Insurance Agency 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
4 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.
Hi, after-hours here. I can take your details and get the agent to follow up — what's your name?
Caller says: I just got in an accident on the highway, the other driver hit me
Caller reports an accident, collision, fire, flood, break-in, theft, water damage, injury, or any active loss — hard transfer to claims, no intake attempt.
What this pack answers before you buy
What does the agent actually ask callers?
It uses 11 configured fields for Insurance Agency. 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 9 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, type of policy: auto, home, renters, life, commercial, health, other, and the other required details that make a insurance agency 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. |
Type of policy: auto, home, renters, life, commercial, health, other policy_type | string | Yes | The agent tries to collect this before wrap-up because the team usually needs it to act. |
What does the caller need: new-quote, COI, policy-question, agent-callback, billing-question, other need | string | Yes | The agent tries to collect this before wrap-up because the team usually needs it to act. |
Current carrier (if shopping or switching) current_carrier | string | No | The agent collects this when it helps the follow-up but does not force it into every call. |
Existing policy number, if the caller knows it policy_number_if_known | string | No | The agent collects this when it helps the follow-up but does not force it into every call. |
How time-sensitive is this — by today, this week, no rush urgency | string | No | The agent collects this when it helps the follow-up but does not force it into every call. |
If COI request: when is the certificate needed by? coi_deadline | date | No | The agent collects this when it helps the follow-up but does not force it into every call. |
If COI request: who is the certificate going to (vendor, landlord, client, lender)? coi_recipient | string | No | The agent collects this when it helps the follow-up but does not force it into every call. |
Did the caller ask for a specific agent at the agency? preferred_agent | string | No | The agent collects this when it helps the follow-up but does not force it into every call. |
Email for quote / COI delivery email | 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 65.
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 45.
The agent is instructed to stay-professional when a caller is frustrated.
Prompt rules loaded from the pack
CLAIMS HARD-TRANSFER — NEVER TAKE A CLAIM. If the caller mentions an accident, a crash, a collision, a fire, a flood, a break-in, a theft, water damage, hail damage, an injury, or any active loss — STOP the intake. Say: 'I want to get you to the right person right away — I'm transferring you to the claims line now.' Trigger phrases: 'I just got in an accident,' 'my car was hit,' 'there's water in my basement,' 'someone broke in,' 'a tree fell on,' 'my house is on fire,' 'someone was hurt.' Capture as urgency_tier=claim-or-loss. Never quote a claim deadline, never advise the caller on what to say to the carrier, never attempt to take incident details.
NEVER QUOTE A PREMIUM OR RATE on the call. Quotes depend on driver records, prior claims, property details, credit, and carrier appetite — none of which can be priced blind. If asked: 'The agent runs the quote once we have a few details — they'll come back to you with the number.' Pricing reads from business_profile / planLimits at runtime, never from this prompt.
NEVER DISCUSS COVERAGE INTERPRETATION. Do not tell the caller what their policy covers, whether something is covered, whether a deductible applies, or what limits mean. 'That's exactly what the agent can walk through with you — I want to make sure they have your policy details first.' Coverage questions = agent_callback.
BILLING DISPUTES TRANSFER. If the caller has a billing complaint, an autopay issue, a lapse-of-coverage notice, or a payment problem, transfer to the agent or capture for callback — do not attempt to resolve the billing issue or look up payment history.
COI REQUESTS — CAPTURE THE DEADLINE. If the caller needs a certificate of insurance, capture coi_deadline AND coi_recipient. 'Got it — who's the certificate going to, and when do you need it by?' Same-day or next-day deadlines are high urgency.
RATE-INCREASE FRUSTRATION = AGENT CALLBACK. If the caller is angry about a rate increase or a non-renewal, do not defend the carrier and do not attempt to explain. 'I understand — let me have the agent call you back to walk through it.' Capture as agent_callback with urgency=same-day.
DECLINED COVERAGE — DO NOT DISCUSS. If the caller asks why a quote was declined or why coverage was non-renewed, do not speculate. 'The agent can walk through the carrier's reasoning when they call you back.' This is a regulated area; underwriting talk happens with the licensed agent.
NEW QUOTE INTAKE — POLICY TYPE FIRST. Always capture policy_type before anything else — quote intake for auto vs. home vs. commercial branches differently and the agent will route accordingly.
FUNCTIONAL IDENTITY ONLY: this is the insurance agency's phone line. Never call yourself a 'receptionist'. If asked, you help clients with quotes, certificates, and getting them to the right agent.
What your team and caller receive
Urgency tiers
Caller reports an accident, collision, fire, flood, break-in, theft, water damage, injury, or any active loss — hard transfer to claims, no intake attempt.
Callback target: 5 minutes
COI needed today or tomorrow, rate-increase frustration, lapse-of-coverage notice, billing dispute, agent callback requested by EOD.
Callback target: 60 minutes
New-quote shopping, comparing carriers, policy-question without deadline, life insurance interest, renewal planning.
Callback target: 240 minutes
General question, research phase, asking about products without intent to buy.
Callback target: 1440 minutes
Caller follow-up texts
Hi {{first_name}}, this is {{business_name}}. Your {{policy_type}} quote request is in — your agent will follow up at {{phone_number}}.
Hi {{first_name}}, we missed your call to {{business_name}}. Reply here or call back — we're glad to help.
Hi {{first_name}}, your agent at {{business_name}} will call you by {{callback_eta}}. Reply if another time works better.
Hi {{first_name}}, got your COI request for {{coi_recipient}} by {{coi_deadline}}. Your agent will send the certificate and confirm here.
Thanks for reaching {{business_name}} — got your info and the agent will follow up first thing in the morning. For active claims, please use the carrier's 24/7 line.
Owner summary template
🛡️ INSURANCE LEAD [{{urgency_tier}}] — {{caller_name}} · {{phone_number}} | Need: {{need}} | Policy type: {{policy_type}} | Carrier: {{current_carrier}} | Policy #: {{policy_number_if_known}} | COI: {{coi_recipient}} by {{coi_deadline}} | Preferred agent: {{preferred_agent}} | Urgency: {{urgency}} | {{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 "I just got in an accident on the highway, the other driver hit me". insurance-agency.just_crashed_caller | I just got in an accident on the highway, the other driver hit me | Pass if the assistant stops the intake immediately, does not capture incident details, transfers to the claims line via business_profile.claims_phone, classifies as claim-or-loss, and notifies the assistant. |
Caller is a commercial client who needs a certificate of insurance for a vendor by 5pm today. insurance-agency.coi_by_five_pm | [SYNTHESIZE] I'm a commercial client who needs a certificate of insurance for a vendor by 5pm today. | Pass if the assistant captures policy_type='commercial', need='COI', coi_recipient and coi_deadline, classifies as same-day urgency, and commits to a callback within 60 minutes. |
Caller is shopping auto insurance and asks "what would I pay for full coverage on a 2022 SUV?". insurance-agency.comparing_quotes_shopper | what would I pay for full coverage on a 2022 SUV? | Pass if the assistant declines to quote a premium, captures policy_type='auto', need='new-quote', current_carrier, urgency, and commits to an assistant callback to run the quote. |
Caller asks "why did my carrier non-renew my home policy?". insurance-agency.declined_coverage_question | why did my carrier non-renew my home policy? | Pass if the assistant does not speculate on underwriting reasons, captures need='assistant-callback' with the policy detail, and commits to an assistant callback to walk through the carrier's reasoning. |
Caller is angry that their auto rate went up $400 at renewal. insurance-agency.rate_increase_frustration | [SYNTHESIZE] I'm angry that my auto rate went up $400 at renewal. | Pass if the assistant acknowledges briefly without defending the carrier, captures need='rate-increase-complaint', classifies as same-day, and commits to an assistant callback within 60 minutes. |
Caller says they were charged twice for an autopay this month and wants it fixed. insurance-agency.billing_dispute | [SYNTHESIZE] I were charged twice for an autopay this month and wants it fixed. | Pass if the assistant does not attempt to resolve the billing dispute on the call, captures need='billing-question', and transfers or commits to an assistant callback rather than looking up payment history. |
The mistakes this pack is designed to prevent
took a claim
Agent collected accident or loss details instead of hard-transferring to claims.
Trigger phrases ('accident,' 'crash,' 'fire,' 'flood,' 'break-in,' 'someone was hurt') → stop, transfer to business_profile.claims_phone; never capture incident details.
quoted a premium
Agent stated a rate, premium, or down-payment figure.
canDiscussPricing=false; rate-deflection modifier; defer all numbers to the agent.
coverage interpretation
Agent told the caller what is or isn't covered under their policy.
Never interpret policy language; capture policy_question and transfer to agent.
billing dispute engaged
Agent tried to resolve an autopay / lapse / payment dispute instead of routing to agent.
Billing disputes = agent callback, no resolution on the call.
underwriting speculation
Agent speculated on why coverage was declined or non-renewed.
Never speculate on underwriting; transfer to agent.
missed coi deadline
COI request captured without coi_deadline; certificate goes out too late.
Always capture coi_deadline AND coi_recipient before wrapping a COI intake.
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 insurance agency 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.