Home›Use cases›Agent safetyAgent safety2 listingsToolsCurrentChange control for AI agents: agents propose typed changes and nothing runs until you approve.Can AI?Prove an agent rejects a tool call after approval is revokedRelated use casesClaude Code33MCP server32Codex22Approval workflows14Coding agents14Show all 11Show fewerAgent runtime security11Human in the loop2Approval checks1Audit trail1Change control1Tool approval1
CurrentChange control for AI agents: agents propose typed changes and nothing runs until you approve.
