Anthropic is testing an AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → that initiates contact and works in the background, pausing for approval before it sends, pays or signs. This shows the interaction and consent pattern it is trying out for long-running assistants.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
