Get quotes from several insurers
Enter one set of conditions in each insurer's agency system to get quotes, and keep each premium with the conditions screen. Staff check items hard to map.
- Runs on your own PCs and servers
- Use Azure OpenAI, Amazon Bedrock, Google Vertex AI, or an in-house model
- Its engine is Descarty's open-source Dagu (GPL-3.0)
The problem today
To compare insurers, staff sign in to each insurer's agency system and enter the same building, vehicle, and coverage conditions again for each one. Field names and options differ between insurers, and an entry mistake breaks the basis of the comparison. Quoting takes time away from hearing what the customer wants and explaining the recommendation.
The workflow in Kitewell
- AI reads the quote conditions from the hearing sheet or the customer's current policy and lists themAI judgment
- Staff confirm which insurers to quote and the conditionsApproval
- Sign in to each insurer's agency system, enter the same conditions, and create a quoteWeb
- Save the premium and the screen of the conditions entered for each insurerAutomatic
- AI compiles a comparison of premiums and condition differencesAI judgment
- Staff check the comparison and the conditions enteredHuman task
What AI does
Reads conditions from the policy or hearing sheet and maps them to each insurer's fields and options. Items that are hard to map are shown to staff with the reasoning. It compiles the premiums and condition differences from each insurer's quote.
Where people decide
Staff confirm which insurers to quote and whether the mapping is right. Staff decide which product to recommend.
Prove Kitewell on your own systems
Try it free for 14 days on your own PC. To see it working first, ask for a 30-minute demo. There is also a one-month onboarding (¥500,000 before tax), where we build your first job together.
What to check when you try this work
- Whether your agency agreements and each insurer's system rules allow automated screen operation
- Whether conditions map correctly to each insurer's fields and options
- Whether each insurer's sign-in works, including the shared gateway, client certificates, and one-time passwords
- Where the customer information used for quotes comes from, and how consent is obtained
How the onboarding runs
- Week 1Requirements and success criteria
- Weeks 2 to 3Build
- Week 4Verify on production screens
- Final dayReport
One-month onboarding
- Length
- One month
- Cost
- ¥500,000 (tax excluded). Your staff build, with the developer beside them
- If you go on to a license
- The onboarding fee is credited to the first year's contract
- Without the onboarding
- At Team scale, start on Team monthly (¥14,800 per computer a month, tax excluded), and cancel in any month
You can try it first on your own PC, in the free 14-day trial.
Frequently asked questions
- May a tool operate insurers' agency systems?
- It depends on your agency agreement and each system's rules. The PoC checks each insurer's quote screens and their rules, and automates only what they allow.
- Does automating quotes meet Japan's comparison-and-recommendation rules?
- No. The FSA states that merely presenting premium comparisons or a system's output does not fulfil the duties to understand the customer's intent and to compare and recommend. The time quoting frees up is meant for confirming what the customer wants and explaining the recommendation.
- May information from one insurer's policy be used for another insurer's quote?
- It depends on the customer's consent and how your agency agreements treat the information. Multi-insurer agencies sending one insurer's policyholder information to other insurers has been treated as a data leak. The PoC settles which information may be entered in which insurer's screens before anything is automated.
- Do our documents and screens leave the company?
- Kitewell runs on your own PCs and servers, and Descarty never receives your business data. You choose the AI model: a cloud API, or an in-house or local model with an OpenAI-compatible API. With an in-house model, no data leaves the company. With a cloud model, what the AI reads is sent to the model's provider.
- What if the AI misreads something?
- A person checks what the AI produced before the work goes on. In a sheet, every value the AI reads shows the quote it came from, and rows below your confidence threshold go to a person. Reviewers can send work back with notes on what to fix, and who approved what is kept in the run history.
- What happens when a screen changes or a run stops?
- When a screen changes, the AI reads it again, relearns the step, and carries on. The relearned step is saved, and later runs repeat it. If a run still stops, ask the assistant right there, and it finds the cause and proposes a fix. A proposal is not saved until a person applies it.
- What happens to the RPA and systems we use today?
- Keep them. Kitewell operates screens the way a person does, so it works with systems that have no API. Move the robots that keep stopping and the work you gave up automating because it needs judgment, and leave fast, fixed processing in your current RPA.
- What does it cost?
- ¥14,800 per computer per month, or ¥148,000 per computer when paid yearly, before tax. A computer costs the same whether it builds or runs. You can try it free for 14 days. The one-month onboarding, where we build your first job together, is ¥500,000 before tax, credited to the first year if you go on.
Related use cases
Find expiring policies and send renewal notices
Collect expiring policies through the insurers' shared gateway or agency systems, and draft renewal notices showing what changed. Coverage changes are flagged.
Draft comparison explanations and records
When a multi-insurer agency recommends a product, AI drafts the quote comparison and the reason. Staff edit it before explaining it and keeping the record.
Consolidate policy data from each insurer
Collect new, changed, and cancelled policies from each insurer into the CRM's customer register. AI suggests which records are the same customer; staff confirm.
See this work in a demo
A 30-minute demo shows this workflow running. The 14-day free trial lets you check it on your own systems.