Agentic AI

https://taxonomy.eticas.ai/risk/agentic-ai

Maturity: established

Risks arising from AI systems that autonomously plan, reason, and act across multiple steps using tools, memory, and external services, beyond single-inference interactions. These risks are distinct from standard LLM risks because the agent takes real-world actions, operates across time, and interacts with external systems and other agents.

Also known as: AI Agents · Agentic risks

System type: Large language models (LLM)
Lifecycle stages: Post Processing

Risk groups

• Autonomous Actions and Tool Use — Risks from the agent taking real-world actions through external tools, APIs, and services, including being granted excessive permissions, executing unnecessary or out-of-scope actions, bypassing human oversight, or consuming disproportionate resources.
• Multi-agent Integrity — Risks from systems composed of multiple agents — including trust exploitation, cascading failures, goal misalignment between agents, and insufficient traceability across the pipeline.

Mappings to external frameworks

Standards & frameworks

Taxonomies & vocabularies