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.
Olostep: automatic documentation crawler for preparing data for AI
Olostep allows crawling entire documentation websites with a few lines of code — the tool collects pages, removes unnecessary elements, and
AWS Releases ToolSimulator for Safe Testing of AI Agents in Strands Evals
AWS has opened access to ToolSimulator — an LLM framework within the Strands Evals SDK for large-scale testing of AI agents without real API
Siemens launches AI agent for autonomous engineering design
OpenAI brings in Cognizant and CGI to bring Codex to the enterprise market
Hugging Face: open-source AI gives defenders the same capabilities as attackers
OpenAI launched Chronicle in Codex — a Windows Recall equivalent for developers
Perplexity Personal Computer turns an old Mac into a local AI agent 24/7
Perplexity has launched Personal Computer, a tool that turns a spare Mac into a personal AI assistant with full access to files and control
Gumloop raises $50M from Benchmark so every employee can build AI agents
Venture capital firm Benchmark invested $50 million in Gumloop, a no-code platform for building AI agents that any employee can use.