Agentic AI · AI Agent · Google · New York · Google Research
The core challenge of agentic AI is that, for an agent to be useful
Compiled by KHAO Editorial — aggregated from 2 sources. See llms.txt for citation guidance.
✓ KHAO Verified
However, this access together with agents’ behavioral flexibility requires meaningfully different approaches from those used in traditional software.
Key facts
- The team met at the Google Contextual Agent Privacy and Security (CAPS) Workshop, held in late 2025 in New York City
- Today, they share a comprehensive new workshop report, " Open and Emergent Problems in Agentic Privacy and Security: A Contextual Angle," the result of a collaborative effort bringing together more
- Eugene Bagdasarian, Research Scientist, and Marco Gruteser, Principal Scientist, Google Research
- Kassem Fawaz, Stefan Mellem, Helen Nissenbaum, and Nina Taft contributed to conceptualization, writing across multiple sections, and guided the writing process
Summary
Eugene Bagdasarian, Research Scientist, and Marco Gruteser, Principal Scientist, Google Research. To be useful, AI agents must understand and be constrained by contextual behavioral norms to ensure they act appropriately. They're rapidly transitioning to a computing landscape defined by highly general, increasingly autonomous agents. Today, they share a comprehensive new workshop report, " Open and Emergent Problems in Agentic Privacy and Security: A Contextual Angle," the result of a collaborative effort bringing together more than 50 academic and industry leaders from numerous institutions. The core challenge of agentic AI is that, for an agent to be useful, it may need to have access to personal data and the ability to take consequential actions across a broad range of contexts.