How do you sort a shared inbox so every email has an owner?
Sorting a shared inbox starts with a suggestion for each email: the colleague responsible, the customer details found, and a draft answer that you review and send.
Works in your own Outlook, next to your own software.
The inbox is where it starts; every correction stays in one shared memory for every AI your firm uses.
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.
Everything arrives in info@, three people check it, and half of it gets forwarded around with "is this yours?"; nobody knows who is handling what.
Three people check info@, and when one opens an email, the others leave it alone. To answer it, someone works out which customer or resident it belongs to, retrieves the details from the software and decides who handles the question. Then the email is forwarded. Outlook has categories, flags and folders, and TwinQ is launching its own mail assistant to sort messages and draft answers. A folder still does not answer the customer's question.
Every email is assigned to the right colleague, with the draft answer already underneath.
Your AI reads the incoming email, recognizes the question and looks up the customer details, with what Bombos remembers. The suggestion shows which customer or resident and which colleague the email belongs to, with the reason and a draft answer. That reason follows your inbox rules. You check the assignment and the content, then send the answer. If there is not enough information to choose, your AI asks for your judgment.
After three months, no email is left sitting because nobody knew it was theirs. The assignment is ready, and your colleagues only need to approve it. The time this frees up goes to work customers pay for. You see where every assignment and answer came from.
What's ready for you then
- Every email has an owner, no more forwarding
- The answer is ready beneath the question
- Customer details are there, no searching required
- See everything still open on one list
Where do you see that?
You see the work from the agreed inbox on one list of suggestions. Next to a message you see the reason for the suggestion and the status: "ready for you" or "waiting on your input". That way you read the question, the details found and the suggested answer together. You are reviewing a concrete next step, without first having to work out why a colleague forwarded the email.
Reviewing the assignment does not require your software to be open. The customer details sit with the email they were looked up for. A suggestion on the list is not yet a change in the customer file or a sent answer. With every proposal you see where it came from. The list of suggestions shows which reply is ready and which email still needs input from a colleague.
How does it start?
In the first week we discuss how to sort info@ in a setup conversation of about an hour. You point out the inbox and show which software holds the customer details. We fill in the rules for sorting: which colleague handles the question, which details go with it, and who reviews the answer. You give access to the systems needed for that. You keep your email and your software; nothing has to move and you do not need to take a course. That is also where we bring up the sorting habits that, until now, only your colleagues knew.
After that, your AI starts preparing the assignment with proposals. A correction to the chosen colleague becomes the rule for the next email. Bombos keeps your corrections as rules; without them, it does not know which colleague an email should go to. 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 answers to the sender; you set that in the AI or agent itself. Changing the inbox rules is done with settings, without custom work, even if you do not work with computers much. After three months, no email is left unattended because nobody knew it was theirs to handle.
If you see a question that comes back every month, a suggestion for that question later sits ready at the inbox, with the reason attached. You say yes or no. The inbox is the first task, not the whole offer: we take your office through this step, and after that, every correction becomes a rule Bombos keeps, so the next task starts from what you already agreed.
The empty inbox is just the start.
Once the inbox is under control, you suddenly see how much other work arrives through the same route, and how much of it depends on the same knowledge.
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
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.
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.
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 Outlook, it stays a proposal.
Working agreements that only live in a colleague's head are something Bombos does not know. That is why your AI asks your colleagues once about those assignment agreements, and Bombos keeps the answers, so the suggestion names the right colleague next time. An unclear email or an unknown sender also does not always make clear which customer or colleague it belongs to. When in doubt, your AI puts the choice to you. A suggestion that reads convincingly can still be wrong, even when the sender's name looks familiar. So the chosen customer, colleague and answer text are all part of reviewing the email.
You approve before an outgoing message goes to a third party, through any channel, including an answer from the shared inbox. You set that in the AI or agent itself. A colleague's name next to a suggestion does not mean the sender already has an answer. Sorting the inbox is also not the same as actually handling every question. A question about a customer still depends on what is in the available email and your software. A read email still needs someone to pick it up.
What does your AI forget?
- 01You tell us which AI you use and where it keeps starting over.
- 02We show what a shared memory changes there, on your own examples.
- 03You keep the plan, with or without Bombos.
