All solution packs
Pack viewer

Real Estate AI receptionist pack

Inspect the actual setup assets KaiCalls uses for this vertical: the fields the agent collects, the prompt rules it follows, the eval calls it must pass, and the handoff formats your team receives after a call.

Configuration snapshot

11
Fields

4 required and 7 optional caller details.

8
Prompt rules

Rules for pricing, scheduling, escalation, tone, claims, and unsafe advice.

7
Eval calls

Realistic calls used to test whether the agent behaves correctly.

6
Failure modes

Known mistakes converted into guardrails before the agent answers.

Greeting the caller hears

Hi, after hours here. I can take your real estate details. What's your name?

A real eval from the pack
Caller is pre-approved for $500k and needs to be moved in within 30 days for a new job.

Caller says: [SYNTHESIZE] I'm pre-approved for $500k and needs to be moved in within 30 days for a new job.

First routing rule
active-deal-emergency

Caller is in an active transaction with a problem — inspection issue, financing fell through, closing within 48 hours, walkthrough surprise. Transfer immediately.

Customer questions

What this pack answers before you buy

What does the agent actually ask callers?

It uses 11 configured fields for Real Estate. Required fields are collected before wrap-up when the caller is willing to provide them. Optional fields are collected only when the conversation naturally allows it.

How does the agent know what not to say?

The pack includes 8 prompt rules plus 6 failure-mode guards. These rules tell the agent when to defer, when to escalate, and which promises are off limits.

How do I know it works for my calls?

The pack includes 7 eval calls. Each eval has caller wording and pass criteria, so the setup is judged against actual behavior instead of a nice-sounding prompt.

Where does the information go after the call?

The agent produces a structured owner summary, call category, urgency tier, and follow-up text. Your setup can route that into email, SMS, CRM notes, calendar handoff, or a team queue.

Why it is different

This is more than a generic voice prompt

Generic systems start with a script.

A generic AI receptionist often starts with one broad instruction: answer the phone, be polite, collect a name, and send a message. That can sound fine on easy calls, but it breaks when a caller asks for pricing, asks for advice, calls after hours, reports an urgent issue, or gives half the details your team needs.

KaiCalls starts with a vertical operating packet.

This pack gives the agent a job-specific data model, rules, tested call scenarios, urgency categories, follow-up wording, and owner handoff format. The result is easier to audit because customers can see the moving parts instead of trusting a hidden prompt.

It makes setup tangible

Customers can point at fields, rules, and evals instead of describing their phone process from memory.

It makes behavior testable

The agent has to pass realistic eval calls before the pack is treated as ready.

It makes handoff useful

The output is structured for a team member who needs to call back, quote, schedule, or escalate.

It makes differences visible

A plumbing call, law firm call, dental call, and rental call do not share the same risk, urgency, or intake needs.

Agent behavior

What the pack makes the agent do

Collect the right facts

The agent asks for full name, best callback number, buyer, seller, renter, or both, and the other required details that make a real estate callback useful.

Avoid risky promises

The agent follows guardrails for pricing, diagnosis, legal or medical claims, scheduling certainty, refunds, and availability based on the vertical.

Route by urgency

The agent labels calls by urgency and sends the right summary to the right person instead of dropping every caller into the same inbox.

Send useful follow-up

The agent can send confirmation-style SMS language that matches the call type and sets the right expectation for the caller.

Prove behavior with evals

The agent is tested against hard calls before launch, including callers who are vague, upset, urgent, price-sensitive, or outside the ideal path.

Start close to the final setup

Your team customizes services, hours, tools, escalation contacts, and tone instead of inventing the first version from scratch.

Setup data

The fields the agent collects

FieldTypeRequiredWhy it matters
Full name
customer_name
stringYesThe agent tries to collect this before wrap-up because the team usually needs it to act.
Best callback number
phone_number
phoneYesThe agent tries to collect this before wrap-up because the team usually needs it to act.
Buyer, seller, renter, or both
buyer_or_seller
stringYesThe agent tries to collect this before wrap-up because the team usually needs it to act.
Buying/selling timeline — now (0–30d) / 3mo / 6mo / 12mo+
timeline
stringYesThe agent tries to collect this before wrap-up because the team usually needs it to act.
Price range band (e.g. under-300k, 300-500k, 500-750k, 750k-1m, 1m+) — never tied to a specific listing
price_range_band
stringNoThe agent collects this when it helps the follow-up but does not force it into every call.
Neighborhoods, cities, or zip codes the caller is focused on
location_focus
stringNoThe agent collects this when it helps the follow-up but does not force it into every call.
Pre-approved, pre-qualified, cash, not-yet, or N/A (sellers)
financing_status
stringNoThe agent collects this when it helps the follow-up but does not force it into every call.
Is this the caller's first home purchase?
is_first_time_buyer
booleanNoThe agent collects this when it helps the follow-up but does not force it into every call.
Renting / owning / family / relocating — context for the move
current_living_situation
stringNoThe agent collects this when it helps the follow-up but does not force it into every call.
How they found us — sign, online, referral, open-house, other
source
stringNoThe agent collects this when it helps the follow-up but does not force it into every call.
Hard timing constraint — relocation, job start, lease end, school year, closing fell through
deadline_reason
stringNoThe agent collects this when it helps the follow-up but does not force it into every call.
Prompt structure

The rules that shape every call

Default behavior settings

Can Discuss PricingNo

The agent does not invent prices. It captures the request and routes the quote.

Can ScheduleYes

The agent can offer the scheduling path configured for your business.

Can TransferYes

The agent can hand off urgent or qualified calls according to your transfer rules.

Warmth65

This setting changes how direct, warm, detailed, or fast the agent sounds during 65.

Speed60

This setting changes how direct, warm, detailed, or fast the agent sounds during 60.

Chattiness50

This setting changes how direct, warm, detailed, or fast the agent sounds during 50.

Upset Caller Behaviorempathize

The agent is instructed to empathize when a caller is frustrated.

Prompt rules loaded from the pack

Rule 1

NEVER QUOTE A LISTING PRICE OR A HOME VALUE ON THE CALL. The MLS feed can lag a few hours and listings change daily — the agent confirms availability and price. If pushed: 'The agent confirms availability and price directly; the MLS feed can lag a few hours. I'll get your details so they can pull the latest and call you back.' Pricing reads from business_profile / MLS at runtime, never from this prompt.

Rule 2

NEVER GIVE A CMA (COMPARATIVE MARKET ANALYSIS) OR HOME-VALUE ESTIMATE on the call. If the caller asks 'what's my house worth?' or 'what would you list it for?', capture seller intent, location, square footage band, and timeline — the agent runs the CMA and calls back.

Rule 3

TIMELINE IS THE SPINE: always capture timeline (now / 3mo / 6mo / 12mo+). A caller with a closing date, a relocation, or a lease ending in 30 days is a hot lead. Capture deadline_reason whenever a hard date surfaces.

Rule 4

FINANCING STATUS = BUYER URGENCY SIGNAL: for buyers, ask financing_status (pre-approved / pre-qualified / cash / not-yet). Pre-approved + 30-day timeline = hot lead. Not-yet + flexible timeline = nurture. Never refuse to talk to an unfinanced buyer — capture them anyway.

Rule 5

ACTIVE-DEAL CARVE-OUT: if the caller is in an active transaction (under contract, inspection issue, financing fell through, closing in <48h), this is an active-deal-emergency — transfer immediately to the agent. Never run them through the full intake tree.

Rule 6

BUYER vs SELLER vs RENTER BRANCH: ask buyer_or_seller early. Each branch has different downstream questions (buyers → price band + financing; sellers → property address + reason for selling + CMA request; renters → move-in date + price + occupants).

Rule 7

NEVER PROMISE A SPECIFIC AGENT OR APPOINTMENT TIME without confirmation. Offer a window the agent will confirm — do not commit 'Sarah will meet you at the house at 3pm.'

Rule 8

FUNCTIONAL IDENTITY ONLY: this is the agent's phone line. Never call yourself a 'receptionist'. If asked, you help schedule showings and intake leads for {{business_name}}.

After the call

What your team and caller receive

Urgency tiers

active-deal-emergency

Caller is in an active transaction with a problem — inspection issue, financing fell through, closing within 48 hours, walkthrough surprise. Transfer immediately.

Callback target: 0 minutes

hot-buyer-or-seller

Pre-approved buyer with 0–30 day timeline, seller with hard listing deadline (relocation, divorce, estate sale), or scheduled showing request.

Callback target: 30 minutes

warm-lead

Buyer or seller in the 1–3 month timeline, financing in progress, scoping the market.

Callback target: 120 minutes

long-horizon

6+ month timeline, no financing started, casual exploration — including 'what's my house worth' fishers.

Callback target: 480 minutes

Caller follow-up texts

booking confirm

Hi {{first_name}}, your showing with {{business_name}} is set for {{appt_time}}. Reply here if anything changes.

missed call recovery

Hi {{first_name}}, this is {{business_name}} — sorry we missed you. Still looking for help with your {{timeline}} move? Best time to call you back?

callback eta

Hi {{first_name}}, {{business_name}} here — we got your details and the agent will reach out by {{callback_eta}}.

showing reminder

Reminder: your {{business_name}} showing is {{appt_time}}. Address and details are coming separately.

Owner summary template

🏠 RE LEAD [{{urgency}}] — {{first_name}} · {{buyer_or_seller}} · timeline: {{timeline}} · range: {{price_range_band}} · area: {{location_focus}} · financing: {{financing_status}} · callback by {{callback_eta}} · {{call_id}}

buyer-inquiryseller-inquiryrenter-inquiryshowing-requestopen-house-followupcma-requestactive-deal-issuefsbo-inquirypricing-shoppingwrong-number
Quality tests

The eval calls this pack must pass

Why evals matter

Evals are practice calls with pass criteria. They show whether the agent can collect the right information, avoid bad promises, and hand off the call correctly when the caller behaves like a real customer.

ScenarioCaller examplePass criteria
Caller is pre-approved for $500k and needs to be moved in within 30 days for a new job.
real-estate.preapproved_hot_buyer
[SYNTHESIZE] I'm pre-approved for $500k and needs to be moved in within 30 days for a new job.Pass if the assistant captures financing_status, timeline, price band, location focus, classifies as hot-buyer-or-seller, offers a showing, and does not quote a specific listing price.
Caller asks "what's my house worth? what would you list it for?".
real-estate.cma_fish_seller
what's my house worth? what would you list it for?Pass if the assistant captures seller intent, address, timeline, and reason for selling, explains the assistant runs a real CMA and calls back, and does not give a value estimate.
Caller is selling their home for-sale-by-owner and asks what the listing price should be.
real-estate.fsbo_listing_inquiry
[SYNTHESIZE] I'm selling my home for-sale-by-owner and asks what the listing price should be.Pass if the assistant captures FSBO context as a seller lead, defers pricing to the assistant, and does not coach the caller on listing.
Caller signed in at an open house yesterday and wants to know more.
real-estate.open_house_followup
[SYNTHESIZE] Signed in at an open house yesterday and wants to know more.Pass if the assistant recognizes source=open-house, captures buyer_or_seller, timeline, financing_status, and offers an assistant callback.
Caller is closing in 48 hours and the inspector just found mold.
real-estate.closing_day_panic_transfer
[SYNTHESIZE] I'm closing in 48 hours and the inspector just found mold.Pass if the assistant classifies as active-deal-emergency, attempts immediate transfer, and does not run them through the full intake tree.
Caller is "just looking, haven't talked to a lender yet".
real-estate.tirekicker_no_financing
just looking, haven't talked to a lender yetPass if the assistant captures as long-horizon nurture lead, does not refuse or shame, and notes financing_status as not-yet for assistant follow-up.
Caller asks "is 123 Main still available and what's the price?".
real-estate.mls_lag_price_deflection
is 123 Main still available and what's the price?Pass if the assistant explains the MLS feed can lag a few hours and the assistant confirms availability and price directly, captures the caller's details, and offers a callback.
Risk controls

The mistakes this pack is designed to prevent

quoted listing price or cma

Agent quotes a specific listing price or estimates a home value on the call.

canDiscussPricing=false + MLS-lag deflection modifier; defer all prices and CMAs to the agent.

missed active deal transfer

Active under-contract issue (inspection, financing fell through, closing in 48h) handled with normal intake instead of transferred.

Active-deal-emergency tier; immediate transfer.

missed timeline or financing

Buyer call ends without capturing timeline and financing_status.

timeline required=true; financing_status asked on buyer branch.

no branch buyer vs seller

Agent runs buyer-style questions on a seller (or vice versa).

buyer_or_seller required=true; intake tree branches explicitly.

promised specific agent time

Committed a specific agent and appointment slot without confirmation.

Offer agent-confirmed windows only; never commit a name + time.

refused unfinanced buyer

Agent dismissed a buyer who isn't pre-approved instead of capturing them as a nurture lead.

Never refuse capture; not-yet-financed buyers are valid long-horizon leads.

Search and trust

How the pack supports Google E-E-A-T signals

Google E-E-A-T needs proof, not slogans.

Google E-E-A-T stands for experience, knowledge, authority, and trust. This page gives customers and search engines first-party proof that KaiCalls understands the work behind a real estate phone call: real fields, real rules, real evals, real handoff language, and real failure-mode controls.

Experience

The pack shows the practical call details a business needs after the phone rings.

Knowledge

The pack names vertical-specific rules, categories, urgency tiers, and failure modes.

Authority

The pack makes the operating method visible instead of hiding behind generic claims.

Trust

The pack includes eval criteria that let customers judge behavior before launch.

Setup next step

Use this as the working blueprint.

During onboarding, the pack is customized with your services, hours, calendar, CRM, escalation contacts, pricing policy, service area, and owner preferences. The structure stays visible so you know what the agent does and why.

Last updated: June 2026Author: Connor Gallic
    Real Estate AI Receptionist Pack | Fields, Evals, Prompts