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.
Mistral renames Le Chat to Vibe — a unified agent for work and coding
Mistral has launched Vibe, a unified agent with Work and Code modes. Le Chat has been officially renamed, with all accounts and conversation
Mistral AI introduced an industrial AI stack and the Vibe agent at the AI Now Summit
At the AI Now Summit, Mistral announced partnerships with Airbus, BMW and ASML, turned Vibe into a full-fledged work agent, and announced pl
Which AI subscriptions for developers offer the best value for money in 2026
Anthropic gave opposite advice for Fable 5 and Opus 4.8: what to change in prompts
How to build team knowledge and judgment into the AI agent improvement loop — LangChain
Arcade.dev raises $60M to tackle the problem of unchecked AI agent permissions
AI tokens are driving up corporate cloud bills — ZDNet flags the trend
Large companies' spending on AI tokens is growing uncontrollably, echoing the chaos of early cloud pricing — only this time it's even harder
A Roadmap for Evaluating AI Agents: Metrics, Benchmarks, and Practical Methods
Evaluating AI agents is harder than evaluating language models: it requires separate metrics for multi-step tasks, tool use, and error recov