AI Agents Struggle with Healthcare Workflows, New Study Reveals
A new benchmark study finds that leading AI agents, including Claude and GPT, fail 72% of U.S. healthcare workflows, raising concerns about their reliability in this critical sector.
More from this archive
New Benchmark Reveals AI Healthcare Agents’ Struggles with Workflows
A new benchmark shows top AI healthcare agents from OpenAI and Anthropic fail 72% of clinical workflows, raising…
GStar 2026 Forum Set to Propel AI Collaboration in Asia-Pacific
The GStar 2026 forum aims to enhance AI collaboration in the Asia-Pacific, featuring top experts and a focus…
Anthropic and Gates Foundation Launch $200M AI Initiative for Global Health
Anthropic and the Gates Foundation have committed $200 million over four years to improve healthcare and education using…