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.
Why memory has become a key element of AI agents: a breakdown across three levels of complexity
A new breakdown of memory in AI agents shows the main point: without preserving context, a model responds in isolation, while useful agent systems are built on…
Meta introduced Autodata — an agentic system for creating high-quality training data
Meta introduced Autodata — a framework in which LLM agents collect, verify, and improve training data themselves so that more capable models learn from more complex…
Microsoft made the Copilot agent in Word, Excel and PowerPoint available to all Microsoft 365 subscribers
Microsoft has opened access to Copilot for all Microsoft 365 subscribers: the AI agent in Word, Excel and PowerPoint can now perform multi-step actions under user…
AI startups in 2026 shift from a single prompt to multi-agent pipelines
Elon Musk revealed how the Macrohard project will unite xAI and Tesla to create software
Perplexity unveiled Personal Computer — an AI agent for Mac mini and teams
Habr AI showed how to prepare structured input for an AI agent instead of a raw technical spec
Meta and OpenAI overpay for Moltbook and OpenClaw amid the agentic AI wave
ZDNet argues that Meta's Moltbook deal and OpenAI's hiring of OpenClaw's creator are a bet on hype: the products generate buzz, but are immature, insecure and no…
OpenAI explained how Codex is changing development in a world where code is increasingly written by agents
OpenAI described an experiment in which an internal product was built almost entirely through Codex: people defined rules, checked invariants, and gradually…
Zendesk acquires Forethought to strengthen AI agents for customer service
Claude Code and Codex compared on a real-world task: Claude is stronger in RAG, Codex saves tokens
Veai 5.6 for JetBrains IDEs adds commit message generation and manual Skills launch
DEMIURGOS adds a rules debugging mode for AI agents and support for 20+ tools
Anthropic explained how businesses can implement agentic systems without unnecessary complexity
Anthropic showed that businesses are better off starting not with autonomous agentic systems, but with simple scenarios: they are cheaper, more reliable, and often…
In five days, Yoyo grew from 200 lines into an autonomous agent that writes code on its own
An experiment with the Yoyo agent showed that 200 lines of Rust were enough to start a self-acceleration loop: the bot reads its own code, writes fixes, files…