Fixed quote after a free call

An AI insurance assistant that handles service, not advice

We build an AI assistant for your website, text line or phone that answers routine questions (office hours, how to pay, how to get ID cards or a certificate, what to do after an accident) from your agency's approved answers, takes policy change and certificate requests into the right workflow and hands any question about coverage, claims decisions or advice to a licensed person. It discloses that it is automated. Projects typically cost $2,500 to $7,500 and take five to eight weeks.

The problem

What an insurance chatbot should and should not do

CSRs spend much of the day on the same requests: send my ID cards, add a vehicle, how do I pay, I need a certificate for a job. Each is simple, but together they push renewal and claims work into the evening.

An insurance AI chatbot can take that load only if it is narrow. It cannot tell someone whether they are covered, recommend a policy or quote a price it did not get from a carrier. It must answer from approved wording, collect clean requests and pass anything else to a licensed agent.

What we build

What our AI insurance assistant includes

Approved answer library

Office hours, payment options, carrier claims lines, ID card and certificate steps written and approved by the agency.

Website chat and text line

A chat widget on your site and, optionally, the same assistant on SMS or WhatsApp.

Clean service requests

Policy changes, certificate requests and document requests collected in a structured format for CSRs.

Carrier claims lines

After an accident or loss, the right carrier claims number and the agency's FNOL form.

Licensed hand-off

Questions about coverage, pricing, recommendations or complaints go straight to a person.

Disclosure and transcripts

It says it is automated, offers a person at any time and logs every conversation.

Who does what

Automation does the chasing, people make the calls.

Every step is marked: what runs on its own, what a member of staff reviews and what stays with a person who decides.
  1. 01 Automated

    Question asked

    A policyholder asks on the website, by text or by phone.

  2. 02 Automated

    Answer from your library

    The assistant answers only from approved wording.

  3. 03 Automated

    Request captured

    Change, certificate or document requests are structured and sent to the right workflow.

  4. 04 CSR or account manager review

    CSR completes

    CSRs process requests and reply to anything the assistant could not answer.

  5. 05 Licensed agent or principal decides

    Coverage advice

    Anything about coverage, pricing or recommendations goes to a licensed agent.

How it behaves

How the AI insurance assistant behaves

What each person sees and what runs in the background, including what happens when something goes wrong.

What the policyholder sees

  • A clear note that they are talking to an automated assistant
  • Quick answers from the agency's own wording
  • A licensed person whenever they ask about coverage or price

What CSRs see

  • Structured change and certificate requests
  • Hand-offs with the full conversation
  • A weekly list of unanswered questions

What the automation does

  • Answers only from approved wording
  • Refuses coverage, pricing and advice questions and hands over
  • Logs every conversation

Edge cases and fallbacks

Question not in the library
It says it does not know, offers a person and logs the question.
Client asks if a loss is covered
No answer; hand-off to a licensed agent and the carrier claims line.
Complaint or distress
Immediate hand-off to the named manager.
AI provider outage
The widget falls back to a contact form and the text line to a holding reply.

Architecture

An AI service assistant for an agency at a glance.

The setup we usually start from. We adapt it to the phone system and practice software you already use.
Policyholder Web, SMS, phone Assistant service n8n or Laravel Language model Claude, Gemini, GPT Approved answers Agency-written Service request Change, COI, docs Licensed staff Coverage questions Transcripts Weekly review
  • Input
  • Logic and services
  • AI step
  • Data
  • Output
  • People

How it flows

  1. 1 A policyholder asks a question and is told they are talking to an automated assistant.
  2. 2 The assistant service retrieves approved answers and passes them, with fixed rules, to the model.
  3. 3 Routine questions are answered and service requests are structured for CSRs.
  4. 4 Coverage, pricing and complaints go to licensed staff, and every conversation is logged.

Project planner

How the project runs, phase by phase.

Typical durations for a first version. Your proposal lists the exact phases, dates and what you sign off at each step.

AI service assistant for policyholders project plan

Typical time to launch: about 6 weeks, then support

  1. 01

    Discovery

    About 1 week

    Collect real questions from calls, emails and texts; agree what the assistant must never answer.

  2. 02

    Answer library

    About 1 week

    Write and approve answers, hand-off rules and disclosure wording.

  3. 03

    Build

    About 2 weeks

    Widget or text line, retrieval, request capture, hand-offs and logging.

  4. 04

    Test

    1 to 2 weeks

    Real, tricky and coverage-bait prompts; licensed staff sign off.

  5. 05

    Launch

    2 to 3 days

    Soft launch after hours, then all day.

  6. 06

    Support

    Ongoing

    Weekly transcript review at first, then monthly library updates.

What it runs on

Real products only, connected through the access each vendor provides. See all integrations

Claude, Gemini or OpenAI models n8n AI Agent node or Laravel Website chat widget Twilio SMS or WhatsApp Business AgencyZoom, NowCerts or AMS route for requests Slack or Microsoft Teams hand-off alerts

Cost estimate

What it costs, line by line.

Estimates to plan with. Your fixed quote follows a free call, once we have seen your systems and volumes.
  • Discovery and answer library

    Real questions collected, answers written and approved.

    $500 – $1,200

  • Build

    Assistant service, widget or text line, retrieval and hand-offs.

    $1,200 – $4,000

  • Integrations

    CRM or AMS request routes, alerts and messaging.

    $300 – $1,000

  • Testing and evaluation set

    Real, tricky and coverage-bait prompts before launch.

    $300 – $900

  • Launch and training

    Soft launch, transcript review and team walkthrough.

    $200 – $400

  • Total project estimate

    $2,500 – $7,500

Optional monthly care after launch is quoted with your proposal. Fixed quote after a free call. A voice line costs more to build and run than web chat. Model usage and messaging are billed to your accounts directly.

Monthly running costs you pay directly

Estimates from the vendors' published pricing, checked November 2026. Billed to you by each vendor, never marked up.

  • AI model usage: Billed by the provider per use; short service answers are usually a small monthly amount.
  • Messaging or voice: Twilio at its published per-message rates if you add a text line; a voice line costs more to run than web chat.
  • Hosting: n8n Cloud from about €20 a month, or your own server.

What pushes cost up

  • Systems without an API, or with integration access that must be requested from the vendor
  • Writing data back into your core system rather than only reading from it
  • Several locations, brands or very different processes to support
  • Custom apps, dashboards or a voice line on top of the workflows

What keeps cost down

  • One location and one clear process to start with
  • Cloud software with a documented API
  • Using tools you already pay for instead of adding new ones
  • Approved wording and sample data ready at the start
Get a fixed quote

Privacy and consent

Rules we design for, with the sources.

General information to plan with, not legal advice. Your counsel or data protection adviser confirms what applies to your practice.

EU: tell people they are talking to AI

Article 50 of the EU AI Act requires AI systems that interact with people to inform them they are interacting with an AI system, from 2 August 2026.

Source: artificialintelligenceact.eu

US: insurer AI governance

The NAIC model bulletin on insurers' use of AI, adopted December 2023, expects governance of AI systems. Agencies working with carriers should expect questions about AI tools, so ours stays out of decisions.

Source: content.naic.org

UK: Consumer Duty

The FCA Consumer Duty requires firms to put retail customers' interests first, so the assistant offers a person at any time and avoids steering.

Source: www.fca.org.uk

How we deliver

Agile delivery, in 1 to 2 week sprints.

We deliver in short Agile sprints using Scrum, so you see working software every one or two weeks instead of waiting for a big reveal at the end.

Every sprint

  1. 1 Sprint planning. At the start of each sprint we agree which backlog items we will finish, each with written acceptance criteria you can check.
  2. 2 Daily stand-up. A short internal check-in on progress and blockers. You get a written update in your Slack or Teams channel, not another meeting.
  3. 3 Sprint review and demo. At the end of each sprint we demo what was built on test data or in a shadow run, and you accept it or ask for changes.
  4. 4 Retrospective. The team looks at what went well and what to change in the next sprint, and we share anything that affects you.

How scope stays under control

Product backlog
Every feature, fix and question in one prioritised list you can see at any time.
Acceptance criteria
Plain-language conditions for "done" on each item, agreed before work starts.
Change requests
New ideas go into the backlog with an estimate. Nothing changes scope or price without your written approval.
User acceptance testing (UAT)
Before launch your team tests the real workflow against the acceptance criteria and signs off.

Tools we use

Jira, ClickUp or Trello for the backlogSlack or Microsoft Teams for updatesGitHub for code and version historyLoom or a live call for demos

Project manager / Scrum master

Runs the sprints, keeps the backlog and timeline honest, and is your single point of contact.

Business analyst

Maps how the work runs today, writes the workflow specification and acceptance criteria with your team.

Automation engineer

Builds the n8n workflows, integrations, AI steps and error handling.

Backend developer

Writes custom code where a no-code step is not enough: APIs, data sync, secure storage.

Frontend / mobile developer

Builds forms, booking pages, dashboards, web apps or Android apps when the project needs them.

QA engineer

Tests every workflow against the acceptance criteria, including edge cases and failure paths.

DevOps engineer

Sets up hosting, access, backups, monitoring and alerts, and the deployment pipeline.

Who does what at each phase

Free call
Project manager, business analyst
Understand the problem, check it is worth automating and outline a rough range.
Discovery
Business analyst, automation engineer
Map the current process, systems and data, and agree success measures.
Design
Business analyst, automation engineer, backend developer
Write the workflow specification, data flows, compliance notes and backlog with acceptance criteria.
Sprints
Automation engineer, developers, QA
Build, test and demo in 1 to 2 week sprints; you accept or adjust after each demo.
UAT and launch
QA, DevOps, project manager
Your team tests and signs off, we switch on, monitor closely and train the team.
Support
Automation engineer, DevOps
Stabilisation window, then optional monthly care with monitoring and changes.

A point of contact

One person who can answer questions and approve decisions, with about an hour a week during the project.

Access

Admin or API access to the systems involved, created as separate accounts with the least access needed.

Sample data

Real but non-sensitive records (or de-identified ones) so we can design and test against reality.

Approved wording

Message templates, policies and consent wording (for SMS, your opt-in and opt-out text) reviewed by you.

Vendor agreements

Signed agreements with the software vendors that will handle personal data, such as a BAA or processor contract.

Time for testing

A few hours from the people who will use the system, for the demos and user acceptance testing.

Working system

Workflows, integrations and any apps running in your accounts, under your keys.

Documentation

Workflow specification, data-flow map, run book and exported workflow files.

Training

A walkthrough for the team and a short recorded video for new starters.

Handover

All access, credentials and code handed over; you can keep us or take it in-house.

Stabilisation window

Fixes for anything that does not meet the agreed acceptance criteria after launch.

Support options after launch

  • No plan

    You run it yourselves after the stabilisation window and contact us when you need a change.

  • Monthly care

    Monitoring, error alerts, small changes and updates each month, with an agreed response time.

  • Priority care

    Faster response times for business-critical workflows and a monthly review call.

How a project moves through our team

Free call PM and analyst Discovery Process and data Design Spec and backlog Sprints Build, test, demo Your review Accept or adjust UAT and launch Sign-off, go live Support Monitor and improve
  • Input
  • Logic and services
  • People
  • Output
  • Data

How it flows

  1. 1 A free call with the project manager and business analyst to understand the problem and whether it is worth building.
  2. 2 Discovery and design produce a written specification, data-flow map and a backlog with acceptance criteria.
  3. 3 The team builds in 1 to 2 week sprints; you review a demo at the end of each and accept or adjust.
  4. 4 Your team runs user acceptance testing, we launch, then monitor and improve under a support plan.

FAQ

AI service assistant for policyholders questions, answered.

Answer routine service questions, collect policy change and certificate requests, point clients to the right claims line and hand everything else to a person. It never advises on coverage.

Ours does not. Selling, quoting and recommending cover require a licensed person, and prices must come from carriers. The assistant collects details for a producer instead.

Yes. It says so at the start and offers a person at any time. The EU AI Act requires this from 2 August 2026, and we do it everywhere.

It collects a complete change request, such as a new vehicle with VIN and driver, and sends it to a CSR to submit to the carrier.

It gives the carrier's claims line, the agency's claim form and emergency steps, and flags the conversation for staff in the morning.

Transcript logs, a weekly list of unanswered questions, the share of requests resolved without a hand-off and complaints, if any, about the assistant.

Free 20-minute call

Want this for your insurance broker?

Book a free 20-minute call. We will look at how the work runs today, tell you honestly whether it is worth building and give you a fixed quote if it is.

Book a free 20-minute call