AI Agents
AI agents are systems that use large language models to plan and take multi-step actions toward a goal — calling tools, using memory, and operating with varying autonomy.
Our coverage of AI agents and agentic systems — runtimes and standards, agent memory, reliability and guardrails, deep-research agents, and the products turning LLMs into autonomous workers.
Latest coverage
Articles
NewsCoding-agent harnesses can triple costs without clear accuracy gains, study finds
NewsBayer Crop Science builds multi-agent analytics engine on AWS
NewsZoom launches Unified Context Layer for enterprise AI agents
NewsAgentic AI Foundation adds four open-source agent projects
NewsAnthropic plans Agent Skills donation to Agentic AI Foundation
NewsAnthropic opens Claude Duet preview to US Pro and Max users
NewsAction State releases open-source receipts for AI-agent actions
NewsScholarEvolve turns research papers into tested AI-agent harness changes
NewsOpenAI outlines distributed-agent study of mouse brain-cell data
NewsNVIDIA opens early access to Factory Operations Blueprint for industrial agents
NewsNVIDIA launches OpenShell architecture for governed AI agents
NewsMotive launches AI agents for fleet safety and maintenance workflows