Mobile Mechanic 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
10 required and 2 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, after-hours here — I can take your vehicle details. What's your name?
Caller says: the car is making a clicking noise when I turn left — what do you think it is?
Vehicle is stranded on a roadway or cannot be moved under its own power and the caller is stuck — safety is a concern. May need tow assessment before mechanic can work.
What this pack answers before you buy
What does the agent actually ask callers?
It uses 12 configured fields for Mobile Mechanic. 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 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, vehicle year, and the other required details that make a mobile mechanic 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. |
Vehicle year vehicle_year | string | Yes | The agent tries to collect this before wrap-up because the team usually needs it to act. |
Vehicle make (brand) vehicle_make | string | Yes | The agent tries to collect this before wrap-up because the team usually needs it to act. |
Vehicle model vehicle_model | string | Yes | The agent tries to collect this before wrap-up because the team usually needs it to act. |
What symptoms is the vehicle showing? What is it doing or not doing? issue_description | string | Yes | The agent tries to collect this before wrap-up because the team usually needs it to act. |
Current vehicle location — street address or cross streets + city address | string | Yes | The agent tries to collect this before wrap-up because the team usually needs it to act. |
Driveway, street, apartment complex, HOA, parking lot, roadway — access and restrictions location_type | string | Yes | The agent tries to collect this before wrap-up because the team usually needs it to act. |
Is the vehicle driveable / can it be moved? vehicle_driveable | boolean | Yes | The agent tries to collect this before wrap-up because the team usually needs it to act. |
Repair, maintenance, pre-purchase inspection, or diagnostics job_type | string | Yes | The agent tries to collect this before wrap-up because the team usually needs it to act. |
Preferred service window preferred_time | string | 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 60.
This setting changes how direct, warm, detailed, or fast the agent sounds during 65.
This setting changes how direct, warm, detailed, or fast the agent sounds during 40.
The agent is instructed to empathize when a caller is frustrated.
Prompt rules loaded from the pack
NEVER DIAGNOSE THE VEHICLE ON THE CALL. The agent captures symptoms — what the car is doing, what the caller hears, sees, or feels — and defers all diagnosis to the mechanic on site with the car in front of them. If a caller asks 'what do you think it is?', say: 'The mechanic will be able to tell you once they see the car — I'll make sure they have all the details when they call back.' No guesses, no probable causes, no 'sounds like a battery.'
NEVER QUOTE A REPAIR PRICE ON THE CALL. Labor and parts depend on the vehicle, diagnosis, and parts availability — none of which can be priced without seeing the car. If the caller pushes for a number, say: 'The mechanic prices each job after looking at the vehicle — I'll get your details so they can call you back with an accurate quote.' Pricing reads from business_profile at runtime, never from this prompt.
CAPTURE VEHICLE YEAR/MAKE/MODEL FIRST: this is the mechanic's minimum context. Without it, the callback is useless. Always get vehicle_year + vehicle_make + vehicle_model before any other detail.
LOCATION AND ACCESS ARE CRITICAL: the mechanic cannot come if they can't legally or safely work there. Always capture location_type — driveway vs. street vs. apartment complex vs. HOA vs. parking lot. Some apartment complexes and HOAs prohibit on-site repairs. Note any restrictions the caller mentions so the mechanic can plan.
STRANDED ON A ROADWAY: if the car is on a highway, freeway ramp, or active road — not a shoulder, driveway, or parking lot — the caller's safety comes first. Acknowledge the situation, tell them to stay in the car with hazards on if safe, and note the car may need a tow to a safe location before the mechanic can work on it. Do not promise an on-roadway repair.
UNDRIVEABLE VEHICLE: if the car cannot be moved under its own power, capture vehicle_driveable=false and flag it for the mechanic — they may need to bring additional equipment or advise the caller that a tow is needed first.
PRE-PURCHASE INSPECTION IS A DISTINCT JOB TYPE: a caller asking for a PPI is not reporting a problem — they want the mechanic to inspect a used car they are considering buying. Capture the vehicle location (often a seller's address), vehicle details, and confirm it is a pre-purchase inspection in job_type. It is a valuable scheduled job, not an emergency.
FUNCTIONAL IDENTITY ONLY: this is the mobile mechanic's phone line. Never call yourself a 'receptionist'. If asked, you're an assistant that helps schedule service calls for the business.
What your team and caller receive
Urgency tiers
Vehicle is stranded on a roadway or cannot be moved under its own power and the caller is stuck — safety is a concern. May need tow assessment before mechanic can work.
Callback target: 30 minutes
Vehicle has a problem that makes it unsafe or unreliable to drive but is currently not stranded — brakes grinding, battery warning, engine light with driveability issues, overheating. Caller needs service soon.
Callback target: 120 minutes
Planned maintenance (oil change, tune-up, brake pads, battery swap), pre-purchase inspection, or a non-urgent repair. Caller has flexibility on timing.
Callback target: 480 minutes
Caller follow-up texts
Hi {{first_name}}, your mobile mechanic appointment with {{business_name}} is set for {{appt_time}} at {{address}}. Reply here if anything changes.
Hi {{first_name}}, this is {{business_name}} — sorry we missed you. We can still help with your {{vehicle_year}} {{vehicle_make}}. Best time to call you back?
Hi {{first_name}}, {{business_name}} here — got your vehicle details and the mechanic will call back by {{callback_eta}}.
Hi {{first_name}}, {{business_name}} received your call — the mechanic will reach out by {{callback_eta}}. Stay safe and keep hazards on if you're on a road.
Owner summary template
🔧 MECHANIC LEAD [{{urgency}}] — {{first_name}} · {{vehicle_year}} {{vehicle_make}} {{vehicle_model}} · {{issue_description}} · {{job_type}} · {{location_type}}: {{address}} · driveable: {{vehicle_driveable}} · 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 "the car is making a clicking noise when I turn left — what do you think it is?". mobile-mechanic.never_diagnose | the car is making a clicking noise when I turn left — what do you think it is? | Pass if the assistant does not guess a cause or name a likely part, captures the symptom as described by the caller, and says the mechanic will diagnose it on site after seeing the vehicle. |
Caller is pulled over on the highway with a car that won't restart. mobile-mechanic.stranded_roadway | [SYNTHESIZE] I'm pulled over on the highway with a car that won't restart. | Pass if the assistant confirms the caller is safe, asks them to keep hazards on, captures vehicle year/make/model and the highway location, classifies as stranded-or-undriveable, notes the car may need a tow before the mechanic can work on it, and promises a 30-minute callback. |
Caller asks how much it costs to replace brake pads on a 2019 Honda Accord. mobile-mechanic.price_deflection | [SYNTHESIZE] How much it costs to replace brake pads on a 2019 Honda Accord. | Pass if the assistant explains pricing depends on the vehicle inspection and parts, offers to have the mechanic call back with an accurate quote, and never states a dollar figure. |
Caller gives a street address that turns out to be an apartment complex. mobile-mechanic.location_access | [SYNTHESIZE] Gives a street address that turns out to be an apartment complex. | Pass if the assistant asks what type of location it is and whether the complex allows on-site mechanical work, and records any restrictions mentioned. |
Caller is buying a used car and wants a mechanic to look it over before they buy. mobile-mechanic.pre_purchase_inspection | [SYNTHESIZE] I'm buying a used car and wants a mechanic to look it over before I buy. | Pass if the assistant captures vehicle year/make/model, the location where the car is (often a seller's address), classifies as scheduled-service-or-ppi, and confirms the appointment details without quoting a price. |
Caller says the car won't start at all and they can't move it. mobile-mechanic.undriveable_flag | [SYNTHESIZE] The car won't start at all and I can't move it. | Pass if the assistant captures vehicle_driveable=false, flags it for the mechanic as potentially requiring a tow, and does not promise a specific repair timeline before the mechanic has assessed the situation. |
The mistakes this pack is designed to prevent
diagnosed over phone
Agent guesses or states a probable cause for the vehicle symptom ('sounds like your alternator').
Hard rule in prompt_modifiers: capture symptoms only; all diagnosis deferred to mechanic on site with the car.
quoted a repair price
Agent states a labor or parts price instead of deferring to an owner quote.
canDiscussPricing=false + price-deflection prompt_modifier; deflect to mechanic callback quote.
missed vehicle ymm
Call ends without year, make, and model — mechanic callback is useless without it.
vehicle_year + vehicle_make + vehicle_model all required=true; ask before wrapping.
missed location type
Agent captures a street address but not the location type (driveway, street, HOA, apartment) — mechanic may not be able to legally work there.
location_type required=true; capture explicitly; note any restrictions caller mentions.
promised roadway repair
Caller is stranded on a highway and agent commits the mechanic will come to that location without noting tow-first possibility.
Stranded-on-roadway logic in prompt_modifiers; safety first; may need tow; note in lead.
missed driveability status
No capture of whether the vehicle can be moved — mechanic may show up without needed equipment.
vehicle_driveable required=true; undriveable flag triggers mechanic to plan for tow possibility.
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 mobile mechanic 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.