Model based approaches have proved to be efficient in supporting engineering activities, models replacing traditional document-based approaches. Nevertheless even in most advanced deployments, a lot of engineering artifacts are textual either because the return on investment of introducing models is too low on this particular case or because the information is more efficiently expressed in natural language even if consistency and correctness issues appears. Huge progress has been made recently in AI-based Natural language processing (NLP), mainly driven by chat bots and vocal home assistant usages. The proposed idea consists in spinning in these technologies into space engineering process, studying how natural language processing can help the space engineer in daily activities. Many engineering domains can take advantages of these technologies. The most evident one are the requirement management domains as most of the requirements are textual and are generally not formally modeled even if they have a certain level of structure and rules. Using NLP technology semantic information can be extracted from textual requirements, which may have several advantages that will be evaluated: find related requirements to a given one, enhance search in requirement database, check consistency of traceability, smart comparison of specification contents, identification of suspicious requirements, identification of overlapping requirements, ... Natural language processing is also promising in linking related engineering textual artifacts (like design reports, justification reports, …) even with models contents.