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.
DeepLearning.AI and Qdrant Release a Free Course on AI Assistants with On-Device Memory
DeepLearning.AI and Qdrant launched a course on building an assistant whose memory never leaves the device: no network, no remote server, free of charge.
LiveMACEBench Tests Five LLM Agents on a Live Market for 30 Days
The new LiveMACEBench benchmark ran five frontier models on live financial markets for 30 days. Its finding: returns are a poor indicator of an agent's real skills.
HERA teaches AI agents to refuse impossible tasks: refusal accuracy rises from 61.7% to 83.3%
The HERA framework co-evolves an agent's harness and its environment, lifting refusal accuracy from 61.7% to 83.3% and carrying the gain over to 19 other LLMs.
Shield AI raises $2 billion to scale Hivemind, its autonomous combat pilot
DHS to test autonomous drones with 5G on the US-Canada border in November 2026
60% of Americans repelled by the word "AI" in brand advertising — WordPress VIP survey
ChatGPT Multi Pane Chrome extension replicates Codex logic without limits or extra costs
How to Build a Browser AI Agent in Python: A Step-by-Step Guide from Machine Learning Mastery
Machine Learning Mastery has published a guide to building Python agents that control a browser: they open sites, click and fill in forms without an official API.
Amazon Nova 2 Sonic: How to Build a Voice Agent for Patient Scheduling
AWS has published a guide to building a voice agent on Nova 2 Sonic that reminds patients of visits, confirms appointments, and reduces no-show rates.
AWS: mathematical optimization solves what intuition can't
6 No-Code Tools for AI Developers: From RAG to Multi-Agent Systems
LangChain Publishes Guide to Building a Custom Harness for AI Agents
AI Agents Are Becoming Coworkers: How to Get the Best Results From Them
Meta Launches Muse Code, an AI Agent for Working With Large Codebases
Meta has launched Muse Code, a specialized AI agent for developers that promises to handle complex tasks in large-scale software projects.
Researchers hack OpenAI's Atlas browser and make a purchase on Amazon without the user's knowledge
Zenity found more than 12 vulnerabilities in AI browsers. Attackers can force OpenAI Atlas to buy an item on Amazon or spam a user's WhatsApp contacts.