--- name: al-403-let-an-ai-receptionist-answer-your-tenants-texts-from-the description: "Every tenant text about a late fee, a repair update or a lease renewal date turns into another task for a property manager, and many arrive at night or on weekends. On Oct 29, 2026 DoorLoop, which calls itself agentic property management software, made its Receptionist Agent available to customers on its Connect and Multiply plans, unveiled at the NARPM Annual Convention in Las Vegas. It handles tenant SMS and portal messages around the clock (voice and email are coming soon), answers from lease terms, account balances, property information and open work orders, follows each company's own policies on things like late fees, pet restrictions and maintenance responsibilities, replies in the tenant's preferred language with an English translation for the manager, and escalates sensitive, exceptional or out-of-policy requests with the conversation history, records and reason attached. DoorLoop says every agent action is logged in plain language, can be walked back from that log (messages…" --- # Let an AI receptionist answer your tenants' texts from their actual lease, balance and open work orders: write the house rules it follows, and the cases it must hand to you with the history attached Every tenant text about a late fee, a repair update or a lease renewal date turns into another task for a property manager, and many arrive at night or on weekends. On Oct 29, 2026 DoorLoop, which calls itself agentic property management software, made its Receptionist Agent available to customers on its Connect and Multiply plans, unveiled at the NARPM Annual Convention in Las Vegas. It handles tenant SMS and portal messages around the clock (voice and email are coming soon), answers from lease terms, account balances, property information and open work orders, follows each company's own policies on things like late fees, pet restrictions and maintenance responsibilities, replies in the tenant's preferred language with an English translation for the manager, and escalates sensitive, exceptional or out-of-policy requests with the conversation history, records and reason attached. DoorLoop says every agent action is logged in plain language, can be walked back from that log (messages already sent stay sent), and starts by asking for approval before it acts, with operators deciding how much autonomy each agent earns. The prompt below writes the rulebook such an assistant needs, whichever software you use. ## Inputs to collect first Ask the user for anything below that they haven't already given you. Don't guess missing facts. - City/region - Property management software - E.g. late fees, rent balance, repair status, lease renewal dates… - Second language ## Instructions Do the task below with the user's inputs in place of each [bracket]. Help me write the rulebook for an AI assistant that will answer my tenants' texts and portal messages. I manage [number] units in [city/region], using [property management software]. Tenants usually ask about: [e.g. late fees, rent balance, repair status, lease renewal dates, parking, pets]. 1) Ask me for my actual policies on each topic (late fee amount and grace period, pet rules, who pays for which repairs, renewal notice period, quiet hours) and turn them into short, plain rules the assistant must quote, not improvise. 2) List the facts it should look up before replying (lease terms, current balance, open work orders) and say what it should do if a record is missing or looks wrong. 3) Write the escalation list: messages it must never answer alone (e.g. disputes, legal threats, harassment, emergencies like gas or flooding, fee waiver requests, anything about discrimination or accessibility) and the hand-off note format (tenant, unit, summary, records checked, reason). 4) Set the approval levels: what it may send on its own from day one, what it drafts for my yes, and what would make me pull back its autonomy. 5) Write 3 sample replies, one in [second language], and 5 test messages I can send to check it follows the rules. Keep tenant replies short and polite. ## 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. - 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. - Read and edit the draft before it reaches a customer or goes public. If you later automate this prompt, start with "draft and notify me", not "send automatically". - Say clearly which parts need a person to review or approve before anything is sent, paid, posted or filed. ## About this skill - Works with: ChatGPT, Claude, Gemini, DoorLoop - Based on this real-world example: https://www.prweb.com/releases/doorloop-launches-receptionist-agent-that-resolves-tenant-requests-247-not-just-answers-them-302923728.html - Free prompt from AgentPlaybook Real Estate: https://agentic-library.netlify.app/prompt/al-403-let-an-ai-receptionist-answer-your-tenants-texts-from-their/ - 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/