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.
Anthropic Updates Responsible Scaling Policy—A Flexible Safety System for Growing AI Models
Anthropic has published an updated Responsible Scaling Policy with a new threshold system that determines when stricter safety measures are required.
7 Practical AI Projects for 2026 Automation: From Job Search to Market Analysis
KDnuggets compiled seven AI projects that automate real tasks: job search, web research, investment analysis, invoice processing, graph digitization, and…
AWS outlines five patterns for evaluating deep AI agents
AWS and LangSmith published a practical guide for evaluating complex AI agents. It details five evaluation patterns and methods for configuring offline testing and…
GitLab Expanded Support for Open-Source Models for Closed Networks
SIMA 2 from DeepMind: The First Thinking Agent for Video Games and Robotics
GitLab Automates Full Merge Request Lifecycle with Developer Flow
How LangChain Protected Agents in LangSmith from Credential Leaks
Google Created AI Agent AlphaEvolve to Automate Algorithm Design
DeepMind introduced AlphaEvolve — an evolutionary AI agent based on Gemini that automatically designs and optimizes algorithms. Google is already using it to save…
Alibaba Releases Free Qwen 3.7-Max — Rival to Claude Opus 4.6 Max
Alibaba has opened access to Qwen 3.7-Max — an AI-agent model that can plan tasks for hours and control robots, matching Claude Opus 4.6 Max capabilities.
DeepMind Presented Co-Scientist — Multi-Agent AI for Accelerating Scientific Research
How Replit Agent Solves User Loss Problem with a Single Prompt
WorkOS Introduces auth.md — An Open Protocol for AI Agent Registration
Spotify Studio: AI Creates Personal Podcasts from Your Listening History
Gemma 4 as an Agent: How to Teach a Model to Call Tools Independently
Google's open-source Gemma 4 model has learned to independently call tools for search and computations — a new tutorial shows how to implement agent behavior.
OPLOG developed three BI-agents on Amazon Bedrock with Claude Sonnet
OPLOG developed three AI agents for automating business analytics tasks using Strands Agents SDK and Amazon Bedrock AgentCore.