Research: AI agents
MCP authorization: who can access an agent's tools
A closer look at access tokens, operation permissions and user consent in MCP connections.
Agentic Workflows: Where They Earn Their Keep
An agent earns its place when the task needs decisions that a fixed sequence cannot sensibly anticipate.
What Happens When Every App Has an Agent
When software can act, the useful questions concern authority, evidence and recovery.
1Password Gives Claude a Login Without the Password
A new integration separates permission to use a credential from exposing the secret to an assistant.
BNB's Agent SDK Puts Payment Rules Beside Identity
The mainnet SDK combines optional identity, escrow, payment and memory modules for applications using agents.