Technology
AI agent
An AI model that acts on its own: it plans steps, uses tools and takes actions, not just answers.
Agents can browse, write and run code, call APIs and operate accounts. The more they can do, the more a mistake or a prompt injection costs, so their permissions, the tools they can reach and human approval for risky steps are central security questions.
AI agent in the news
Recent stories that mention it.
Related
- TechnologyLLM · Large language modelAn AI model trained on huge amounts of text to understand and generate language, such as ChatGPT or Claude.
- AttackPrompt injectionHiding instructions in content an AI reads, so it follows the attacker instead of its user.
- ProtocolMCP · Model Context ProtocolA standard way to connect AI models to tools and data sources.
Plain-language explainers written by SecurityTabs, matched to stories by name. All terms