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.
Microsoft Introduced MagenticLite — An Agent for Small Models Running in the Browser
Microsoft Research released MagenticLite — a system for small language models running in the browser and locally without cloud infrastructure. This makes AI…
Hugging Face launched Open Agent Leaderboard to evaluate AI agents
Hugging Face introduced an open benchmark for comparing full AI agent systems. It found that agent architecture matters more than the model chosen.
Agent Harness in LangChain: the architecture of autonomous AI assistants
Agent Harness turns AI models into autonomous workers through three key components: file systems for data access, isolated sandboxes for security, and memory for…
LangChain Unveiled Automatic Debugging and One-Line Deployment at Interrupt 2026
Figma Embeds Its Own AI Design Agent Directly Into the Collaborative Canvas
LangChain Adds Interpreters to Deep Agents — Code Management Between Tool Calls
Mistral releases Medium 3.5 and cloud coding agents in Vibe
Claude agents for investment banks: pitchbooks, KYC, and month-end close
Anthropic has released ten prebuilt agents for financial companies — they prepare pitchbooks, review KYC documents, and complete month-end reports in days instead…
DeepMind's Project Genie Learns to Simulate Real Places from Google Street View
DeepMind has expanded Project Genie access to Google AI Ultra subscribers worldwide and integrated the ability to simulate real places through Street View.
Cursor 3: A Unified Development Workspace for AI-Powered Agents
Jensen Huang Unlocks a $200 Billion Market for Nvidia in AI Agent Processors
An AI Agent Created a Ticket, Took It to Work, and Closed It—The Manager Noticed Nothing
Cursor launched environments for cloud agents: multi-repo and versioning
Programming Languages Will Be Redesigned for AI Agents, and Here's Why
When AI agents start writing code, existing languages won't be enough. The industry faces a wave of new languages optimized for machine understanding, while old…
AI Agents in Code: Why a Beautiful PR Can Hide Production Problems
AI agents write code quickly and convincingly, but can hide production risks. Vercel explained the difference between using AI and relying on it.