Engineering breakthrough: IBM introduces Watson AI for RQA

By | 2 minute read | February 28, 2019


In today’s age of growing engineering complexity, connected products and the Internet of Things (IoT) are changing the way we live and work. Engineering teams are facing pressure to quickly adapt to the pace of change in nearly every industry, with more data than ever to leverage. Enter artificial intelligence (AI) for engineering. 

IBM® is bringing the power of IBM Watson® AI to the end-to-end engineering lifecycle, delivering new innovations in requirements management for systems engineers. Embedded in IBM’s engineering requirements management solution, formerly DOORS Next Generation (NG), Watson brings new features to improve requirements quality early in a project. 

As any engineering team knows, requirements management is critical to the success of any project. Poor requirements definition results in project delays, cost overruns, and poor product quality. By integrating Watson AI into IBM‘s Engineering Requirements Management, engineering teams can more easily flag poorly written, incomplete, and ambiguous requirements while receiving real-time coaching from Watson on how to improve them. 

Watson AI uses natural language processing and understanding to analyze a requirement’s text, suggesting improvements that leverage industry best practices for writing high quality requirements, based on the INCOSE Guidelines for Writing Good Requirements. 

With a built-in, pretrained AI capability, this new-and-improved solution provides 10 quality indicators, with more to come in the future. In a single-tool environment, the new Watson capability helps mitigate risk and ambiguity in the authoring phase, using rapidly integrated AI functionality. Watson will score the quality requirements and present suggestions on how to improve them. Requirements reviewers in turn receive clear, consistent, and complete requirements from these authors, enabling them to review for technical intent instead of structural issues.

Benefits of using AI for Engineering Requirements Management:

  • Reduce errors
    • The requirements analysis phase takes up only 2 percent of total design time, but poor requirements account for more than half of all engineering errors.
  • Reduce Costs
    • The cost of correcting errors increases exponentially as a project progresses. Decrease product development costs and delays by catching errors early and reducing rework.
  • Strengthen Requirements
    • Isolate requirement issues before they are sent for manual human review. Receive suggestions for improvement based upon a score provided by Watson.

Additionally, engineering teams are faced with the ‘gray washing’ of their industries as senior employees reach retirement. The next generation of requirements authors can only benefit from their predecessors’ expertise.Teams can disseminate engineering expertise to junior engineers who are less experienced in writing requirements. This mitigates the risk of losing valuable existing knowledge from employee turnover and a retiring workforce. 

IBM‘s Requirements Management Quality Assistant accelerates the requirements review process and reduces costly ambiguities. Focusing on the business and technical intent of the requirements—instead of structural issues—reduces the risk of defects later in the process. 

Check out this video on how IBM is bringing Watson AI to engineering.

Learn more about Requirements Quality Assistant – watch the webinar