Collected sources and patterns will appear here. Add from search or the patterns library.
AgentExecutionPlan -> ApprovedExecutionPlan
Intercept an AI agent's execution flow via an MCP server tool call, pausing execution until a user manually approves or alters the plan via an external UI.
Problem it solves
Autonomous agents execute multi-step plans without giving users a chance to preview, correct, or veto actions.
Consumes
Emits
The real projects this mechanism was found in. Attribution is the point — this is how the best teams actually do it.