
The deployment of autonomous AI agents in production environments represents a paradigm shift from stateless language models to persistent, goal-directed systems with access to external tools, persistent memory, and real-world effectors. These agentic systems execute multi-step plans, maintain state across extended interactions, spawn subagents for specialized tasks, and interact with external APIs and databases. While this evolution enables unprecedented capabilities in domains such as software development, financial analysis, customer service, and infrastructure management, it simultaneously introduces attack surfaces and vulnerability classes that differ fundamentally from those encountered in traditional language model deployments.
Risk intervention, AI safety, Agentic AI, Post-deployment governance, Runtime monitoring, AI Compliance, AI governance, Autonomous systems
Risk intervention, AI safety, Agentic AI, Post-deployment governance, Runtime monitoring, AI Compliance, AI governance, Autonomous systems
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
