https://whitewater.ai/jimmy-explains/permission-is-not-proof/ https://whitewater.ai/videos/permission-is-not-proof.jpg Permission Is Not Proof: Why AI Agent Credentials Are Not Enough An agent can have valid credentials and spending authority while relying on stale evidence. Jimmy explains why permission, decision integrity and a verifiable result need separate checks. https://whitewater.ai/videos/permission-is-not-proof.mp4 62 2026-10-26T22:12:01-05:00 https://whitewater.ai/jimmy-explains/claude-duet-approval-and-receipts/ https://whitewater.ai/videos/claude-duet-approval-and-receipts.jpg Claude Duet: Approval Checks Before an AI Agent Sends Changed attachments, changed recipients, revoked permission and uncertain sends: four proposed checks for keeping the decision visible and bringing back the receipt. https://whitewater.ai/videos/claude-duet.mp4 103 2026-10-26T21:56:11-05:00 https://whitewater.ai/jimmy-explains/six-questions-before-ai-agent-sends/ https://whitewater.ai/videos/six-questions-before-ai-agent-sends.jpg Before Your AI Agent Hits Send: Six Governance Questions Walk through a customer-pricing example: define the task, evidence, permissions, human stopping point and action history before an agent sends. https://whitewater.ai/videos/before-send.mp4 113 2026-10-26T05:41:00-05:00