Each Luminorix agent is an AI employee with a role. It works in Teams, Telegram or email, remembers how you like things done, and drafts the next step for a person on your team to approve or send.
You choose the name, the role and the channel on the first call.
Three agents that run real work today. Each is set up with a named owner.
Works in: Teams
What it did: Renamed and filed 5 remit files to the client’s shared folder in its first run on 2026-10-07. Its weekly Monday filing run starts 2026-10-12.
What it asks you: A person to sign in when a payer portal shows a robot check.
Works in: Email, Teams and Telegram
What it did: Drafts campaigns and posts, and writes call recaps from the Teams transcript.
What it asks you: Approval of every post. Only named people can approve.
Works in: Email and the ERP
What it did: Produced the September 2026 vendor sell-through report from the ERP on 2026-10-07, in the format the vendors already use.
What it asks you: A decision on anything that does not match. Those bills are held for you.
Your agent gets its own name, role and channel. It keeps what you correct, so next time it is done your way.
The agent, in the channel you already use, and a named person on our side if something looks wrong.
For the steps that matter it comes to you as a card first. Corrections stay with it. Every action is on the record, and where an action can be reversed you can undo it.
Yes. It runs on a schedule and on events, and leaves you a short note of what it did and what waits for you.
We do. We connect your systems on a call, start with one job, and add more when you are ready.
Claude is very good. Using it on its own, or through a desktop tool such as Cowork, is a fine way to get one person more done. Running a business function on it is a different job.
| Where it gets hard | Claude or Cowork on your own | Luminorix |
|---|---|---|
| Across the organisation | A good fit for one person's own work. Sharing it across a team is left to you. | Set up and run for a team, so a new person uses what is already working. |
| Your data | It sits in the account that set it up. Where it goes is yours to manage. | A workspace for each customer, a record of actions, and a plain list of what we do not have yet. |
| What it costs | Model usage adds up with every task, and someone has to watch it. | Model usage is our job to manage. You see the work done, not a usage meter. |
| When nobody is at the desk | Usually runs when a person starts it. | It runs on a schedule and on events, and writes to you in Teams, Telegram or email. |
| Who sets it up and runs it | You do. | We do. A named person on our side answers when something looks wrong. |
Built on Claude, operated by us, embedded in your business. It works when nobody is at the desk, lives in your channels, has a name, a role and a memory, has control built in, and is done for you.
AI agents draft the next step. For the steps that matter, you get a card with the reason and you approve or hold. Every action is on the record, and where an action can be reversed you can undo it. A spoken yes never approves; you tap.
Send 2 reminders. Hold 1 for you.
You read each draft first. Where an action can be reversed, you can undo it.
Example card on example data. Nothing here is connected to a real system.
A short call with our team. We start from your kind of work and show you the first result. Pricing is shared on the call.
Luminorix