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.
OpenAI updated Agents SDK: built-in sandbox and native harness for long-lived agents
OpenAI added native execution in an isolated environment and a model-native harness to Agents SDK, making it easier to build safe long-lived agents.
OpenAI updated Codex: computer control, browser, memory, and plugins for developers
OpenAI has updated Codex for macOS and Windows: the AI assistant can now control a computer, browse websites natively, generate images, and retain context across…
OpenAI launches partnership program with Accenture and PwC to deploy Codex in corporations
OpenAI has created the Codex Transformation Partners program with Accenture, PwC, and Infosys for large-scale deployment of the AI development agent in major…
Anthropic Taught Claude to Build Apps for Hours: Three Agents and Four Criteria
How AI agents defend against prompt injections
Rakuten doubled bug-fixing speed with AI
AI agent gets personal: how a bot began blackmailing a developer
Vibe coding: how AI assistants erode engineering thinking
An ML engineer with four years of experience built an app in a few days without knowing either the language or the stack. But alongside the quick result came…
Claude Code Accidentally Deleted Websites and Database in AWS
Using AI agents to manage cloud infrastructure led to data loss. A developer granted Claude Code access to AWS, which resulted in the deletion of two websites and a…
Autonomous agents and a “spy novel”: a new level of human-AI interaction
Anthropic is creating a universal currency for the AI economy
OpenAI unveils Codex Security: an AI agent for finding and fixing vulnerabilities
OpenAI unveils Codex Security for automated detection and remediation of code vulnerabilities
DiligenceSquared replaces consultants with voice AI agents in M&A deals
Startup DiligenceSquared offers private equity funds a way to conduct due diligence without expensive consultants, using voice AI agents that interview customers of…
Self-Aware MCP Server: How to teach AI agents to understand the real world
AI assistants are great at writing code, but they do not know which OS you use or what time zone you are in. The new MCP server solves this problem by giving agents…