Brunella: an AI team that works inside your company
You talk to it on Telegram. It handles the daily, repetitive information work, and anything it would send outside the company, you approve first.
A day with Brunella
Not a made-up demo. This is how our own team works every day, without client data.
- Morning
One message with the day ahead: important emails, calendar, and the system's suggestions.
- During the day
Outreach emails are prepared as drafts. We send them, not the machine.
- Every four hours
A review of the task board. If something is stuck, the system says so and names who has to decide.
- At night
Four suggestions for the next morning, drawn from the day's work.
The team
- Brunella
Lead agent: takes the requests, hands out the work and sums up.
- Kenshin
Software development, bug fixing, version control.
- Lumen
Websites, interfaces, frontend.
- Aura
Market research, finding and checking sources.
- Irisz
Data analysis and reports.
- Nyomozó
Looks up earlier decisions and history.
- Zeph
Scouts new tools and capabilities.
- Stratéga
Growth and marketing strategy.
- Agybackup
Backup engine when the main AI engine is unavailable.
- Pilotbackup
Backup engine when the main AI engine is unavailable.
With a client, we shape the team around the company's work.
What it does, and what it doesn't
How it starts
30-minute demo
We show our own system live.
Assessment
We pick 2-3 repetitive jobs to start with.
Installation and setup
On the company's computer (macOS or Linux).
Maintenance
Updates, proven recipes, error alerts.
Brunella System · Beta
One chat. One team. Working through the night.
Brunella isn't a chatbot. It's a team of AI colleagues running on my own machine: they know my projects, remember past decisions, and keep working on their own even when nobody is at the keyboard. I stay in touch with all of it through a single channel: Telegram.
"Brunella's dashboard: agents, tasks, memory and schedules in one place."
What this actually is
The difference isn't the answer, it's the work
A typical AI assistant answers a question, then forgets everything. Brunella does the work instead: it looks things up, reads files, puts together a document, adds a calendar entry, kicks off a process, and then reports back that it's done.
And it doesn't work alone. The system is made up of several separate specialists who work independently but talk to each other. When I hand off a task, my first question isn't "can this be done" but "who on the team is best suited for it."
The user interface is a single Telegram message. Everything else happens behind the scenes.
"That's the whole interface. No separate app, no learning curve."
A real example
Four words, and a finished strategy
This isn't a made-up case. One afternoon I sent a voice message that said nothing more than: "It's yours to handle." The system transcribed the voice note, understood it was a handoff of a decision, and instead of asking follow-up questions, it got to work.
What happened between those two messages: it read through all twenty-three project notes in my knowledge base, compared the eight client projects, checked the real status of my five own products, spotted a pattern across them that I hadn't noticed myself, then wrote it up as a structured, readable document, and drafted the client emails that go along with it.
The one thing it didn't do: send anything. It prepared the emails, but left the sending to me, because that's an irreversible step. More on that later.
"Four words in, a finished document out."
The team
Eight specialists, each with their own job
The members of the team run separately, each with its own personality and its own memory. They aren't copies of the same program: each has a different specialty, and some even run on a different AI engine, because that's the better choice for that particular job.
When a task is complex, the coordinator breaks it up and hands the pieces to whoever is best suited. The specialists can also message each other directly, so work keeps moving even while I'm dealing with something else.
"The team. Everyone runs separately, but they work on the same thing."
Memory
Nothing needs to be said twice
With most AI tools, every conversation starts from zero. Not here. The system has three kinds of memory, roughly the way a person does: what matters right now, what's a lasting habit or setting, and what's a lesson learned from a past mistake.
When a topic comes up, the system searches the notes not only for the exact words but also by meaning. That's why it can still find a decision from months ago, even if I phrase today's question completely differently.
On top of that, important knowledge also gets written out into human-readable notes that I can review myself. It's not a black box: I can check at any time what it knows about me, and why.
"Three layers of memory, searchable and readable by a human too."
Learning
What was hard once becomes a recipe the second time
This might be the system's most unusual trait. When an agent pulls off something complex, or runs into an error and solves it, it writes itself a recipe afterward: when to reach for it, what the right order of steps is, and which pitfalls it just ran into.
Next time, it doesn't start from scratch. This isn't theory: on one such day, two new recipes were born this way. One of them captured exactly where file paths tend to trip things up during voice-message transcription. That mistake won't happen again on this team.
The proven recipes reach the other installations too, as updates.
"The system writes down what it learned, for itself."
Task management
A board that breaks down the work on its own
Tasks live on a board, the way they would on any team. The difference is that the system itself breaks a large task into smaller steps, and assigns each one to the right specialist.
The board flags a card that's been sitting too long.
And there's one rule I care about. If an agent gets stuck and needs me, it doesn't just quietly stop. It writes on the card exactly what I need to decide, and moves the card to my name, so the responsibility stays visible.
Background work
It keeps working even when nobody's watching
Every half hour during the day, the system looks around on its own: is there an unanswered message, did anything happen worth remembering, did it learn something new that deserves a recipe.
The most important rule here is silence. If there's nothing worth reporting, it stays quiet. An assistant that checks in every hour to say "nothing to report" becomes unbearable within a few days. This one only writes when there's actually a reason to.
On top of that, scheduled jobs run too: daily and weekly cycles that we set up once, and which run on their own after that. At night, for example, suggestions for the next morning are drawn from the day's work.
"Daily and weekly cycles, unsupervised."
Control
Autonomy comes in degrees
This is the part most people ask about, and rightly so: what happens when an AI works autonomously and gets something wrong?
The answer is that every type of action in the system has its own autonomy level, which I set myself. At the first level, it only tells me what it would do. At the second, it asks for permission and waits for my answer. At the third, it does the work and reports afterward.
By default, anything irreversible or outward-facing requires approval. Sending an email, deleting data, making a payment, publishing something publicly: the system prepares these, but it never presses the button for me. That's not a limitation; it's exactly what makes it safe to use with confidence.
Access
Not cut off from the world
An assistant is only as good as the tools it can actually reach. Brunella can be connected to email, a calendar, cloud storage, a code repository, a notes system, a browser, and an automation engine, and through those it does real work, not just talks about it.
I turn on each connection one at a time, and can revoke any of them at any time. Passwords and keys live in an encrypted vault, not in the conversation.
Multiple systems
Two teams can connect when needed
If someone else has their own Brunella system, the two can be linked. In that case, my team can ask a specialist on the other side a question, and vice versa, without either side giving the other access to its own data.
The boundary is strict: only the text of the task crosses over, never a secret, a password, or personal data. The system treats anything coming from the other side as data by default, never as a command.
By the numbers
Where the beta stands right now
The memory, the notes and the task board are stored on my own machine. The text itself is processed by the AI model in the provider's cloud, so whatever the system processes also goes there.
The honest part
This is a beta. It changes day by day, and not every part of it is equally mature yet. I'm not promising it's flawless; I'm promising that it won't hide it when something didn't work, and that a human always makes the call on anything irreversible. Based on the last few months, the system isn't useful because it knows everything. It's useful because it remembers, it learns, and it doesn't stop when I close the laptop.
Frequently asked questions
Where is our data?
On the company's computer: memory, notes and the task board are stored there. The text itself is processed by the AI model in the provider's cloud, so whatever the system processes also goes there. Data processing is set out in a separate contract.
What happens if it stops?
A health check reports the error. An outage at night is fixed in the morning, not at night.
What does the company need?
A computer (macOS or Linux), a Telegram account, a daily contact person and its own AI subscription.
Can I try it?
Yes: at the demo we show you our own system live.
