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.
- 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)
24 policies expiring in December collected from 3 insurers' agency systems through their screens and turned into 16 customers' change summaries and draft renewal notices in 37 seconds; the 5 customers whose cover shrinks were flagged to confirm intent, each quoting the insurer's own words. A person approved, and the 16 notices were sent. Kitewell built the workflow 6 minutes after the request.
A real run on October 29, 2026, sped up. The system it works with was built for the demo.
The problem today
Two to three months before expiry, staff sign in to each insurer's agency system, list expiring policies, and draft notices customer by customer. A customer with policies from several insurers has their information split across those systems. When a renewal substantively changes coverage, Japanese rules also require confirming the customer's intent for the changed part.
The workflow in Kitewell
- Get policies nearing expiry through the insurers' shared gateway or each insurer's agency systemWeb
- Group policies by customer; AI summarizes premium and coverage changes from last yearAI judgment
- AI flags policies whose coverage substantively changes as candidates for confirming intentAI judgment
- Staff review the notices and the list, and approve sendingApproval
- Send the notices and alert staff to customers who have not replied as the deadline nearsAutomatic
What AI does
Groups policies spread across insurers by customer and summarizes what changed from last year. For policies that may need intent confirmation, it shows the changes behind that judgment.
Where people decide
Staff decide whether intent confirmation is needed and what the notice says, and approve before anything is sent.
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 expiring policies can be retrieved through the insurers' shared gateway or each insurer's system
- Whether your agency agreements and each insurer's system rules allow automated screen operation
- Whether the change summaries and intent-confirmation flags match your standards
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, insurer by insurer, the routes to expiring policies and their rules, and automates only what they allow.
- Does AI decide whether intent confirmation is needed?
- No. AI summarizes what changed from last year and points out candidates with the changes behind them. Staff decide whether intent confirmation is needed and what the notice says, and approve before anything is sent.
- 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
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.
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.
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.