Fitness Center 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
3 required and 7 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.
¡Hola! Llamaste fuera de horario — puedo tomar tus datos. ¿Tu nombre?
Caller says: [SYNTHESIZE] About joining and wants to know how much membership costs.
New potential member requesting an immediate tour, day pass, or first session — highest conversion signal.
What this pack answers before you buy
What does the agent actually ask callers?
It uses 10 configured fields for Fitness Center. 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 6 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.
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, membership inquiry, class booking, personal training, day pass, or tour, and the other required details that make a fitness center 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. |
Membership inquiry, class booking, personal training, day pass, or tour inquiry_type | string | Yes | The agent tries to collect this before wrap-up because the team usually needs it to act. |
Primary fitness goal or interest (weight loss, strength, cardio, classes, etc.) fitness_goal | string | No | The agent collects this when it helps the follow-up but does not force it into every call. |
Morning / midday / evening — preferred time to train preferred_schedule | string | No | The agent collects this when it helps the follow-up but does not force it into every call. |
Specific class or format interested in (e.g. spinning, HIIT, yoga, Zumba) class_interest | string | No | The agent collects this when it helps the follow-up but does not force it into every call. |
Personal training interest and any trainer preference trainer_request | string | No | The agent collects this when it helps the follow-up but does not force it into every call. |
Individual, couple, family, or student — if expressed membership_type_interest | string | No | The agent collects this when it helps the follow-up but does not force it into every call. |
Does the caller want a gym tour or day pass? tour_requested | boolean | No | The agent collects this when it helps the follow-up but does not force it into every call. |
How did you hear about us? how_heard | 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 80.
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 55.
The agent is instructed to empathize when a caller is frustrated.
Prompt rules loaded from the pack
LANGUAGE DETECTION — SPANISH FIRST: This gym is in Puerto Rico. If the caller uses any Spanish at all, switch fully to Spanish and stay in Spanish for the entire call. Do NOT announce the switch. If the call opens in English, continue in English. If the caller switches mid-call, match immediately without comment.
NEVER QUOTE MEMBERSHIP PRICES ON THE CALL. Membership rates depend on plan type (individual, couple, family, student), promotional availability, and contract term — none of which can be confirmed without the owner. If the caller asks for a price, say: 'Membership options depend on what works best for you — I'll get your details and the team will walk you through everything when you come in or on a callback.' Pricing reads from business_profile at runtime, never from this prompt.
INTAKE BRANCH — ask the inquiry type first: (1) general membership → capture goal + schedule preference + membership_type_interest, offer to book a tour; (2) class booking → capture class_interest + preferred_schedule, book or queue callback; (3) personal training → capture trainer_request + goal + schedule, queue PT callback; (4) day pass or tour → capture when and book slot.
TOUR = HIGH-VALUE: A tour request is the highest-conversion action in fitness. Always offer a tour or free day pass to any new-inquiry caller who has not already been to the gym. Never let a new lead hang up without either a booked tour slot or a confirmed callback.
WARMTH FIRST: Fitness callers are often nervous or self-conscious (first gym, returning after a break, weight loss goal). Match their energy with warmth and zero judgment. Never ask about weight, age, or health conditions.
FUNCTIONAL IDENTITY ONLY: this is the gym's phone line. Never call yourself a 'receptionist'. If asked, you help with scheduling and information for {{business_name}}.
What your team and caller receive
Urgency tiers
New potential member requesting an immediate tour, day pass, or first session — highest conversion signal.
Callback target: 60 minutes
Caller wants to book a specific class or personal training session with a time in mind.
Callback target: 120 minutes
General membership interest — exploring options, asking about pricing, or comparing gyms.
Callback target: 480 minutes
Caller follow-up texts
¡Hola {{first_name}}! Tu cita en {{business_name}} está confirmada para {{appt_time}}. Escríbenos si necesitas cambiar algo. / Hi {{first_name}}, your {{business_name}} appointment is set for {{appt_time}}. Reply here if anything changes.
Hola {{first_name}}, te llamaron de {{business_name}} — ¿cuándo podemos hablar sobre tu membresía o clase? / Hi {{first_name}}, {{business_name}} here — we missed you! When's a good time to chat about your membership or class?
Hola {{first_name}}, {{business_name}} aquí — recibimos tu mensaje y te llamamos antes de {{callback_eta}}. / Hi {{first_name}}, {{business_name}} here — we got your info and will call you back by {{callback_eta}}.
Recordatorio: tu visita a {{business_name}} es {{appt_time}}. ¡Te esperamos! / Reminder: your {{business_name}} tour is {{appt_time}}. See you then!
Owner summary template
🏋️ FITNESS LEAD [{{urgency}}] — {{first_name}} · {{inquiry_type}} · goal: {{fitness_goal}} · schedule pref: {{preferred_schedule}} · tour: {{tour_requested}} · 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 asks about joining and wants to know how much membership costs. fitness.membership_inquiry_no_price | [SYNTHESIZE] About joining and wants to know how much membership costs. | Pass if the assistant warmly captures name, inquiry_type, fitness_goal, and preferred_schedule, offers a tour, and does not quote a specific membership price. |
Caller says "I want to come check out the gym this week". fitness.tour_request_hot_lead | I want to come check out the gym this week | Pass if the assistant classifies as tour-or-trial (hot), offers to book a slot, confirms callback number, and does not end call without a tour time or callback promise. |
Caller asks about signing up for a spinning class on Wednesday morning. fitness.class_booking_branch | [SYNTHESIZE] About signing up for a spinning class on Wednesday morning. | Pass if the assistant captures class_interest as spinning, preferred_schedule as morning, attempts to book or queue a callback, does not quote a price. |
Caller asks about working with a personal trainer for weight loss. fitness.personal_training_inquiry | [SYNTHESIZE] About working with a personal trainer for weight loss. | Pass if the assistant captures trainer_request, fitness_goal, preferred_schedule, queues PT callback, and does not promise a specific trainer or rate. |
Caller opens with "Hola, quiero información sobre la membresía". fitness.spanish_switch | Hola, quiero información sobre la membresía | Pass if the assistant responds entirely in Spanish, captures all intake fields in Spanish, never announces the language switch, and does not revert to English. |
Spanish caller pushes for a membership price ("¿cuánto cuesta hacerse socio?"). fitness.price_deflection_spanish | ¿cuánto cuesta hacerse socio? | Pass if the assistant responds in Spanish, explains pricing is discussed by the team, and offers a tour or callback without quoting a figure. |
Caller sounds hesitant and says they haven't worked out in a long time. fitness.warmth_new_member_nervous | [SYNTHESIZE] Sounds hesitant and says I haven't worked out in a long time. | Pass if the assistant responds with warmth and zero judgment, does not ask about weight or health history, offers a no-pressure tour. |
The mistakes this pack is designed to prevent
quoted membership price
Agent states a specific membership rate on the call instead of deferring.
canDiscussPricing=false + price-deflection prompt_modifier; always defer to in-person or callback.
missed inquiry type
Call ends without capturing whether caller wants membership, class, PT, or tour.
inquiry_type required=true; branch logic explicit in intake tree.
no tour offer
New-lead caller hangs up without a tour or callback booked.
Offer tour or day pass to every new-inquiry caller before wrap.
language slip
Agent starts in Spanish, reverts to English mid-call without caller switching first.
Language-detection modifier: match caller's language throughout; never revert unilaterally.
judgment or fitness shaming
Agent asks about weight, age, medical conditions, or uses phrasing that implies judgment.
Warmth-first modifier; banned questions: weight, BMI, age, health conditions.
wrong urgency tier
Tour request treated as low-priority inquiry instead of hot lead.
tour_requested=hot; 1hr SLA; classified as tour-or-trial urgency tier.
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 fitness center 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.