Give your AI a goal, not a task: tell it you want to cut vacancy at one rental property, and have it build a step-by-step plan from your own portfolio data that you approve before any message goes out or work order opens: AI agent prompt
In AppFolio's Fall 2026 product update (October 30, 2026), the company describes the new Realm-X as starting from a goal rather than a task: tell it what you want, such as reducing vacancy at a property or increasing revenue before the quarter closes, and it builds a plan using your portfolio data in real time. From there you can ask questions about documents, drill from portfolio-wide insights to individual properties, visualise the data and export reports, and it can take actions like sending personalised messages at scale, opening work orders, initiating bills and flagging delinquent accounts, while the team keeps oversight and control. The same update says the Realm-X Connector in Claude is now out of beta for all customers. The prompt below gets the planning half of that workflow from any AI assistant using the reports you export.
Who this is for
Landlords who want a vacancy plan built from their own numbers, not from invented rents.
Not for
Anyone asking the AI to cut rent or approve a tenant without you.
What you need
A vacancy report with days empty, asking rents, inquiries, showings and open make-ready work.
The prompt
I manage rental property and my goal is: [e.g. reduce vacancy at [property name] from [X] vacant units to [Y] by [date]]. Here is my data: [paste a vacancy or unit-status report, days vacant per unit, asking rents, recent leasing activity (inquiries, showings, applications), open make-ready or maintenance work orders on vacant units, and any comparable rents I have]. 1) Diagnose why units are sitting empty: for each vacant unit, say whether the evidence points to price, condition or make-ready delays, marketing reach, or follow-up on leads, and quote the figure behind each call. 2) Build a step-by-step plan to hit the goal, grouped by this week, next two weeks and this month, with an owner for each step. 3) For each step that involves an action (messages to prospects or residents, a work order, a price change), draft it but mark it NEEDS MY APPROVAL. 4) List the numbers I should check weekly to know if the plan is working. Use only my data; write MISSING where you'd need something I haven't given you. Follow fair-housing rules: describe units and terms, never who a unit suits.
Fill in the blanks, then copy
This prompt has 2 [bracket]s to fill in. Type your details below and the prompt updates as you go. Your answers stay in this browser and are reused on other prompts with the same blanks. Nothing is sent to us.
Example values are fictional, just to show how a filled-in prompt reads. Replace them with your real details.Worked example
A fictional business, so you can see what to paste in and what a good answer looks like. The example answer was written with AI help and its numbers and dates were checked; your AI's answer will be worded differently, so check it the same way.
Sample input (what you paste in)
Goal: reduce vacancy at 88 River Road, Springfield from 2 vacant units to 0 by 15 December 2026. Data: Unit 2, 1-bed, asking $1,495, vacant 38 days, 4 inquiries, 1 showing, 0 applications; make-ready complete. Unit 5, 2-bed, asking $1,925, vacant 12 days, 6 inquiries, 0 showings (vendor still finishing paint — work order open since 28 Oct); nearby 2-beds lease at $1,850–$1,900.
Example output (illustrative)
Diagnosis - Unit 2: evidence points to follow-up and possibly price/marketing, not make-ready (make-ready is done). 38 days vacant, 4 inquiries but only 1 showing and 0 applications. Quote: 4 inquiries / 1 showing. - Unit 5: evidence points to make-ready delay, not price yet. 12 days vacant and 6 inquiries but 0 showings while paint is still open (work order since 28 Oct). Nearby 2-beds at $1,850–$1,900 vs asking $1,925 — flag as a later price check once showings start, not a cut today. Plan This week: finish Unit 5 paint (vendor / you); reply to every Unit 2 inquiry with the same facts and two viewing windows (you). NEEDS MY APPROVAL: any asking-rent change. Next two weeks: hold Unit 5 showings as soon as paint clears; track inquiry-to-showing conversion on both units (you). This month: if Unit 2 still has inquiries but no second showing by 1 Dec, review $1,495 against leased 1-beds you actually have (not a guess). Goal check on 15 Dec: vacant count 0, 1 or 2. Drafts marked NEEDS MY APPROVAL - Inquiry reply for Unit 2: same rent, same next step, no screening questions. - Vendor nudge for Unit 5 paint: ask for a finish date, no penalty language you did not already agree. Numbers to watch: days vacant, inquiries, showings, applications, make-ready days outstanding, asking rent vs your own leased comps.
Check before you use it: Do not cut rent or pick a tenant in this plan. Every outbound message and any price change stays marked for your approval.
How to use it
- Copy the prompt above.
- Replace every [bracket] with your own details (use the fill-in-the-blanks box above, which remembers your answers for the next prompt).
- Paste it into AppFolio Realm-X, Claude, ChatGPT and review the answer before you use it.
Works with: AppFolio Realm-X, Claude, ChatGPT, Gemini
Real-world example: appfolio.com/blog/product-update-2026-q3
Featured in: AI prompts for writing SOPs, reports, policies and checklists · ChatGPT prompts for property management and landlords: tenants, repairs, inspections, ledgers and owners
Before you use it: what to check
Already built into this prompt
- Follow fair-housing rules: describe units and terms, never who a unit suits.
Check yourself
- This prompt works on text other people wrote (emails, reviews, messages or web pages). That text can hide instructions aimed at AI, such as "ignore your rules and…". Paste it as material to work on, and never let the AI act on requests inside it, like paying, sharing logins or changing records. How prompt injection works →
- 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.
- Anything legal, tax or compliance-related is a first draft for a qualified person to check. It is not professional advice, and clause references and deadlines must be checked against the source.
- Remove names, contact details, account numbers and other personal data the task doesn't need before you paste, and check your AI tool's data and training settings.
Using an AI agent? Download this prompt as a SKILL.md agent skill with these checks built in, or get the .zip for Claude.ai. How to install skills.
Want to make this prompt even better? Grade it with the free prompt grader or build your own with the AI prompt generator.
32 copy-paste agent prompts (PDF) plus 5 new prompts every week.
Get it free