Piet BaudoinBy Piet Baudoin, updated September 26, 2026

How do you do order entry for orders that arrive by email?

Order entry for an order that arrives by email or as a PDF happens by hand today; your AI reads the order and the attachment, finds the customer and gets a schedule proposal with a draft confirmation ready for you to process.

Works with your own scheduling software, calendar and accounting package.

The order email is the first task; what you correct about your customers stays in one 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

Regular customers order by email with an attachment, or with "just the same as last time", and the office staff look everything up and retype it.

Today, someone on the office team reads the email, finds the customer and retypes the job into your software. "Same as last time" sits above the attachment. First, they must identify the customer, the job address and what is being requested. A request through Jobber's client hub is already processed digitally, but with a separate email, the work starts with reading and looking things up.

Withbombos

The order from the email and the attachment is ready for your schedule, with the confirmation to the customer attached.

The job is ready as a proposal, with the details your schedule needs. Your AI reads the email and PDF and finds the customer details, with what Bombos remembers. You see the requested work, customer and address, with the reason they belong to this job. The draft confirmation is ready beside it. You review the proposal, correct anything that is wrong and send the confirmation. After your approval, if your AI has a connection to your schedule, it puts the job there.

After three months

After three months, every order is in your schedule without anyone retyping it. Your office team reviews instead of entering data, even with a PDF or "same as last time." Every order shows which email it came from.

What's ready for you then

  • Every order email is ready for scheduling
  • Including the PDF and "same as last time"
  • The customer confirmation is ready beside it
  • Every order traceable to its email

Where do you see that?

The order that came in sits on the list of proposals, with the details found and the draft reply attached. You see which email was read and why that customer was attached to the order. You read the description from the attachment next to the customer details found and adjust the work order proposal. The draft confirmation belongs to that same job, so you read the text to the customer next to the content of the order. Your package does not have to be open beside it.

With "ready for you" you see that the preparation is waiting for your review. "Waiting on your input" means there is still a question, for example about the address where the work has to happen. That question sits with the email and the attachment you are looking at. With every proposal you see where it came from.

How does it start?

It starts with a conversation of about an hour in the first week, in which we go through an order email with an attachment together. Which inbox receives the orders, where do the customer details live and which scheduling package do you use? You say which details you need before an order can be processed. We also agree who decides when the email and the attachment say different things about the work.

After that, your AI starts the first task with proposals. The reading, lookup and preparation start with the order and the attachment as they come in. You keep your own package and inbox, nothing moves and no training is needed; we set it up together. If you correct a customer found or the reading of a request, that correction is the rule from then on. Bombos keeps those corrections as rules; without them, it does not know how you read a request. 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 the confirmation to the customer; you set that in the AI or agent itself.

The order email is the first task, not the whole offer. We take you along on that first step, and after that, every correction becomes a rule Bombos keeps, so the next task starts from what you already agreed. We would rather you did not keep coming back to us. After three months, every order is in your schedule without anyone retyping it.

Every order in one shared memory.

Retyping an order requires no judgment, yet a person still does it. A fast-growing business gets more of these emails every month, and the office team fills up first.

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 your scheduling software, it stays a proposal.

An order only becomes a final work order after you have approved it; it is not made out of every incoming email by itself. On the list sits the proposal with the details for processing and scheduling. A description in a PDF can be unclear. If the email names a different visit address than the attachment, you decide which address is right; your AI puts that question to you.

What a customer only mentioned by phone is not in the email or the PDF. That is why your AI asks you once what was agreed verbally about the job, and Bombos keeps the answer, so that information is in the proposal right away next time. The customer found and the summary of the work can contain mistakes too, so check them.

You approve before a confirmation goes to a customer, on every channel. You set that in the AI or agent itself. A delivery date that has not been agreed yet does not belong in that message as a promise. The work starts with the email; the decision is about the job you make of it.

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.