In this paper, we describe a prototype agent-based decision-support system for helping suppliers respond to requests for quote in a business-to-business supply chain. The system provides suggested ways of fulfilling requests and shows alternatives that illustrate tradeoffs in quality, cost and timelines, which allows the decision maker to consider alternatives that reduce cost and improve customer value. The system is implemented in Java and we use examples from paper manufacturing to illustrate the features of our system. In on going work, we are enhancing the prototype to include probabilistic reasoning techniques so that it can create conditional plans that maximize expected utility, subject to the risk preferences of the decision maker. We are also exploring the use of data mining techniques to infer customer preferences and to estimate the probability of winning an order, with a given quote.