Most Intelligent Agent technologies have an architecture based on Belief, Desire and Intention (BDI) methodologies. The BDI model comes from research done in the field of artificial intelligence over the past twenty years and has proven to be the most robust and flexible model for Intelligent Agent Systems.

Intelligent agents using the BDI model have a:

	set of beliefs - that represent what the agent "knows";
	set of desires/goals that represent what the agent is trying to achieve;
	set of intentions to achieve the agent's current goals;
	set of plans that are combinations of actions which achieve certain outcomes or respond to events and are used by the agent to further its intentions.

When an event occurs the agent:

	looks for relevant plans (plans that responds to this type of event);
	then, for each relevant plan, the agent examines its appropriateness to the situation the agent finds itself in;
	then the agent selects and starts executing the most appropriate plan found.

Additionally the agent performs ongoing reasoning functions to decide:

	what goal to pursue or alternatively what event to react to;
	how to pursue the desired goal;
	when to suspend/abandon the goal, or change to another goal.

The agent may also vary its balance between reactive and deliberative by changing the amount of time allowed for deciding what to do next. This enables the agent to be more or less sensitive to changes in the environment, that is, be more or less "committed" to its current plan.