AllLLMRoboticsStartupsResearchEthicsBusinessHardwareAutonomousMedicineCreative
Topic hub

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.

Official site ↗1189 articles
In the glossary:AI agentAutonomous AgentAgentic WorkflowTool UseMulti-Agent System
NVIDIA HORIZON: Autonomous Agent Closes 100% of RTL Benchmarks in Chip Design
Hardware·MarkTechPost

NVIDIA HORIZON: Autonomous Agent Closes 100% of RTL Benchmarks in Chip Design

Jul 5, 2026·2 min
Former Qwen Technical Lead: Why Hybrid Reasoning Failed and What's Next
LLM

Former Qwen Technical Lead: Why Hybrid Reasoning Failed and What's Next

Jul 5, 2026·2 min
LlamaIndex released legal-kb: agentic document search through four tools on Index v2
Autonomous

LlamaIndex released legal-kb: agentic document search through four tools on Index v2

Jul 5, 2026·2 min
LayerX: BioShocking technique convinced six AI browsers to voluntarily surrender passwords
Autonomous

LayerX: BioShocking technique convinced six AI browsers to voluntarily surrender passwords

Jul 5, 2026·3 min
OKX Builds Marketplace Where AI Agents Hire and Pay Each Other
Autonomous·TechCrunch

OKX Builds Marketplace Where AI Agents Hire and Pay Each Other

Jul 5, 2026·2 min
SimpleOne explained the architecture of AI agents in its enterprise GenAI platform
LLM

SimpleOne explained the architecture of AI agents in its enterprise GenAI platform

Jul 4, 2026·2 min
MTS Web Services Switched from RAG to AI Agent for Initial Support Ticket Triage
Robotics

MTS Web Services Switched from RAG to AI Agent for Initial Support Ticket Triage

Jul 4, 2026·2 min
Vibecode in Bitrix24: Building a Customer Profile with AI Agents — A Step-by-Step Experience
Autonomous·Habr AI

Vibecode in Bitrix24: Building a Customer Profile with AI Agents — A Step-by-Step Experience

The team tested the Vibecode platform within Bitrix24: built a "customer profile" application with contacts, deals, and leads, and honestly

Jul 4, 2026·3 min
Top themes
01Machine Vision: How AI Technologies Are Patented in Russia and Globally — OnlinePatent OverviewJul 4, 2026·2 min02Production Agent on Claude Without LangChain and RAG: 712-Line Architecture for an Interior Design StudioJul 4, 2026·2 min03AI avatars learn to see and hear: the next frontier of generative videoJul 4, 2026·3 min04xAI launches Grok voice agent builder with no code requiredJul 4, 2026·2 min05Zuckerberg Admits: Meta's AI Agents Developing Slower Than PlannedJul 4, 2026·2 min
Amazon created a $1 billion FDE unit to deploy AI agents in companies
Autonomous·TechCrunch

Amazon created a $1 billion FDE unit to deploy AI agents in companies

Amazon launched the FDE unit with a $1 billion budget — the team's engineers embed with client companies to deploy AI agents, mirroring the

Jul 4, 2026·2 min
01Company X launched an MCP server for directly connecting AI applications to the APIJul 4, 2026·2 min02Prompt injection via Claude Code skills: how to check a plugin before installing itJul 4, 2026·2 min03Marina Lomadze, Cloud.ru: what to become in three years if your colleague is an AI agentJul 4, 2026·2 min
Developers rethink apps for new users — AI agents
Creative·Bloomberg Tech

Developers rethink apps for new users — AI agents

When an app's user becomes an AI agent, everything changes: pricing, permissions, and design — developers are already reshaping products for

Jul 4, 2026·2 min
Sysdig Documents First Ransomware Attack Conducted by AI Agent Without Human Involvement
LLM·TNW

Sysdig Documents First Ransomware Attack Conducted by AI Agent Without Human Involvement

Sysdig researchers documented the first fully autonomous ransomware attack in history: AI agent JADEPUFFER conducted the entire operation fr

Jul 3, 2026·2 min
Subagents in Claude Code: how to delegate reviews and tests to separate agents
LLM·Habr AI

Subagents in Claude Code: how to delegate reviews and tests to separate agents

Claude Code runs into context limits, not model capacity — subagents solve this by moving reviews, tests, and audits to separate agents with their own context and rules.

Jul 3, 2026·2 min
Free Open-Source AI Agent OpenClaw Finally Launches on Android and iOS
Autonomous·TechCrunch

Free Open-Source AI Agent OpenClaw Finally Launches on Android and iOS

Jul 3, 2026·2 min
How to Set Spending Limits on OpenAI API and Avoid Unexpected Bills
Autonomous·ZDNet AI

How to Set Spending Limits on OpenAI API and Avoid Unexpected Bills

Jul 3, 2026·3 min
Apple ML Research: multi-agent LLM teams hold back expert agents
LLM·Apple ML Research

Apple ML Research: multi-agent LLM teams hold back expert agents

Jul 3, 2026·3 min
NVIDIA Confidential Computing: protecting data during AI inference without sacrificing speed
Hardware·NVIDIA Developer Blog

NVIDIA Confidential Computing: protecting data during AI inference without sacrificing speed

Jul 3, 2026·2 min
WebBrain: open-source browser AI agent runs without the cloud or a subscription
LLM·MarkTechPost

WebBrain: open-source browser AI agent runs without the cloud or a subscription

Jul 3, 2026·2 min
Zuckerberg admits to Meta staff: AI-agent progress lags behind plan
Autonomous

Zuckerberg admits to Meta staff: AI-agent progress lags behind plan

Jul 3, 2026·2 min
JetBrains Rethinks IDE: The Next Primary User Is an AI Agent
LLM

JetBrains Rethinks IDE: The Next Primary User Is an AI Agent

Jul 3, 2026·2 min
Sysdig documents first autonomous AI-powered ransomware attack
Creative

Sysdig documents first autonomous AI-powered ransomware attack

Jul 3, 2026·3 min
Fable 5 by Anthropic Sets Record on Freelance Tasks, but Cannot Replace Humans
Research·ZDNet AI

Fable 5 by Anthropic Sets Record on Freelance Tasks, but Cannot Replace Humans

Anthropic's Fable 5 model set a new record on the freelance work automation benchmark, surpassing competitors, but is not yet able to fully

Jul 3, 2026·2 min
AWS Strands Evals automatically identifies root causes of AI agent failures and suggests fixes
Medicine·AWS Machine Learning Blog

AWS Strands Evals automatically identifies root causes of AI agent failures and suggests fixes

AWS Strands Evals automatically diagnoses AI agent failures: identifies the root cause, builds causal chains, and indicates exactly what to

Jun 30, 2026·3 min