From Prompt to Product: A Human-Centered Benchmark of Agentic App Generation Systems

This article likely presents a research paper focusing on evaluating systems that generate applications based on user prompts. The 'human-centered' aspect suggests a focus on usability and user experience in the evaluation. The use of 'agentic' implies the systems utilize autonomous agents to fulfill the prompt's requirements. The benchmark likely involves a set of tasks and metrics to assess the performance of these systems.