How does a leak a resident reports on info@ become a work order for the contractor in your homeowners association software, without any digging around?
A resident report becomes a work order suggestion by reading the email, looking up the resident and the supplier, and getting the details ready for your review.
Works in your own Outlook, next to your own software.
It starts with the leak reported to info@; who manages which building stays in one shared memory for every AI your team 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.
A resident emails that water is dripping from the ceiling. The plumber does not know about it yet.
The email describes what is leaking. A photo of the ceiling is attached, and the address sits in an earlier email. You work out which association the report belongs to, who the regular plumber is and which details the work order needs. Then you create the order in Convect, where the technician's invoice will also sit, and only then reply to the resident. TwinQ has its own mail assistant for sorting and drafting replies.
The work order for the regular plumber sits ready, with the reply to the resident underneath it.
For the leak report, the work order details are ready. Your AI reads the email, looks up the resident and the association, and adds the regular supplier from the recorded information. You get a suggested work order and a draft reply to the resident, with the reason attached. You check the details, decide on the order and send the message. If the right resident is uncertain, your AI asks you.
After three months, the right work order is ready for every report, without anyone working out where it belongs. Your property manager approves it, and the resident quickly knows what to expect. What once lived only in the manager's head is now recorded.
What's ready for you then
- Every report goes straight to the right association
- The regular plumber's work order is ready
- The reply to the resident sits underneath
- You approve, without searching or retyping
Where do you see that?
The suggestion for the maintenance order sits on the same list as the other prepared work. Next to the leak report you see the reason and the status "ready for you" or "waiting on your input". The resident details found, the suggested supplier, and the reply text sit together. Your homeowners association software does not need to be open separately for that review.
A maintenance order on the list of suggestions waits for your decision on the details and the supplier. You compare the address found with the resident's report. With every proposal you see where it came from. The plumber's name next to the report does not yet mean they have received an order. The suggestion for the contractor and the reply to the resident are each recognizable as prepared work.
How does it start?
In the first week we go through a leak report on info@ together, during a setup conversation of about an hour. You show us the mailbox with resident reports and the homeowners association software. We look at where the resident details and regular suppliers sit and fill in the rules for the first task. We also agree on who reviews the order suggestion. You give access to the systems needed. Your existing email and software stay where they are; nothing has to move. No course is needed, even if you do not work with computers much. In that same conversation, we also record which regular plumber belongs to which association, instead of leaving that only in the manager's head.
After that, your AI starts preparing the maintenance order with proposals. A correction to the resident details or the regular plumber becomes the rule for the next report. Bombos keeps those corrections as the rules for which resident details or plumber belong to the report. 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 messages to the resident and the contractor; you set that in the AI or agent itself. The rules for reports are settings, without custom work.
After three months, the right work order is ready for every report without anyone working out where it belongs. The reports are the first task, not the whole offer: after that, every correction becomes a rule Bombos keeps, so the next task starts from what you already agreed.
Every association in one shared memory.
Every new association brings more reports, residents and suppliers, and who handles what mostly lives in your property managers' heads.
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 Convect, it stays a proposal.
You approve before a maintenance order is recorded in Convect. The order sits ready with the details found in it; only once you approve it, and if your AI has a connection to Convect, does it go there. Picking a regular supplier goes by what is in the reachable email and your software. Which plumber belongs to which association is often not written down anywhere. That is why your AI asks you once which regular supplier belongs to which association, and Bombos keeps the answer, so it is suggested next time. When in doubt, your AI asks for your judgment. A familiar name in the email is not enough to fill in missing details about the resident or the association.
An order suggestion can be wrong. The resident details, the supplier, and the content of the order all need review, therefore, before anything happens with them. You approve before outgoing messages go to third parties, whatever the channel, for both the reply to the resident and the message to the contractor. You set that in the AI or agent itself. Getting a reply ready is not a promise that the plumber is coming. The resident reports what is leaking; the order tells the plumber where to go.
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.
