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
NewsOpenAI's BioBasicsBench tests wet-lab AI agents
NewsAWS maps a six-agent product development workflow in Quick
NewsOumi expands Frontier AI Engineer into agent development
NewsKORA announces AI-focused Linux desktop for 2027
NewsTCS builds governed test orchestrator on Amazon Bedrock AgentCore
NewsAina opens $399 preorders for smart ring that lets users approve AI agent actions
NewsAWS releases UAEF for cross-framework AI agent evaluation
NewsAWS sets AgentCore Runtime V2 as the default in 19 regions
NewsAirbnb targets first half of 2027 for AI travel agent rollout
NewsAWS launches Web Answer for Bedrock AgentCore in us-east-1
NewsMistral expands Studio with managed agents and enterprise apps
NewsIBM and Microsoft launch Imagine Enterprise agent platform