AI Agents
AI agents are LLM-powered systems that don't just answer — they plan steps, call tools and drive a task to completion: writing code, searching the web, booking, analyzing. 2026 became the year of agents, from coding agents to autonomous researchers. This page gathers all our coverage of agentic AI: launches, protocols (MCP, A2A), reliability and real-world use.
DeepMind unveils AlphaEvolve: a Gemini-powered AI agent for development and science
DeepMind has launched AlphaEvolve, a Gemini-based AI agent that automates development and is used in business, infrastructure, and scientifi
AI agents with vision proved several times more expensive than a standard API
Vision-enabled browser agents cost companies significantly more than standard APIs: each screenshot has to be processed by a powerful vision
AI agents are changing development: Cursor and Claude Code against the skeptics
How to Measure an AI Agent's Performance in QA: The Story of a Benchmark
Two windows with an AI agent instead of one: architect, developer, and six types of errors
MELT-1: how Metabolic AI tests agents for survival
Intruder created an AI agent that conducts pentests in minutes instead of days
Intruder launched AI for pentests that previously cost $50,000 and took weeks — now they take minutes.
LazyWeb connects AI agents to the designs of 257,000 real apps
The LazyWeb MCP server gives Claude Code and other AI agents access to the visual context of 257,000 real apps to generate realistic interfa