confirm list printed, never hidden. If you ask for "just the highlights," the check still runs and still fails by name: a short version may be produced only as a separate extract labelled with the failed gate and its gaps named — it is never titled, formatted, or sold to you as the deliverable. The complete deliverable remains the offer.

Figures and dates are arithmetic, not atmosphere. Every weekday in the Book is derived from its date, every interval is recomputed, and every $/sq ft is recomputed on the page with its parts shown. Any figure in the Book is a figure you pasted or stated, exactly as supplied, with its source: a line you did not supply is printed as NOT SUPPLIED, never treated as zero and never estimated; a printed figure that disagrees with its own parts stands beside its recomputation with the difference flagged — the kit does not silently prefer either, does not explain the difference, and does not attribute it to any cause. No average of comps is computed or printed anywhere in this kit.

Your Book holds other people's information — the privacy stance. The Book holds your clients' and leads' names and your notes about them, unclosed-transaction terms, and your pricing worksheets. The agents never publish, post, or share your Book anywhere; client detail appears outside the Book only inside the exact draft text you approved, as that draft's purpose requires — and you send that draft yourself. Passwords, account numbers, and access details (alarm codes, lockbox codes, key locations) are never recorded in the Book at all. Keep the Book where only the people you choose can see it, share only the part a person needs — a person who needs the comp table never needs the client register — and know 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.

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 Listing & Transaction Book as a real file under git, with a commit before the first edit and one per verified step; the Transaction Coordinator — the kit's only calendar writer — can create an event on your own calendar only, as the exact block you approved, one by one, with no invitees by default (an invitee is added only when you name that invitee and approve that exact block including the invitee list), and can mirror your own recorded milestones and checklist items into Todoist where that route is available, with your approval per export and the Book remaining the source of truth, task titles carrying no client-identifying detail by default. Where a Gmail draft route verifies in a session, the Client Care Coordinator or the Transaction Coordinator may create its own draft in your own Gmail drafts, after you approve that exact text — a draft, never a send: nothing is sent, in either mode. The Listing Writer and the Comp & Pricing Analyst — arithmetic only: no value opinion, no recommended price, no range — create no draft, no calendar event, and no task export in either mode. 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. No real-estate platform is connected at all. There is no integration, sync, checking, or login with Follow Up Boss, kvCORE, Zillow, Redfin, or any MLS, in either mode — no agent route into any of them is claimed — and the agents prepare copy-ready artefacts for you to carry into whatever system you already use. Any line implying this kit sends your messages, posts your listings, or syncs with a CRM, MLS, or portal would be wrong, and no agent in this kit will make that claim.

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 Listing Writer you answer its 7 questions one at a time and reach the first milestone: the Book opened — its cover with you as you stated yourself, the listing address exactly as supplied, the fact-sheet lines exactly as supplied, your stated list price with its recomputed $/sq ft labelled as arithmetic on your stated price, anything missing shown as "To confirm" — plus claim-traced listing copy, a change log opened with its first entry, and one faithful first entry demonstrated live: paste one real thing and receive it back recorded exactly as supplied. That is the first session — not a filled pipeline. The comp table, the queue, and the tracker come step by step after that, from the Book you build.

The worked example: the materials walk one complete fictional example end to end — Dana, a licensed solo agent, opening her Book on Monday 2027-03-15 for 14 Maple Court, its fact sheet holding exactly four supplied lines (3 bed, 2 bath, 1,840 sq ft, and the address), her stated list price of $565,000 recomputed to $307.07/sq ft and labelled arithmetic on her statement; Comp A, 22 Maple Court, pasted at $548,000 and 1,790 sq ft — recomputed $306.15/sq ft beside the $310.00/sq ft her sheet itself prints, the $3.85/sq ft difference flagged and never attributed to any cause (inside that flag only, the printed figure's implied $554,900 total and its $6,900 difference from the pasted price are shown to size the disagreement — never as a price); Comp B, 9 Birch Lane, pasted at $592,500 and 1,925 sq ft — recomputed $307.79/sq ft, its garage line NOT SUPPLIED and never filled from Comp A; the differences printed as arithmetic only (+$17,000 and −$27,500 on price, +50 and −85 sq ft on area) with no conclusion drawn; a request to add a renovated kitchen the fact sheet does not hold, listed as untraced and kept out of the copy; a sellers' request for characterising language about the neighbourhood, refused under the drafting guardrails with no softened synonym substituted; and a transaction record of six sourced milestones — contract Monday 2027-03-29, inspection deadline Friday 2027-04-09, appraisal due Thursday 2027-04-15, financing deadline Thursday 2027-04-22, final walkthrough Thursday 2027-04-29, closing Friday 2027-04-30 — none of them reported complete, with the contract-to-closing interval recomputed at 32 days — so you can see every format before you build your own. Your Book gets your own material; the example is there to show the shapes. Dana is a fictional example created for this kit — not a customer story.

If a legal or deadline question comes up: if you ask what a contract clause means, whether a deposit is at risk, or what a deadline legally requires, the agent stops, reproduces the excerpt exactly as you pasted it, gives no answer and no reassurance, and drafts the question — resting on your recorded facts — for your broker or lawyer, filed in the Book unanswered. It never sends that question, never states a rule for your jurisdiction, and never confirms a rule you suggest.

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 Listing & Transaction 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 — fact sheets and stated prices, comp sheets and disagreement flags, claim traces, the client and lead record, showing facts, milestones and excerpts, broker/lawyer questions, drafts logged as drafts, the open-items list, the connected-mode record, gate results, and the change log

- Prompt Sheet — the exact phrases to say to each agent, for every job, including the approval phrases for calendar entries, Todoist exports, and draft creation (there is no approval phrase for a send — this 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

- Troubleshooting & FAQ — a claim that is not on the fact sheet, a comp figure that came back "corrected", a status that changed without your report, a clause that came back paraphrased: the known rough edges and their fixes

- Changelog — what changed in this version

Who it's for:

- A licensed solo agent or small-team agent whose paperwork lives in several places at once — fact sheets in one document, comp sheets in another, client notes on a phone, transaction dates across emails — and who needs one Book built from those materials, with any disagreement between their own papers shown to them instead of quietly smoothed over

- Agents who write their own listing copy and want every claim in it traceable to a fact they actually hold, screened by drafting guardrails before it goes anywhere

- Agents whose facts change mid-listing or mid-transaction — a restated price, a corrected comp, a reported status — and who want the Book re-issued from the updated facts, with every change logged, instead of documents drifting apart

Who it's NOT for:

- Anyone looking for a CRM, an MLS or portal integration, a lead-generation service, or software that sends, posts, or submits anything for them — this kit is instruction files for your AI, plus the Book work you direct and check

- Anyone who wants an agent to say what a home is worth, recommend a list price, adjust a comp, interpret a contract, or state what their jurisdiction's forms or deadlines require — those calls belong to you as the licensed agent and to your broker or lawyer; the kit records your facts, does the arithmetic, and drafts your questions

- Anyone who wants a Book that looks complete whether or not the facts are in — an incomplete record is delivered with its gaps showing, and a completeness gate that fails is stated, never waived

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 — your fact sheets exactly as you have them, your comp sheets as you receive them, your notes on clients and leads in your words, your showing facts, and your transaction documents and dates with their sources; the agents use only what you supply, and infer nothing

- A private place to keep the saved Listing & Transaction Book — it holds client information, unclosed-transaction terms, and pricing worksheets, 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 a real-estate service, and not a human agent service. Prompt packs for this work exist cheap, and generic listing prompts are easy to find free; what this kit adds is the Book those prompts never build — filled only from your supplied facts, with every listing claim traced to its source line, every figure recomputed with its parts shown, every deliverable passing a named completeness gate, and the whole record kept current by re-issue and change log when your facts change. What the agents can do depends on where you run them: in a chat-only AI they guide and draft — 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 they 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; calendar work is an approved event on your own calendar with no invitees by default, created by the Transaction Coordinator only, where that route verifies, and a copy-ready block everywhere else; a Todoist mirror is created only by the Transaction Coordinator, only where that platform offers the route, and the Book stays the source of truth; and every message is a draft in both modes — where a Gmail route verifies, a draft may be created in your own Gmail drafts only, by the Client Care Coordinator or the Transaction Coordinator, each its own, and a draft is never reported as a send, because nothing in this kit is ever sent by an agent. No CRM, MLS, or portal is integrated in any mode. The kit's boundary holds in both modes: the Book is built only from what you supply, unknowns are printed as "To confirm", figures are held only as pasted and recomputed with their parts shown, no value opinion, recommended price, range, or adjustment is ever stated, no contract is interpreted and no jurisdiction rule is stated, fair-housing guardrails operate as drafting rules and never as legal advice or a compliance certification, statuses change only when you report them, and a confirmed change re-derives everything resting on it and flags what it conflicts with instead of rewriting the record. The agents' worked example, Dana, is an illustration created for this kit 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.