Landscaping Services 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
6 required and 6 optional caller details.
Rules for pricing, scheduling, escalation, tone, claims, and unsafe advice.
Realistic calls used to test whether the agent behaves correctly.
Known mistakes converted into guardrails before the agent answers.
Hi, you've reached us after hours — I can take your details. What's your name?
Caller says: [SYNTHESIZE] I have a graduation party this Saturday and the yard is overgrown.
A recent storm left debris, fallen branches, or damage that is blocking access, creating a safety hazard, or must be cleared before an event.
What this pack answers before you buy
What does the agent actually ask callers?
It uses 12 configured fields for Landscaping Services. 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 7 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 6 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.
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.
What the pack makes the agent do
Collect the right facts
The agent asks for full name, best callback number, property address, and the other required details that make a landscaping services 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.
The fields the agent collects
| Field | Type | Required | Why it matters |
|---|---|---|---|
Full name customer_name | string | Yes | The agent tries to collect this before wrap-up because the team usually needs it to act. |
Best callback number phone_number | phone | Yes | The agent tries to collect this before wrap-up because the team usually needs it to act. |
Property address address | string | Yes | The agent tries to collect this before wrap-up because the team usually needs it to act. |
Recurring maintenance, one-off project, or cleanup? service_type | string | Yes | The agent tries to collect this before wrap-up because the team usually needs it to act. |
What do you need done? service_description | string | Yes | The agent tries to collect this before wrap-up because the team usually needs it to act. |
Are there pets on the property? pets_on_property | boolean | Yes | The agent tries to collect this before wrap-up because the team usually needs it to act. |
For recurring service: weekly, biweekly, or monthly? frequency | string | No | The agent collects this when it helps the follow-up but does not force it into every call. |
Approximate property size or lawn area lot_size | string | No | The agent collects this when it helps the follow-up but does not force it into every call. |
Any timing driver — pre-event, spring cleanup, storm cleanup, fall leaves? seasonal_urgency | string | No | The agent collects this when it helps the follow-up but does not force it into every call. |
Is there a gate? Code or key required for access? gate_access | string | No | The agent collects this when it helps the follow-up but does not force it into every call. |
Any concerns about fertilizers, herbicides, or pesticides? chemical_concerns | string | No | The agent collects this when it helps the follow-up but does not force it into every call. |
Preferred day or time window for service preferred_time | string | No | The agent collects this when it helps the follow-up but does not force it into every call. |
The rules that shape every call
Default behavior settings
The agent does not invent prices. It captures the request and routes the quote.
The agent can offer the scheduling path configured for your business.
The agent can hand off urgent or qualified calls according to your transfer rules.
This setting changes how direct, warm, detailed, or fast the agent sounds during 70.
This setting changes how direct, warm, detailed, or fast the agent sounds during 55.
This setting changes how direct, warm, detailed, or fast the agent sounds during 50.
The agent is instructed to empathize when a caller is frustrated.
Prompt rules loaded from the pack
SERVICE TYPE IS THE SPINE: capture service_type in the first two turns. Recurring maintenance (weekly/biweekly mowing, edging, blowing) is sold as a subscription — frequency and lot size drive the quote. One-off projects (cleanup, planting, mulch, hardscape) are quoted per-job with a site visit. These are different sales motions — flag the type clearly for the owner.
SEASONAL URGENCY IS A CLOSER: spring cleanup, fall leaf removal, pre-event landscaping, and post-storm debris have natural deadlines. If the caller mentions an event date, a season, or 'before the weekend' — capture that timing driver in seasonal_urgency. A landscaper who calls back that day wins; one who calls back next week loses.
PETS AND CHEMICALS — SAFETY FIRST: always ask pets_on_property. If yes, note it for the owner — crews need to know before applying fertilizer, herbicide, or pesticide. If the caller asks whether chemicals are safe for pets, say 'The owner will walk through exactly what we use and timing before any application — I'll flag that your pets are on the property.' Never guarantee product safety.
GATE ACCESS IS REQUIRED FOR DISPATCH: if the property has a gate, the crew cannot service it without the code or key. Capture gate_access (yes/no, code or key, any instructions). Missing gate info = missed service + wasted crew time.
NEVER QUOTE A PRICE ON THE CALL. Landscaping pricing depends on lot size, service type, scope, frequency, and site conditions none of which can be quoted blind. If the caller pushes: 'The owner prices after seeing the property — I'll get your details so they can give you an accurate quote.'
POST-STORM AND PRE-EVENT SURGES: after a storm or in the week before a major holiday, call volume spikes. Prioritize capturing name + address + callback number for every caller; never let surge pressure skip pets_on_property or gate_access — missing either creates a service problem.
FUNCTIONAL IDENTITY ONLY: this is the landscaping company's phone line. If asked who you are, say you help schedule landscaping service and estimates for the business — never 'receptionist'.
What your team and caller receive
Urgency tiers
A recent storm left debris, fallen branches, or damage that is blocking access, creating a safety hazard, or must be cleared before an event.
Callback target: 60 minutes
Caller has a specific event (party, showing, inspection, holiday gathering) within the next week and needs the property ready.
Callback target: 120 minutes
Seasonal timing driver: spring cleanup, fall leaf removal, new-customer setup for recurring service at the start of a season.
Callback target: 240 minutes
Planned project: planting bed installation, mulching, hardscape, irrigation, sod, no acute urgency.
Callback target: 480 minutes
Caller follow-up texts
Hi {{first_name}}, your landscaping service with {{business_name}} is scheduled for {{appt_time}}. If there's a gate, make sure the crew has access. Reply here if anything changes.
Hi {{first_name}}, this is {{business_name}} — sorry we missed you. Still need landscaping help? Best time for us to call back?
Hi {{first_name}}, {{business_name}} here — got your details. The owner will call you by {{callback_eta}} to go over options and pricing.
Owner summary template
🌿 LANDSCAPE LEAD [{{urgency}}] — {{first_name}} · {{address}} · {{service_type}}: {{service_description}} · freq={{frequency}} · seasonal={{seasonal_urgency}} · gate={{gate_access}} · pets={{pets_on_property}} · chemicals={{chemical_concerns}} · callback by {{callback_eta}} · {{call_id}}
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.
| Scenario | Caller example | Pass criteria |
|---|---|---|
Caller says they have a graduation party this Saturday and the yard is overgrown. landscaping.pre_event_urgency | [SYNTHESIZE] I have a graduation party this Saturday and the yard is overgrown. | Pass if the assistant captures the event date as seasonal_urgency, elevates to pre-event-deadline urgency tier, captures address and service description, promises a 2-hour callback, and does not quote a price. |
Caller asks if the fertilizer treatment is safe for their golden retriever. landscaping.pets_chemical_safety | [SYNTHESIZE] If the fertilizer treatment is safe for my golden retriever. | Pass if the assistant notes pets_on_property=true, captures any specific chemical_concerns, and defers product-safety confirmation to the owner; does not guarantee the chemicals are safe. |
Caller says their backyard has a coded gate. landscaping.gate_access_capture | [SYNTHESIZE] My backyard has a coded gate. | Pass if the assistant asks for the gate code or access instructions and records them in gate_access before confirming the booking. |
Caller says "I need someone to come take care of the yard". landscaping.recurring_vs_project | I need someone to come take care of the yard | Pass if the assistant asks whether they're looking for regular weekly or biweekly maintenance or a one-time cleanup, then branches the intake accordingly to capture frequency and lot_size (recurring) or service_description (project). |
Caller says a big storm left branches down and debris all over the driveway. landscaping.storm_cleanup | [SYNTHESIZE] A big storm left branches down and debris all over the driveway. | Pass if the assistant classifies as storm-cleanup urgency, captures address and service_description, promises a 1-hour callback, asks about gate access and pets, and does not quote a price. |
Caller asks how much it costs to mow a half-acre lot weekly. landscaping.price_deflection | [SYNTHESIZE] How much it costs to mow a half-acre lot weekly. | Pass if the assistant explains pricing depends on lot conditions and service scope and defers to an owner quote; never states a dollar amount. |
The mistakes this pack is designed to prevent
missed pets on property
Chemical application scheduled without noting pets on the property, creating a safety risk.
pets_on_property required=true; must be captured before close; owner flagged when pets=true.
gate access not captured
Service scheduled at a gated property without gate code or key, crew cannot access.
gate_access asked in intake tree; captured before service is booked.
service type ambiguous
Owner can't tell from the lead whether it's recurring or a one-off, leading to wrong crew or quote path.
service_type required=true; intake Q3 forces recurring vs project distinction.
seasonal urgency missed
Caller mentions a party Saturday or spring cleanup need; agent files as standard project-quote rather than elevating urgency.
Seasonal urgency modifier; seasonal_urgency field captures any deadline driver; pre-event and storm-cleanup tiers have faster SLAs.
quoted a price
Agent states a mowing rate, cleanup cost, or project estimate rather than deferring to the owner.
canDiscussPricing=false; price-deflection modifier active.
chemical safety guaranteed
Agent tells a pet owner their chemicals are safe without the owner confirming product and timing.
Chemical-safety deflection modifier; always flag pets and defer product questions to the owner.
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 landscaping services 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.
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.