Purpose ‐ This paper seeks to propose a new approach for tackling the uncertainty and imprecision of identifying suitable supplier offers, evaluating these offers and choosing the best alternatives in bi-negotiation. In a build-to-order supply chain, the handling of uncertainties is addressed by a real time information sharing system and appropriate supplier selection. Design/methodology/approach ‐ A methodology integrated analytic hierarchy process (AHP) with bi-negotiation agents based on the multi-criteria decision-making approach and software agent technique is then developed to take into account both qualitative and quantitative factors in supplier selection. Findings ‐ During the decision-making between buyer and suppliers, the AHP process matches product characteristics with supplier characteristics. Next, agents assist the user in the debate to negotiate a joint representation of the supplier chosen and automatically justify proposals with this joint representation. Originality/value ‐ This study focused on a multi-attribute negotiation mechanism including qualitative conditions, which enables automated negotiation on multiple attributes. Finally, a fuzzy membership function represented the joint representation's cognition for each condition such as quantity, price, quality, and delivery for the outsourced component. A case study in a high-end computer manufacturing company is given to demonstrate the potential of the methodology.