When an agent receives a query from another agent, it tries to satisfy it by building an answer based on its current knowledge. Depending on the available time or the urgency of the requirement the agent can produce answers with different levels of quality. Answers can contain the best one, a provisional one because it can be improved later, or a conditional answer because the agent ignores some information needed to build the answer. Agents always depend on the availability of information obtained from perception or from the communication with other agents. We assume that in the real world normally is better to receive an answer with poor quality than no answer. The answer can be good enough for the receiver or the receiver can spend more time to wait for a better answer. Autonomy implies taking the best decision with the available information, avoiding blocking situations and no action. In this paper, we propose an architecture for deliberative agents using anytime like reasoning to produce better answers as time increases.