Guide · Devices, robotics and AI agents
Connected devices and AI agents:what a small team can automate now.
A connected device is a sensor or a machine that reports what it sees to software; an AI agent is software that uses tools to complete a task in several steps. Together they let a small business automate work that used to need a person on site. Here is what is realistic and where a person still decides.
What a connected device can do for a company
A connected device does three things: it measures, it alerts and, sometimes, it acts. A sensor in the store room reports the temperature every minute. A counter at the door records how many people came in. A machine reports that it has finished, or that it has stopped. None of this is new; the price is. A board like the ESP32 costs a few euros before the sensor and the enclosure, connects to Wi-Fi and runs from a USB charger for as long as its power holds.
The value is what you stop doing by hand, and what you learn once the data exists: how often the temperature drifts, how long a job really takes. A small board and a simple dashboard may be enough for one specific question. A managed platform may still be worth its subscription, even for a few devices, if it saves you maintaining updates, alerts and access control. Start with what you need to know, then compare the setup and upkeep of both options.
From sensor to screen: how an ESP32 IoT prototype is built
A simple monitoring prototype usually has four parts: a sensor on a board, a connection, a service to receive the data and a screen. An ESP32 or a Wi-Fi-equipped Arduino can send readings over the network using MQTT, a lightweight messaging protocol. A small backend service or Home Assistant can receive those readings and use them for a dashboard or alerts.
- 01 Sensor and board An ESP32 or Arduino reads the value: temperature, presence, a count or a machine state.
- 02 Connection Sends the readings over Wi-Fi, usually with MQTT, a protocol made for small devices.
- 03 Data and service A small backend or Home Assistant stores the readings and applies the rules.
- 04 What people see A dashboard, an alert on the phone or a field in the app you already use.
A prototype tests the idea: the sensor reads what you need and the alert reaches the right person. Production also needs a suitable enclosure, reliable power, firmware updates and support. Check the product requirements for the market where the device will be used or sold; in the EU, these may include conformity assessment, technical documentation and CE marking. Plan that work separately from the prototype.
Robotics and the physical world: what building robots taught me
My hardware projects were personal learning projects, not client work. I built robots to learn lidar, navigation with ROS 2 and sensors, built devices with Arduino, ESP32, ESP8266 and Raspberry Pi, and automated my own home with Home Assistant. I also designed iGrow, an automatic controller for growing conditions that I filed as a utility model application (OEPM, 2018). It is not an installation I can show you in a factory, but it is why I know what a device does when the Wi-Fi drops.
Robotics is a hard teacher because failures are visible: a robot that misreads a lidar scan drives into a wall. Software that responds to reality has to expect noisy readings, late messages and a dashboard that still shows the last 25 degrees after the sensor has dropped off.
That habit carries into the business software I build professionally: custom apps, business automation with RPA and AI, and agentic systems. Assume the input is sometimes wrong, check before acting, make failures visible.
AI agents: what changes for a small team
Rules and RPA still do most of the work well: when the steps are fixed, they are fast, cheap to run and predictable. What they cannot do is handle a case nobody wrote down.
An AI agent is software in which an AI model uses tools to complete a task in several steps: read the email, look the customer up, prepare the reply, hold it for review. It handles variation: a request phrased in ten ways, a document in a new layout. In return it needs a log of what it did, limits on what it may touch and a person who reviews the exceptions.
| Rules and RPA | AI agents | |
|---|---|---|
| What it handles | Fixed steps, known formats | Variation, free text, new layouts |
| When it fails | Unexpected cases can stop the flow; recovery needs rules | Can be wrong even on clear tasks; needs validation |
| Cost of setup | Low for simple tasks, grows with exceptions | Depends on the task, the model use and the review needed |
| Where a person reviews | Errors and stops | Exceptions and actions with consequences |
For a small business, AI automation means this: work that varied a little, and so needed a person, can now be automated, with a person still reviewing what matters.
When it makes sense to start, and how
Start when one question repeats every day: is the store room too warm, did the machine stop, who answers today’s requests. If answering it takes someone on site, or someone reading through requests, it is a candidate.
First we clarify what you need, by message or in a free consultation. For suitable projects, we agree a free basic demo: simulated readings or a device you already have feeding a dashboard, or an agent handling one type of request. The quote for the full build then sets out the features, estimated timeframe and price. Any hardware purchases or on-site setup are listed separately in that quote.
Security is part of the design from the start. Reverse engineering and bug bounty programmes, which I also take part in, shape how I design accounts, data and integrations: a device gets its own credentials and the least access it needs, an agent reaches only the data its task requires, and every action leaves a trace.
Sources and further reading
Questions before we start
Do I need custom hardware or can I buy something off the shelf?
Start by checking existing products: a smart plug, a ready-made temperature sensor, a counter. Custom hardware makes sense when those cannot meet a specific need. Compare the total cost, including setup, subscriptions and maintenance, rather than the board price alone. A prototype can help test the missing capability.
Can an ESP32 prototype go into production?
It can become the basis for a production device, but it needs a suitable enclosure, stable power, firmware updates and support. The product must also meet the requirements of its intended market, including conformity assessment, technical documentation and CE marking where required in the EU. The prototype helps define what that version needs to do.
What is the difference between RPA and an AI agent?
RPA follows predefined steps, clicking and typing as a person would. Unexpected cases can stop the flow unless error handling is built in. An AI agent uses a model and tools to choose its steps and can handle some variation, but it can be wrong even on clear tasks. Both need logs and appropriate checks; neither should silently act on an error.
Is it safe to connect devices and AI to my company’s data?
It is as safe as the design. Devices and agents get their own credentials and the least access their task needs, actions with consequences pass through a person, and everything is logged. We agree those limits before anything touches real data.