Define Acceptance Criteria
From use case: Define Acceptance Criteria
Amazon Web Services, Amazon’s cloud computing unit, reports it used AI to automate test case generation in automotive software. It found that the test case creation time was reduced by up to 80%, helping dramatically improve efficiency and maintain quality.
Financial services firms integrating digital commerce capabilities also report gains. One multinational bank’s retail division reduced clarification requests during sprint planning by 62% after deploying automated acceptance criteria generation for mobile commerce features. The technology proved especially valuable in strengthening security and payment card industry compliance.
Technology consultancy Thoughtworks used generative AI with a client to expand the capacity of existing features. The client’s quality analyst concluded the AI-generated acceptance criteria and testing scenarios were better than
what they could have produced by themselves and estimated there were about 10% fewer bugs and reasons for
rework than usual. Overall, there was about a 20% reduction in analysis time.
IndustryARC, a market research and consulting firm, projects the Software Development AI Market will grow to $1.3 billion at a compound annual growth rate of 20.9% from 2024-2030. Fueling that growth, the firm says, is AI’s ability to reduce the cost and time required for software development. Bain & Company says generative AI appears to save about 10% to 15% of total software engineering time, with improvements up to 30% possible by organizations that leverage the full potential of generative AI.
Success depends on maintaining reusable template libraries, training AI models on commerce-specific data, and adopting AI gradually to build user confidence.