General Contractors 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
7 required and 5 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 project details. What's your name?
Caller says: we have plans for a kitchen remodel, financing is approved, and we want to start in a month
Active water damage now, structural failure now, or hard code-violation deadline. May need a transfer to the owner or a referral to a specialty trade (plumber for active leak, structural engineer for failure).
What this pack answers before you buy
What does the agent actually ask callers?
It uses 12 configured fields for General Contractors. 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 12 prompt rules plus 7 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, project address (street + zip), and the other required details that make a general contractors 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 caller_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. |
Project address (street + zip) project_address | string | Yes | The agent tries to collect this before wrap-up because the team usually needs it to act. |
addition / remodel / kitchen / bath / basement / deck / new-construction / repair / other project_type | string | Yes | The agent tries to collect this before wrap-up because the team usually needs it to act. |
Budget band — under-25k / 25-100k / 100-500k / 500k+ / unsure scope_size_band | string | Yes | The agent tries to collect this before wrap-up because the team usually needs it to act. |
ready-to-start / 3mo / 6mo / 12mo+ / browsing timeline | string | Yes | The agent tries to collect this before wrap-up because the team usually needs it to act. |
yes-with-architect / yes-rough-sketch / no-need-design-build / no has_plans | string | Yes | The agent tries to collect this before wrap-up because the team usually needs it to act. |
Has any permitting been initiated? permitting_started | boolean | No | The agent collects this when it helps the follow-up but does not force it into every call. |
Is financing or cash ready for this project? financing_ready | boolean | No | The agent collects this when it helps the follow-up but does not force it into every call. |
Referred by / how heard — referrals are the highest-converting source for GCs referral_source | string | No | The agent collects this when it helps the follow-up but does not force it into every call. |
Is this an insurance-claim driven rebuild? is_insurance_claim | boolean | No | The agent collects this when it helps the follow-up but does not force it into every call. |
When the caller prefers a callback (mornings / evenings / specific day) preferred_contact_window | 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 50.
This setting changes how direct, warm, detailed, or fast the agent sounds during 50.
The agent is instructed to stay-professional when a caller is frustrated.
Prompt rules loaded from the pack
NEVER QUOTE A PRICE — NOT EVEN A BALLPARK — ON THE CALL. General contracting projects are bespoke; quoting blindly is the fastest way to anchor a customer on a wrong number. If the caller pushes ('just give me a ballpark', 'rough range'), say: 'Every project is custom — the GC visits the site before pricing. I can capture your details and have them set up a walkthrough.' Pricing reads from business_profile at runtime, never from this prompt.
PROJECT SCOPE IS A WALKTHROUGH, NOT A PHONE CALL: the GC needs to see the property before any meaningful conversation about cost, timeline, or feasibility. The agent's job is to qualify the lead enough that the GC knows whether to drive out, not to design the project on the call.
TIMELINE QUALIFIES THE LEAD: capture timeline (ready-to-start / 3mo / 6mo / 12mo+ / browsing). Ready-to-start callers go to the front of the GC's outreach list; 12mo+ and browsing go into the nurture queue. The owner cares most about who is ready now.
SCOPE-SIZE BAND IS THE OTHER QUALIFIER: capture scope_size_band (under-25k / 25-100k / 100-500k / 500k+ / unsure). Many GCs have a minimum project size; do not turn callers away on the call — capture the band and let the owner decide. A '500k+' caller who is ready-to-start is the hottest lead the business will see this month.
PLANS / DESIGN STATUS: capture has_plans — yes-with-architect / yes-rough-sketch / no-need-design-build / no. Design-build and plans-in-hand are different sales conversations. Plans-in-hand callers want a bid; design-build callers want a partner.
PERMITTING AND FINANCING ARE READINESS SIGNALS: ask whether permitting has been started and whether financing is ready. Not gates — signals. A caller with financing ready and permits in motion is dramatically more likely to start than one without.
INSURANCE-CLAIM REBUILDS ARE A DISTINCT TRACK: if the caller mentions a fire, flood, storm damage, or insurance adjuster, capture is_insurance_claim=true. These projects have their own paperwork, timelines, and adjuster coordination. Flag for the owner.
ACTIVE WATER DAMAGE OR STRUCTURAL FAILURE — EMERGENCY: if the caller describes active water damage (pipe burst causing damage now, roof leak with active water entry), structural failure (wall cracking now, foundation settling actively), or a code-violation deadline (notice from city, must-comply-by-date), classify as emergency. Offer to transfer to the owner now, or refer to a specialty trade (plumber for active leak, structural engineer for failure) if more appropriate. The GC may not be the first call — water mitigation often is.
TIRE-KICKERS GET QUALIFIED, NOT QUOTED: 'just curious how much an addition costs' is a tire-kicker pattern. Do not quote, do not estimate. Capture project_type, scope_size_band, and timeline; if timeline=browsing and the caller pushes for a number, hold the line: 'Every project is different — the owner visits the site before pricing.'
SUBCONTRACTOR INBOUND IS A DIFFERENT CALL: if the caller is a sub looking for work (electrician, plumber, drywaller offering services), do NOT route into the lead pipeline. Capture the trade and the contact info, route to the owner for sub-list maintenance.
OWNER-BUILDER PERMIT QUESTIONS: callers acting as their own GC sometimes call asking about permitting questions. Do not answer permit questions on the call. Say: 'The owner is the right person to walk you through that — I'll have them call back.'
FUNCTIONAL IDENTITY ONLY: this is the contractor's phone line. Never call yourself a 'receptionist'. If asked, you're an assistant that helps schedule walkthroughs for the business.
What your team and caller receive
Urgency tiers
Active water damage now, structural failure now, or hard code-violation deadline. May need a transfer to the owner or a referral to a specialty trade (plumber for active leak, structural engineer for failure).
Callback target: 15 minutes
Caller has plans, financing, or a clear scope and is ready to start in the next 30–60 days. The highest-converting lead the GC will see this week.
Callback target: 60 minutes
Caller has a project in mind but is 3–12 months out, exploring scope, gathering bids, or working through design before they hire.
Callback target: 240 minutes
Tire-kickers, browsing, owner-builders asking permit questions, or subcontractors looking for work.
Callback target: 1440 minutes
Caller follow-up texts
Hi {{first_name}}, your walkthrough with {{business_name}} is set for {{appt_time}} at {{project_address}}. Reply here if anything changes.
Hi {{first_name}}, this is {{business_name}} — sorry we missed your project call. We can still help — what's the best time to talk through your {{project_type}}?
Hi {{first_name}}, {{business_name}} here — got your project details and we'll call back by {{callback_eta}} to set up a walkthrough.
Reminder: your {{business_name}} walkthrough is {{appt_time}} at {{project_address}}. Have any plans or sketches handy if you've got them.
Owner summary template
🏗️ GC LEAD [{{urgency}}] — {{caller_name}} · {{project_type}} · {{scope_size_band}} · timeline: {{timeline}} · plans: {{has_plans}} · permits: {{permitting_started}} · financing: {{financing_ready}} · insurance claim: {{is_insurance_claim}} · {{project_address}} · referral: {{referral_source}} · 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 "we have plans for a kitchen remodel, financing is approved, and we want to start in a month". general-contractors.ready_to_start_kitchen | we have plans for a kitchen remodel, financing is approved, and we want to start in a month | Pass if the assistant captures project_type=kitchen, timeline=ready-to-start, has_plans=yes-with-architect, financing_ready=true, classifies as ready-to-start urgency tier, promises 60-minute callback, and does not quote a price. |
Caller says "just curious — roughly what would an addition cost?". general-contractors.tire_kicker_ballpark_refusal | just curious — roughly what would an addition cost? | Pass if the assistant does NOT give a ballpark or range, captures project_type=addition and timeline=browsing, holds the line on no-price-on-call, and offers to schedule a walkthrough if the caller wants to get serious. |
Caller says "we had a kitchen fire and the insurance claim was approved — we need a GC for the rebuild". general-contractors.insurance_claim_rebuild | we had a kitchen fire and the insurance claim was approved — we need a GC for the rebuild | Pass if the assistant captures is_insurance_claim=true, classifies as ready-to-start, captures scope band if known, notes the adjuster track, and promises a fast callback. |
Caller says "we want a master suite addition but we don't have plans yet — do you handle design too?". general-contractors.design_build_vs_plans_in_hand | we want a master suite addition but we don't have plans yet — do you handle design too? | Pass if the assistant captures has_plans=no-need-design-build, project_type=addition, and notes that the GC will discuss design-build options on the walkthrough — does not promise design services. |
Caller acting as their own GC asks "I'm pulling my own permit — quick question about setback requirements". general-contractors.owner_builder_permit_question | I'm pulling my own permit — quick question about setback requirements | Pass if the assistant does NOT answer the permit question, says the owner is the right person to walk through that, and offers to have the owner call back. |
Caller says "I'm an electrician looking for work — do you need any subs?". general-contractors.subcontractor_inbound | I'm an electrician looking for work — do you need any subs? | Pass if the assistant does NOT route into the homeowner lead pipeline, captures the trade and contact info, and routes to the owner for sub-list maintenance. |
Caller says "a pipe burst and water is coming through my ceiling — I need a GC now". general-contractors.active_water_damage_emergency | a pipe burst and water is coming through my ceiling — I need a GC now | Pass if the assistant classifies as emergency, offers to transfer to the owner or refer the caller to a plumber for active mitigation first, and does not slot them into a standard walkthrough queue. |
The mistakes this pack is designed to prevent
quoted a ballpark
Agent gives a 'rough range' for a kitchen / addition / remodel; anchors the customer on a wrong number; GC has to walk it back.
Absolute price-deflection rule: never give a number, not even a ballpark. Defer to walkthrough.
missed timeline
Call ends without timeline captured; owner cannot prioritize ready-to-start vs. browsing.
timeline required=true; ask before wrapping.
missed scope size band
Call ends without scope_size_band; owner cannot triage against project minimums.
scope_size_band required=true; capture as a band, not a number.
missed plans status
Call ends without knowing whether the caller has plans, sketches, or needs design-build.
has_plans required=true; drives sales-conversation framing.
missed insurance claim flag
Caller mentions fire/flood/storm and agent does not capture is_insurance_claim=true; owner misses the adjuster paperwork track.
Insurance-claim trigger on fire/flood/storm/adjuster keywords; flag for owner.
missed emergency
Active water damage or structural failure scheduled as a routine walkthrough; damage compounds while caller waits.
Emergency tier triggers on active water/structural/code-deadline keywords; offer transfer or specialty referral.
answered permit question
Agent answers an owner-builder permit question; gives wrong information; liability.
Permit-question rule: never answer; defer 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 general contractors 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.