Piet BaudoinBy Piet Baudoin, updated September 26, 2026

How do you answer a time off request that arrives by email?

A time off request or leave request that arrives by email gets a draft reply from your AI, with the leave rules Bombos keeps, which you lay next to the balance in BambooHR and the schedule before you decide.

Works with BambooHR and however your hours come in.

Leave by email is a small task to start with; your leave rules stay in one shared memory for every AI your team uses.

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

"Can I have the 14th off?" waits for someone to pull up the schedule and the balance.

Today someone looks up the balance in BambooHR and opens the schedule for every leave email, which is why the answer sits there. The email says which day someone wants off, but everything you need to decide is elsewhere. BambooHR already has a time-off route with the balance shown and manager approval. For a loose email, you still do the reading and the lookup before you can say yes or no.

Withbombos

The draft reply is ready, so all you have to do is lay the balance and the schedule next to it.

Your AI reads the leave email, looks up the available details, and prepares a draft reply with the reason attached. For your decision, you compare the proposal with the balance in BambooHR and the schedule: the text is ready, but you still judge the balance and staffing. Missing or uncertain information comes back as a question. You add your decision, send the reply, and record the leave in BambooHR.

After three months

After three months, every leave request gets an answer the same day. Bombos knows your rules, so the drafts are more often right and you decide faster. The groundwork around leave no longer sits waiting. You see which rule each draft rests on.

What's ready for you then

  • Every leave request answered the same day
  • The draft is ready, you decide yes or no
  • No colleague waits days for an answer
  • Your leave rules finally recorded

Where do you see that?

The prepared replies to leave requests sit on one list. For each proposal you see the reason and the status "ready for you" or "waiting on your input." You do not need to have BambooHR open to view the list of proposals.

"Ready for you" means a draft is there to check. With "waiting on your input," there is a question about information or a decision still needed. That way you see which leave request you can pick up and where you first need to add something. For your check, you pull up the balance and the schedule.

With every proposal you see where it came from. The list of proposals keeps the preparatory work visible; you process the leave booking in BambooHR after your decision.

How does it start?

In the first week we look at the leave requests together, in a setup conversation of about an hour. We discuss which mailbox receives the requests, which package you use, and which rules apply to the replies. We look at the work that comes in by email alongside the existing leave route in BambooHR. In that conversation we also write down the house rules for leave that up to now only existed by word of mouth.

Your AI then starts on the first task. Every task starts with proposals: the leave reply sits as a draft ready for your check. Your corrections become the rules for next time. That is how you show how a leave request should be answered at your company. Bombos keeps your corrections as rules; without them, it does not know how you answer a leave request.

You keep your mailbox and package, without moving anything or taking a course. We fill in the settings together. 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 set in the AI or agent itself that messages and bookings wait for your approval. With every proposal you see where it came from.

When you see the same house rule keep coming back in your corrections, your AI proposes it to you as a standing rule, with the earlier requests as the reason. You say yes or no.

The leave is the start, not the whole offer. We take you through the first step; after that, every correction becomes a rule Bombos keeps, so the next task starts from what you already agreed. After three months, a leave request gets an answer the same day.

From leave email to one shared memory.

A leave email looks like a small task. Yet it is typical of the work that consumes a growing company: looking something up, then fitting it around everything else.

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 BambooHR, it stays a proposal.

Leave is not granted without your approval. Checking the balance and the schedule stays with you, and the processing in BambooHR follows only on your approval. A prepared message contains the text to check, then, not the permission to stay away.

Bombos only knows the leave arrangements that are in the mail, the text messages, or the package. An arrangement made between people that is written down nowhere does not come back in the proposal. That is why your AI asks you once which house rules you use for leave, and Bombos keeps the answer, so you can add what matters for this request. A proposal can be wrong even when your AI shows no doubt; the content needs a check before you use it in the leave request.

You approve before any message goes to the requester or the client, on every channel, even a short reply to a leave request; you set that in the AI or agent itself.

The work sits in the decision behind that short yes or no.

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.