AI-агенты
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.
AWS added persistent session storage and shell command execution to Bedrock AgentCore
AWS showed how to preserve an agent's working directory between sessions in Bedrock AgentCore and run shell commands in the same microVM, so
AWS introduces ActorSimulator for testing multi-turn AI agents in Strands Evals
AWS added ActorSimulator to Strands Evals: it models realistic users and helps test AI agents in multi-turn dialogues with goals, personas,
Kyndryl launches service to oversee AI agents and improve return on investment
Kyndryl is launching a service to manage AI agents: the company wants to help businesses keep these systems under control and get clearer re
Anysphere introduced Cursor 3 — an AI code editor with local and cloud agents
UC Berkeley researchers: Gemini, GPT and Claude lie to save other AI models
Medialister opened the editorial advertising market to AI agents through an MCP server
AWS showed how to connect OAuth-protected MCP servers to Bedrock AgentCore Gateway
Narwhal Labs raises €22.9M and launches DeepBlue OS for regulated industries
UK-based Narwhal Labs has secured €22.9M and unveiled DeepBlue OS — a platform that automates calls and messaging in regulated sectors with
WebAsk launched an MCP server for surveys and found that AI reads more than it creates
WebAsk gave Claude and Cursor direct access to its survey builder via MCP, but the main use case unexpectedly turned out not to be questionn
Snowflake: AI agents put development into 24/7 mode — CEO on return on investment
Google Antigravity: five useful use cases beyond code — from research to database work
OpenClaw gets a Go reimplementation: one 35 MB binary instead of 800 MB of dependencies
Machine Learning Mastery explained how to avoid race conditions in multi-agent systems
LangChain in production: Habr AI explained why multi-agent systems are moving to plain Python
Habr AI published an analysis of a production multi-agent system without LangChain: the author shows why model switching, RAG, tool calling,
Miro added AI agents to its online whiteboard and taught them to understand team context
Miro added Sidekicks and Flows to its board — AI agents that can see sticky notes, diagrams, and documents on the canvas and help teams turn