How do you answer "what is the status of my claim" in one line when the status sits in the package, the email and the insurer's extranet?

Your AI gets an answer ready from the email, your package and the insurer's extranet once that access is set up, and you send it after your approval.

Works with SharePoint, ANVA, CCS, Convect and your own file and client systems.

The status question is where it starts; every answer shows where it came from, and every correction becomes a rule in the shared memory.

Book your half hour

Together we map what your AI forgets. Free, and the plan is yours, with or without Bombos. Join the plugin waitlist →

This is how it goes now, and how it goes with Bombos.

Now

"What is the status of my claim?" One line of question, three systems of answer.

Today a staff member gathers the status from the package, the email exchange and the insurer's extranet, then writes one answer. A client asks where their claim stands. You check ANVA or CCS for the policy details and read the latest messages. If the current status only sits with the insurer, you still have to retrieve it from the extranet before answering the client.

Withbombos

The answer is ready, built from the package, the latest email exchange and the insurer's extranet.

Your AI reads the status question, looks up information in your package and email, and prepares a draft answer with the reason included. If the claim status sits in the insurer's extranet and your AI has access to it, it retrieves it there. Instead of filling in unavailable information, it asks you what is missing. You read the draft, add what is needed and send it.

After three months

After three months, the answer to a status question is ready before you start searching. You read it, add anything that is missing and send it. Clients hear sooner where things stand and need to call less often. Every answer shows where it came from: the package, the email or the extranet.

What's ready for you then

  • Every status question has an answer ready to send
  • Package, email and extranet combined in one answer
  • Clients hear sooner where their claim stands
  • Phone agreements count once Bombos knows them

Where do you see that?

The proposed answer to the status question sits on one list, with the reason attached. You see the status "ready for you" or "waiting on your input". The package does not need to be open to read the draft. The draft shows the details your AI found in the email and the package. If the status from the insurer's extranet is needed, it sits there with the draft once that access is set up.

The status of the proposal is about the prepared work. It is not the claim status at the insurer. That difference matters when reviewing: a draft that is ready is a text to read, not a decision about the claim. You add to the answer and send it. With every proposal you see where it came from.

How does it start?

In the first week we go through, in about an hour, which mailbox and which package you use for claim questions. You decide which rules apply to preparing answers and arrange access to the systems for that task. We also go through a phone agreement about the claim that is not recorded anywhere yet.

Nothing moves, no new package is added and no course is needed. Adjusting means filling in settings, not custom work. Even if you do not work with computers much, we set up the preparation together. After three months, the answer to a status question is ready before you have checked three places.

After the setup, your AI starts with proposals. A correction to the claim answer becomes the rule for the next reply. Bombos keeps that explanation; without it, the memory does not hold what you want to read differently. Once a task type has gone well for a while, you decide how much autonomy you give your AI, with Bombos as the memory underneath. You approve outgoing answers; you set that in the AI or agent itself.

The status question is the first task, not the whole offer. We take you through the setup. After that, every correction becomes a rule Bombos keeps, so the next task starts from what you already agreed. If the same status question comes from another client, the next draft is already there before you ask, with the reason attached.

One answer, from one shared memory.

The status question returns every day, and each time someone checks three places: the package, the email and the extranet. Your AI brings them together in one answer.

Bombos is the memory layer under the AI your team already uses: Claude, Claude Code, ChatGPT, Copilot, Grok, Codex, Cursor or your own agents. One plugin gives them all one shared memory: your team's knowledge, the rules it learns from your corrections, and what is already in your email, documents and business software.

You see where every answer came from. Bombos runs in the cloud or standalone on your own server, and one person can try the plugin with their own agents first.

The pilot runs three months for €2,000 instead of €3,000, then €1,000 per month, excl. VAT. Book your half hour to talk through your situation.

What Bombos does, in three steps

  1. It reads what comes in

    An email, a message, a photo or a PDF: your AI reads it, finds the client and the details through Bombos in the systems you already have, and sees what is missing.

  2. It drafts the work, you approve it

    The proposal sits on one list with the reasoning next to it. You read it, adjust it and approve. Only then is anything sent, booked or filed.

  3. It remembers what you decide

    Every correction becomes the rule for next time. Once it has gone well for a while, you give your AI more autonomy step by step, with Bombos as the memory underneath.

What does Bombos not do here?

Bombos does not act here itself: it gives your AI the memory. Without a connection between your AI and ANVA or CCS, it stays a proposal.

What is recorded nowhere, Bombos does not know. An agreement you made over the phone sits in no system at all. That is why your AI asks you once what was agreed with the client by phone about this claim, and Bombos keeps the answer, so that it counts in the answer next time. If information is missing, that question stays open in the draft. When unsure, your AI puts the question to you. A proposal can be wrong and needs review before use in the claim answer.

This application for insurance covers claims only. Life insurance, disability insurance and health data fall outside it. You approve before messages go to third parties, through any channel, including an answer about the claim status. You set that in the AI or agent itself. That approval is also required to keep a change for good in the file. A draft answer therefore does not mean the claim status in your package has already been updated. For a short answer, the latest status has to be gathered first.

The first half hour · free

What does your AI forget?

  1. 01You tell us which AI you use and where it keeps starting over.
  2. 02We show what a shared memory changes there, on your own examples.
  3. 03You keep the plan, with or without Bombos.
Piet Baudoin
Piet BaudoinYou talk to Piet, from the Bombos teamDutch team from Utrecht and Nijmegen · data in Europe
We reply the same working day.