- World extends AgentKit to AI agents verified with World ID.
- AI agents can act online on behalf of verified human users.
- The system aims to prevent bots while enabling reliable automation.
The world is expanding in reach AgentKitits framework is designed to create human-verified AI agents and allow individuals to connect these agents to a verified person World ID.
The system enables AI agents to act on behalf of users online while maintaining identity verification through the world’s network.
This development comes at a time when artificial intelligence agents are increasingly capable of performing online tasks such as shopping, making reservations, browsing websites and interacting with digital services.
This growing ability has created a challenge for companies in distinguishing between agents representing real users and automated botnets.
AgentKit is positioned as a response to this problem by connecting AI agents directly to World ID, allowing websites and apps to verify when an agent is acting on behalf of a unique human.
The framework is designed to support task delegation while maintaining safeguards associated with identity verification and user monitoring.
How AgentKit connects AI agents to verified identity
To get started using AgentKit, individuals need a verified World ID, access to the World App, and an AI-powered agent, including tools like Claude Code, Codex, Cursor, Hermes, or OpenClaw.
Users connect their human proof through World’s ToolRouter’s interface, generate an API key, and connect their AI agent within minutes.
Once connected, the agent can interact with AgentKit-enabled services and perform tasks on the user’s behalf.
The system is designed to allow individuals to delegate digital tasks to AI agents while maintaining controls associated with verified identity.
According to the framework’s description, this structure aims to ensure that AI activity remains attributable to a real human user rather than anonymous or automated systems.
The demo shows the real-world use case
This technology was recently demonstrated with a limited edition of 500 “Human in the Loop” hats available exclusively to certified Global ID card holders.
During the demo, AI agents detected dropouts, checked eligibility, navigated the storefront, and completed purchases on behalf of users while keeping limits of one item per person tied to verified identities.
All 500 hats have been claimed by verified individuals in multiple countries, including the United States, Germany, Japan, and the United Kingdom.
The demonstration was used to show how AI agents can execute real-world transactions while maintaining identity-based restrictions designed to limit abuse.
The example highlights how companies can allow AI agents to complete tasks on behalf of users while still preventing exploitation by botnets.
Building a trust layer for the agent economy
As more services integrate with AgentKit, World aims to create what he describes as a trust layer for the emerging agent economy.
The goal is to enable AI agents to transact and interact online while remaining accountable to the humans they represent.
The system aims to support a growing range of use cases where AI agents operate autonomously but within the framework of verified identity and user authorization.
This includes both business applications and broader digital services interactions.
Originally conceived by Sam Altman, Max Novendstern, and Alex Plania, the global project aims to provide proof of humanity, finance, and communication for every human in the age of artificial intelligence.
The company says AgentKit is part of its broader effort to support identity verification in an environment where AI agents are increasingly able to act autonomously across online platforms.
