Diabetes management is a complex problem and the patient needs to monitor several parameters and react differently according to them. A diabetic needs to understand different rules to manage different situations. These advice are usually transmitted in medical appointments and learned by experience. The patient is on a continuous process of managing the disease.

Our approach was to design a system able to accompany the user, advise and guide through different diabetic's known problems. To accomplish this goal, we incorporate the medical protocols , advice and directives in a Rule Based System. This Rule Based System which we call ac{ARBS} is capable of advising and uncovering possible causes for different occurrences.

We believe that this solution, is not only beneficial for the diabetic, but also for the doctor accompanying the situation.
The advice and rules are useful data that the medical expert can use while prescribing a particular treatment.

We have started to add data-mining algorithms and methods, to uncover hidden behaviour patterns that may
lead to crisis situations. This approach has the potential for automatically adding new logical
rules, able to trigger in a particular contexts.
The proposed system will accompany the user at start with generic advice, and with constant learning, advise the user more specifically.
We discuss this approach describing the architecture of the system, its base rules and data-mining component.
The system is to be incorporated in a currently developed diabetes management application for Android.