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.
Agentic Development vs. Vibe Coding: How Avito Keeps AI-Written Code Under Quality Control
Andrey Brovko, head of testing at Avito Auto, explains how agentic development differs from vibe coding and which practices keep the quality of AI-agent-written…
How an AI Agent Is Built: The Wrapper Layers Around an LLM and Where to Look for the Source of a Bug
A developer with ML experience breaks down the internals of AI agents: an LLM always sits at the center, wrapped in layers where most failures hide during debugging.
Cognition Acquires the Team Behind Poke: 100 Million Messages in Three Months
Cognition, maker of the AI engineer Devin, says The Interaction Company, creator of the personal agent Poke, is joining it. Users exchanged more than 100M messages…
Thales Group Report: One in Three Companies Already Uses AI Agents, and Security Risks Are Growing
Koda Desktop: Desktop App With an AI Coding Agent Launches in Beta
OpenAI Presence: An Enterprise Platform for Voice and Chat Agents
Jack Dorsey Launches Buzz, a Slack Rival Where AI Agents Work in Chat Alongside Humans
Wired: New Malware Worm Targets AI Infrastructure, Steals Logins and Destroys Victims' Files
Wired describes a new type of malware that infiltrates AI coding systems, steals data and credentials, and on the attacker's command destroys files and locks…
OpenAI's GPT-Red: Automated Red Teaming Through Self-Play Against Prompt Injection
OpenAI unveils GPT-Red, an automated red-teaming system in which a model attacks itself through self-play to improve safety, alignment and resistance to prompt…
Hamidun News AI Agenda Index: First Half of 2026
Sysdig Describes First Fully Autonomous Ransomware AI Agent Attack Without Human Involvement
Microsoft Research Presented Flint — a Data Visualization Language for AI Agents
GitHub Copilot Learned to Connect a Domain to GitHub Pages Without Manual DNS Setup
AI Agency: How Autonomous Agents Differ From Regular Programs or Scripts
Understanding what agency in AI means and why autonomous agents capable of solving tasks independently fundamentally differ from deterministic scripts.
Habr: agent memory removes technical noise from hybrid development team chats
Habr author showed how a team transfers requirements, solutions, and defects from human chats to a separate layer of agent memory for collaboration between humans…