Hello, world! This is the very first post on the DMJBot blog, so it feels right to start at the beginning: what we are building, and — more importantly — why we decided to build it.
DMJBot stands for "Do My Job Bot." It is a personal AI assistant for work automation. Not another chat window you have to babysit, but an AI employee that keeps working for you 24/7 — while you sleep, jog, play tennis, or simply get on with your life.
The conversation that started it all
The idea began with a simple question.
"Recently I asked my tech-experienced husband whether ChatGPT could now do his everyday work for him, by itself. The answer was no. ChatGPT and other popular tools only work when you are sitting in front of your computer, constantly asking them something. The same is true for AI coding assistants. All of these tools are passive — they wait until you ask. To get real automation you need an orchestrator, and that is complex to set up."
That answer was the spark.
"Why not create an AI assistant that can work for you 24/7 and be proactive and event-based? What if the assistant had initiative? What if it worked like an orchestrator, but was simple and intuitive to set up using nothing but chat instructions? What if it could work for you while you are sleeping, jogging, or playing tennis — because you have already told it how to act in most scenarios?"
And so DMJBot was born: a personal AI assistant whose goal is to become the single interface to all the tools you use when you work with a computer.
Why we are building it
After many conversations — especially with software developers — one thing became clear. A large part of office work can already be automated with today's AI tools. And yet there is still no assistant on the market that is at the same time simple to set up, secure, and genuinely easy to use.
The AI tools we have are powerful, but they are fragmented, numerous, and increasingly hard to manage. Every service has its own app, its own login, its own way of doing things. Tying them together into something that actually acts on your behalf is still a job for experts.
We think it should be a job for a sentence in a chat.
What DMJBot can do
The assistant is event-based. You give it instructions once, it remembers them, and it acts when something happens. A few examples of what that looks like in practice:
"Hey, please monitor my email. If a message arrives from my boss with the subject urgent, reply with 'I am on it, will get back to you in 10 minutes,' then send me a notification."
"I'm expecting an email from Kate with a report attached. When it arrives, download the attachment, save it to my Dropbox folder
Reports/, reply to the email with a nicely written thank you, and let me know when it's done."
You describe the scenario. DMJBot waits for the event. It acts. You stay in control.
What we want to build
Here is where we are heading:
- Runs 24/7, hosted anywhere — SaaS on our infrastructure, in the cloud, on premise, or on your own local machine.
- Secure and easy to use — security and simplicity are first-class goals, not afterthoughts.
- Connected to tools and agents everywhere — it can reach tools and other agents running across different locations and environments.
- Available on web and mobile — interact with your assistant wherever you are.
- Orchestrates other AI agents — it can manage tools like Claude Code, Codex, and similar agents running in different environments.
- Event-driven — it monitors incoming emails, messages, calendar events, webhooks, and more, and acts the moment something happens.
- Integrates your services — Jira, GitHub, Slack, email, calendars, cloud storage, and beyond, mostly through the MCP protocol.
- Handles long-running work in parallel — ask it to "implement Jira task XX-123 with Claude Code and open a draft PR," watch the progress live in the app, and run many such tasks at once.
The vision is an AI-first way of working where humans stay in control and intelligent systems work seamlessly on their behalf.
This is just the beginning
DMJBot is a product in active development, and this blog is where we will share the journey — the ideas, the design decisions, the features, and the lessons along the way.
Thank you for reading our hello world. The AI employee is clocking in. 👋
