Abstract: A method and system for providing a translation decision assistant. The document is processed to determine a value and document insights. The value is a quantification of the impact of the content to the business. The insights include language, personally identifiable information, and the domain of the work. These insights and content value are evaluated against prior job history to identify suitable resources for the translation job. A machine learning aggregation process extracts resources including people, machine translation engines, terminology, and workflows. The machine learning aggregation process from prior training selects resources from the various evaluations. A constraint filter processes the resources with external constraints including hard constraints and soft constraints. Hard constraints include translator certification, languages, and permissions. Soft constraints include quality, availability, costs, and service levels.