Recent research on neural network-based agents for coordinating and filtering information is presented. Neural net agents have advantages over rule-based agents because they can be easily adapted to the information needs of the user through the learning capabilities of neural networks. Three application areas for these agents are discussed: electronic bulletin boards, Group Decision Support System (GDSS) meetings, and electronic mail (e-mail). This paper reports accuracy results of the network for electronic bulletin boards and meeting messages. The agents could accurately filter messages, under optimal conditions, in the range of 85% to 99%. Interface designs for incorporating these agents in GDSS and e-mail systems are discussed and illustrated. The advantages of neural network-based agents over rule-based agents are discussed also.