How does an insurance agency / broker train the intusell AI? A step-by-step guide

An insurance agency's inbox is always filled with the same questions: "How much is comprehensive auto?", "When does my traffic policy expire?", "Is earthquake insurance mandatory, and how much?", "Does health insurance cover this?". Instagram posts, the WhatsApp line, the bottom of your website — it doesn't matter; the same twenty questions repeat a hundred times a day. While the agent is dealing with a claims file, at 10 p.m. a customer writes "my policy expires tomorrow, can I get a quote right away?" and waits for an answer until morning. Every quote request answered late goes to another agency; every customer whose renewal window is missed is renewed by a competitor.

intusell takes over this load. But to do that, it first needs to learn your agency, the branches you work in and your quote process. This article explains how an insurance agency or broker trains the intusell AI from scratch, step by step. This is the insurance chapter of our sector-by-sector "how to train your AI" series, and it is the pillar article of the series.

Quick answer

Why is training important?

intusell is not an off-the-shelf chatbot; it is a fully autonomous AI salesperson that behaves like an experienced agency assistant and quote handler. A good assistant doesn't start on day one without knowing the branches either: it needs to know which types of insurance you work in, which coverages you offer and which question to leave to the agent. Training ensures the AI does two things right: give the correct information (coverage scope, process information, business hours) and stop at the right boundary (not inventing a premium/coverage it's unsure about, not giving individual advice, leaving the exact quote to the agent).

An untrained assistant either gives an overly general answer or guesses on a topic it doesn't know. In insurance, guessing is expensive: a wrong premium or a baseless sentence like "yes, this comprehensive policy covers everything" both misleads the customer and creates liability for the agent. That is why the most critical part of training is teaching the AI "what it knows" and "that it should hand off to the agent when it doesn't know, or when an exact quote/advice is required." A well-trained assistant stops when it doesn't know.

Who is it for?

This guide is for insurance teams whose inboxes are crowded with quote questions and renewal requests, who answer the same questions over and over:

• Agencies working in traffic, comprehensive auto, earthquake and home branches
• Solo or small-team insurance agencies and brokers
• Teams selling health, life and complementary health insurance
• Agencies receiving dozens of quote requests a day via Instagram and WhatsApp
• Offices struggling to manually track many simultaneous renewals
• Brokers managing multi-step quote processes for SME and commercial insurance packages

You don't need a technical team. All of the steps below are completed from sections in the panel, without writing code.

The structure of training: 5 core steps + 2 ongoing steps

Splitting training into two groups makes your job easier. The first 5 core steps get the assistant working; these are the one-time part of setup. The 2 ongoing steps that follow (review and turning on channels) are the continuous part you sharpen as you use the assistant. You'll find all of them in order below.

1. Load the policy and coverage knowledge base

The foundation of training is the knowledge base (RAG). In the panel, you upload all of your agency's textual information into the Knowledge Base section. Every time the AI generates a response, it automatically searches these sources and uses only the information written there. In insurance, this means the branches you work in and your coverage processes.

Supported source types:

Every file you upload is automatically chunked and becomes searchable via pgvector. When you upload a "comprehensive auto coverage table.pdf," and a customer asks "is glass breakage included in comprehensive cover?", the AI finds the right section and explains the coverage scope.

What must absolutely be loaded for an insurance agency: the branches you work in (traffic, comprehensive auto, earthquake, home, health, life, personal accident, business), each branch's coverage scope and exclusions, the information required for a quote (license plate, registration, national ID, age, address, etc.), claims and renewal process information, business hours and the most frequently asked questions. An important boundary: the knowledge base is a living source that must be kept up to date. If a coverage has changed or you've added a new branch, you need to update the knowledge base; this is the foundation of a correct answer. The exact premium, however, is not a fixed value written into the knowledge base — because the premium changes by person and risk information, the AI does not state a premium, it collects the quote request (see step 4).

2. Set up quote meetings and business hours

The knowledge base explains "which coverages you offer"; the scheduling system lets the assistant give the customer a real meeting time. In insurance, this is most often a quote meeting, policy consultation or claims-file meeting. In the panel, you define three things:

Once these three are defined, the AI no longer offers times out of thin air; it proposes meetings based on your business hours and open slots. Booking the same time twice (double-booking) is prevented by the system. When a booking is created, if Google Calendar is connected the booking is also copied one-way to the agent's calendar. The customer can reschedule or cancel their own meeting via the /manage-appointment/{token} link sent to them; this reduces last-minute wasted scheduling.

The real power of the quote process in insurance, though, lies less in scheduling and more in the follow-up engine: collecting the quote request and proactively reminding a customer whose policy renewal is approaching. We've gathered every detail of this engine — quote request intake, renewal reminders and the follow-up flow — in a separate article: insurance quote and policy renewal automation. You can also see the quote and scheduling capabilities on the solutions page and the insurance solution page.

3. Set the persona and tone

In the first two steps you taught the AI what to say; now you'll determine how it says it. There are two settings in the panel:

• Assistant name (ai_persona_name): The name it introduces itself to the customer with. Most agencies choose a name that fits their team, inspires trust and is clear.
• Tone (ai_tone): The typical tone for insurance is calm, reassuring and explanatory; the language of an advisor who tries to understand the customer's need and risk and moves them toward a quote meeting without applying pressure. You can make the tone more corporate or more casual to match your own agency culture.

Multilingual note: The AI replies in whatever language the customer writes in. For customers writing from abroad in English, Arabic or Russian, you don't do anything separately; the assistant detects the language automatically and replies in it while preserving your tone — so the foreign customer's quote request is collected without being lost.

4. Set the response rules and boundaries

The persona defines "who it is"; the response rules define "how it behaves." In insurance, this step serves two purposes at once: conveying your sales discipline and drawing where the AI should stop and hand off to the agent. With the AI Manager Chat, you add rules by writing in plain language, just like giving instructions to a teammate.

Typical rules for insurance agencies:

• "When a quote is requested, don't state the premium yourself; collect the information needed for the quote (license plate/registration/national ID/age/address) in full and forward it to the agent."
• "Explain coverage scope from the knowledge base; but don't give personal advice like 'this policy is enough for you' — leave the needs analysis to the agent."
• "Don't state a coverage, exclusion or claims outcome you're unsure about; say you'll ask the agent and hand off."
• "Always pass claims files, payment and policy cancellation processes to the agent."

The most common mistake in insurance is the AI stating information it doesn't have (for example an exact premium or a coverage promise like "definitely covers it") as if it were true. On top of that, insurance is a regulated field: the AI does not give individual insurance advice, it only informs and directs to the licensed agent — just as it directs to an expert in legal and health. In intusell, two layers work against this. The main control is this: the AI is constrained by the system instruction to use only the information in the knowledge base from the start, not produce a premium/advice, and hand off when it's unsure. The second layer is a guardrail that scans responses and flags risky statements; this layer runs in observation (shadow) mode by default, meaning it doesn't hard-block the response, it detects and flags it. So the real assurance is that the AI is constrained from the start so it won't produce exaggerated promises or baseless premiums.

If you want to compare two different approaches, you can use the A/B testing feature: for example, you put a more informative tone next to a closing that calls the customer to a quote meeting more directly, at 50/50 traffic, and measure which one converts into more quote requests.

5. Teach from past conversations

This is the step that takes training from "good" to "specific to your agency." In the panel, you upload the audio recordings of your past sales conversations (MP3, MP4, WAV, M4A) and mark each one as Won or Lost — for example, did the customer buy/renew the policy, or did they go to another agency?

The system uses these recordings in two ways:

This way, the AI learns how your best agent understands the customer's need, how they move someone saying "let me think about it" to a quote meeting, and how they handle the "it's cheaper at a competitor" objection. The KVKK side is protected: PII (personal data) masking and explicit consent are applied to uploaded recordings — this step is especially important because sensitive data such as national ID, license plate and policy exists in insurance.

This step is not mandatory, but don't skip it. The knowledge base teaches the AI "what" it knows; past conversations teach it "how you sell." When the two are combined, the assistant truly resembles an experienced insurance advisor.

6. Refine through review (ongoing step)

The first five steps get the AI working. Everything after that is the continuous part that perfects it over time. Every AI response drops into a review queue. There you can do three things: approve, reject or correct.

The AI learns from these corrections. Say it explained a coverage's exclusion incompletely or miscounted the required documents for a branch; you correct it, and in similar situations it now uses the right phrasing. Over time, patterns specific to your agency accumulate (the way you explain coverages, your flow for collecting information for a quote, your language for steering toward renewal).

We recommend looking at this queue for 10-15 minutes a day for the first two weeks. During this period the correction rate drops quickly, because the AI learns the frequently made mistakes. Review is the "live" part of training: the system gets smarter the more it's used.

7. Turn on channels (ongoing step)

Once training is ready, you put the assistant in front of customers. intusell gathers all channels into a single inbox: Instagram DM, Instagram comments, WhatsApp, Facebook Messenger, Telegram, Web Chat and email.

Ways to turn on channels:

• Meta channels (Instagram, Messenger): connect with one-click OAuth.
• WhatsApp: connects in about 1 minute by scanning a QR code from your phone — no Meta Business approval required. An official Cloud API option is also available.

In insurance, the first two channels to turn on are usually WhatsApp and Instagram DM, because quote questions and "my policy is expiring" messages flow there most. Instagram comment automation, on the other hand, is rolled out gradually depending on Meta approval; the DM gate (instagram_dm_enabled) and the comment gate (instagram_comments_enabled) are separate. So you can first automate DMs and keep the comments under posts manual, then bring comments online once the comment gate is gradually opened.

There are working modes for human handoff: ai_only (the AI answers everything), human_only (everything goes to the agent), hybrid (the AI normally answers and escalates to the agent when needed). Most agencies start with hybrid; the AI handles quote questions and renewal traffic, while claims files and conversations requiring an exact quote go to the agent. For the details of Instagram and WhatsApp automation: Instagram and WhatsApp quote automation for insurance.

How long does training take?

A working setup takes half a day:

1. Loading branch and coverage information into the knowledge base: 1-2 hours (shorter if your coverage tables are ready)
2. Quote meeting types and business hours: 20-30 minutes
3. Persona, tone and first response rules: 30 minutes
4. Connecting channels: 1-5 minutes per channel

But there is no moment where "training is over." Over the first two weeks, as you approve and correct responses in the review queue, the assistant sharpens to fit your agency; keeping the coverage information up to date and A/B tests are also ongoing improvements. Setup is fast; mastery is continuous.

What it isn't

Putting intusell in the right category matters, because a wrong expectation leads to a wrong setup.

• It is not an online policy sales/comparison site. It does not issue policies on its own or publish price comparisons; it learns your branches and runs the communication and quote intake with the customer.
• It is not an insurance advisor. It does not perform an individual risk assessment and say "buy this"; it informs about coverages and directs the final advice to the licensed agent.
• It is not a premium-calculation engine. It does not state the exact premium; it collects the information needed for a quote, and the agent finalizes the price.
• It is not a bot that invents information. It does not state coverage, exclusion or claims information it's unsure about; it clearly says it doesn't know and hands off to the agent.

In short: not a bot giving canned answers, but an insurance sales assistant that represents your agency to the extent you train it — yet stops where it doesn't know, doesn't give advice, and hands off to the agent.

Frequently asked questions

How long does AI training take for an insurance agency?

A working setup is finished within half a day: loading branch and coverage information into the knowledge base, defining quote meeting types and business hours, setting persona and tone, and adding a few response rules. The real refinement accumulates over the first few weeks as you approve and correct responses in the review queue. Training is not one-off, it is continuous.

What happens if the AI states the wrong premium or coverage?

The AI only uses the coverage and process information you have loaded into the knowledge base; it will not invent a premium amount, a coverage scope or a claims outcome it is unsure about — it says it does not know and hands off to the agent. The exact premium and policy quote are always the agent's responsibility; the AI collects the quote request, and the agent finalizes the price.

Do I need technical knowledge to train the AI?

No. All training is done from the panel; no code, API key or developer is required. You upload branch and coverage information as PDF/Excel, enter your quote meeting types and business hours, and write your response rules in plain language. You connect channels with one-click OAuth or a QR code.

Does the AI give insurance advice?

No. intusell informs about coverages and processes, collects the quote request and brings a suitable prospect to a meeting with the agent; but it does not give individual insurance/risk advice such as "buy this policy" or "this coverage is enough for you." A personalized risk assessment and the final quote are the licensed agent's job; the AI protects this boundary from the start.

Does the AI answer quote and policy questions that come in at night?

Yes. It responds instantly, 24/7, to questions like "how much is comprehensive auto, when does my traffic policy expire, is earthquake insurance mandatory" that arrive under Instagram posts and on WhatsApp at night, collects the necessary information from a prospect requesting a quote and forwards it to the agent. By the time the team arrives in the morning, the quote requests are complete and prioritized.

Is customer and policy data safe under KVKK?

Yes. intusell is end-to-end encrypted and KVKK compliant. The personal data you collect in insurance — name, national ID, license plate, policy and claims — is stored encrypted; PII masking and explicit consent are applied when you upload past conversation recordings. All data is isolated on a per-tenant basis.

Next step

You've trained your assistant; next comes using it in daily operations. The next article in the series explains how to run the intusell you've trained on a real workday: the quote question that comes in at night, quote request intake, renewal tracking, reminders and customer follow-up. Continue straight from there: how an insurance agency uses intusell.

This was the insurance pillar article of our sector-by-sector series. We've set up the same structure in other sectors too; for example, for gyms see gym AI training, for tourism tour agency AI training, and for healthcare clinic AI training.

If you'd like to see it live before starting setup, use Get a demo so we can open your panel together in a 20-minute session, or write to hello@intusell.com. For package and quota details, see the pricing page, and for other guides, browse the all articles list.