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 ↗1828 articles
In the glossary:AI agentAutonomous AgentAgentic WorkflowTool UseMulti-Agent System
NVIDIA explained how to manage autonomous agents in enterprise AI factories
Hardware·NVIDIA Developer Blog

NVIDIA explained how to manage autonomous agents in enterprise AI factories

Jul 1, 2026·2 min
Cursor releases a mobile app to manage an AI agent on the go
Autonomous

Cursor releases a mobile app to manage an AI agent on the go

Jul 1, 2026·2 min
1Password Acquires Apono: Access Control for AI Agents in Corporate Systems
Autonomous

1Password Acquires Apono: Access Control for AI Agents in Corporate Systems

Jul 1, 2026·2 min
LangChain launched dynamic subagents in Deep Agents: orchestration via code
Autonomous

LangChain launched dynamic subagents in Deep Agents: orchestration via code

Jul 1, 2026·3 min
Amazon Bedrock and HealthLake automate health insurance claims processing
Medicine·AWS Machine Learning Blog

Amazon Bedrock and HealthLake automate health insurance claims processing

AWS showed how to combine Bedrock Data Automation and AgentCore to automatically process health insurance claims and convert them into FHIR resources in HealthLake.

Jul 1, 2026·2 min
MIT Technology Review: Why calling AI agents “colleagues” is a mistake
Medicine·MIT Technology Review

MIT Technology Review: Why calling AI agents “colleagues” is a mistake

MIT Technology Review examines a corporate trend: companies give AI tools names like “Alex” and present them as employees — and that shifts people’s expectations in…

Jul 1, 2026·2 min
Yandex compared MCP and CLI+Skill for AI agents: 400 requests and an unexpected failure
Autonomous·Habr AI

Yandex compared MCP and CLI+Skill for AI agents: 400 requests and an unexpected failure

The Yandex team ran a benchmark across 14 scenarios, comparing MCP and CLI+Skill for AI agents with internal APIs — and found that architecture directly affects…

Jul 1, 2026·2 min
Inside an AI agent: seven tools that turn an LLM into an executor
LLM·Habr AI

Inside an AI agent: seven tools that turn an LLM into an executor

Give a language model a terminal, a file system, and internet access, and it becomes an agent — we break down how to add seven tools and teach the model to choose…

Jul 1, 2026·2 min
Top themes
01Voice AI agent lied to customers and mixed up callers — developer found the cause wasn’t in the promptJul 1, 2026·3 min02Alibaba unveiled AI models for robots — China is betting on agentsJul 1, 2026·2 min03Stack Overflow for agents: why AI developers work in complete isolationJul 1, 2026·2 min04AWS launches Neuron Agentic Development to automate AI kernel developmentJul 1, 2026·2 min05AWS showed how to build an AI assistant for equipment repair on Bedrock AgentCoreJul 1, 2026·2 min
Amazon Bedrock AgentCore automates initial intake of insurance claims
Autonomous·AWS Machine Learning Blog

Amazon Bedrock AgentCore automates initial intake of insurance claims

Jul 1, 2026·2 min
Amazon Quick generates incident RCA brief from a single prompt via New Relic and Asana
LLM·AWS Machine Learning Blog

Amazon Quick generates incident RCA brief from a single prompt via New Relic and Asana

Jul 1, 2026·3 min
Amazon Bedrock AgentCore Runtime: isolated microVMs for Claude Code, Codex, and Cursor
LLM·AWS Machine Learning Blog

Amazon Bedrock AgentCore Runtime: isolated microVMs for Claude Code, Codex, and Cursor

Jul 1, 2026·2 min
AWS open-sourced Agent-EvalKit: systematic evaluation of AI agents in six phases
LLM·AWS Machine Learning Blog

AWS open-sourced Agent-EvalKit: systematic evaluation of AI agents in six phases

Jul 1, 2026·2 min
eToro integrated xAI models into Tori agent for real-time market sentiment analysis
LLM·xAI News

eToro integrated xAI models into Tori agent for real-time market sentiment analysis

eToro integrated xAI language models into its AI agent Tori to track market sentiment in real time and incorporate it into users' investment decisions.

Jul 1, 2026·2 min
Google DeepMind launches a $10 million fund to study the collective behavior of AI agents
Autonomous·@GoogleDeepMind

Google DeepMind launches a $10 million fund to study the collective behavior of AI agents

Google DeepMind and its partners have created a $10 million research fund to understand how millions of AI agents interact in groups and what unpredictable…

Jul 1, 2026·2 min
eToro launched Tori AI agent powered by Grok models for market sentiment analysis
Autonomous·@xAI

eToro launched Tori AI agent powered by Grok models for market sentiment analysis

Investment platform eToro launched Tori, an agent powered by xAI's Grok models and the real-time SpaceXAI data feed, to help retail investors understand market sentiment.

Jul 1, 2026·2 min
Gopuff launched Grok-based AI agent Go — it handles voice, photos, and text
Creative·xAI News

Gopuff launched Grok-based AI agent Go — it handles voice, photos, and text

Jul 1, 2026·2 min
Replit launched parallel agents: an app, a video, and a pitch deck at the same time
Creative·@Replit

Replit launched parallel agents: an app, a video, and a pitch deck at the same time

Jul 1, 2026·2 min
Together AI at NVIDIA GTC 2026: Dynamo, multi-agent models, and voice AI
Hardware·Together AI Blog

Together AI at NVIDIA GTC 2026: Dynamo, multi-agent models, and voice AI

Jul 1, 2026·2 min
Replit: describe an idea in words — get a complete app with a database and deployment
Autonomous·@Replit

Replit: describe an idea in words — get a complete app with a database and deployment

Jun 30, 2026·2 min
Together AI beat TensorRT-LLM by 31% in benchmarks for code agents
LLM·Together AI Blog

Together AI beat TensorRT-LLM by 31% in benchmarks for code agents

Jun 30, 2026·2 min
OpenAI launches Codex: the AI agent that writes code instead of engineers
Hardware

OpenAI launches Codex: the AI agent that writes code instead of engineers

Jun 30, 2026·1 min
LangGraph gets fault tolerance: retries, timeouts, and error handlers for production agents
Autonomous

LangGraph gets fault tolerance: retries, timeouts, and error handlers for production agents

Jun 30, 2026·2 min
Alibaba launched Qwen3.7-Plus: multimodal agent with video analysis and autonomous coding
Creative

Alibaba launched Qwen3.7-Plus: multimodal agent with video analysis and autonomous coding

Jun 30, 2026·2 min
GitLab launched a managed DevSecOps platform on Google Cloud with Gemini 3.5 Flash
Creative·GitLab Blog

GitLab launched a managed DevSecOps platform on Google Cloud with Gemini 3.5 Flash

GitLab now runs as a fully managed platform on Google Cloud, with Gemini 3.5 Flash and Gemma 4 built in and full control over the company’s code and data.

Jun 30, 2026·2 min
Claude Fable 5 arrives on GitLab Duo — multi-day agent tasks without manual stops
LLM·GitLab Blog

Claude Fable 5 arrives on GitLab Duo — multi-day agent tasks without manual stops

Anthropic brought a Mythos-class model to GitLab Duo Agent Platform — Fable 5 completes multi-stage tasks on its own, without manual checkpoints or repeated…

Jun 30, 2026·3 min