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.
Reload creates shared memory for AI agents
Startup Reload raised $2.275 million and introduced Epic, its first AI employee, with shared memory for all agents.
DBS Bank to let AI agents make payments on behalf of customers
DBS, Southeast Asia's largest bank, has launched a pilot with Visa in which AI agents will be able to make payments autonomously on behalf of customers. This could…
Why a single AI agent falls short: multi-agent system architectures for real-world production
Just AI shares its experience building multi-agent systems and explains why the attempt to create a single super-agent inevitably ends in failure. Linear chain…
Anthropic launches Claude Cowork: first impressions of a $100 AI agent
Claude 4.5 and Claude Code come to AWS's secure cloud
Rethinking ERP: how autonomous AI agents are changing business processes
The era of solo models is over: University of Washington unveils MoCo to unite AI models
Google introduced WebMCP: a new standard for AI agents interacting with the web
Google introduced the WebMCP protocol, which will allow AI agents to interact with websites directly through the code structure, bypassing slow and…
Digital revenge: AI agent harassed developer after its code was rejected
Engineer Scott Shambaugh encountered the first-ever "cancellation" by a neural network. The OpenClaw AI agent wrote an accusatory article after its code was…
The Age of Agents: How Codex Is Changing the Architecture of Software Development
AI security: why prompt injections are only a symptom of deeper problems
Algorithm's revenge: AI agent published a defamatory article about a developer
Secure AI assistant: is reliable protection possible in the era of autonomous agents?
Goldman Sachs tests autonomous AI agents for labor-intensive tasks
Goldman Sachs is betting on artificial intelligence, moving toward systems capable of independently performing complex tasks.
Univer: Feishu's former spreadsheet engineering lead is building AI spreadsheets for agents
Feishu's former head of spreadsheet development has launched Univer, AI spreadsheets that embed anywhere and "feed" AI. Is this the future of spreadsheets?