AI agents

Escalation, handoff, and work routing

• A Reason Code Taxonomy for Agent Escalations
• Confidence From Span Scores: Citing Versus Escalating
• Feeding a Stopped Review Back Into the Eval Set
• What a Support Agent Should Say When It Does Not Know
• A Conflict Taxonomy for Precedence: Escalate, Merge or Drop
• A Cost Table for a Second Model Call Versus a Human
• A Second-Hop Queue: When the First Owner Does Not Answer
• Confidence Scores as Review Triggers: Calibrating the Threshold
• Decision Log for Reviewers: What to Record When a Gate Is Waived
• Designing an Escalation Policy for Agent Failures
• Escalation and Handoff When a Human Approves a Partial Action
• Escalation Volume and Reviewer Capacity: A Planning Model
• Logging Escalations by Reason Code: Fields and a Dashboard
• Logging the Escalation: Fields That Prove Why a Human Got It
• Measuring Handoff Quality: Time to First Human Reply
• Paging a Human When an Agent Stalls
• Pricing Escalation Volume Against a Tighter Cap
• When a Refusal Should Escalate: Mapping Reason Codes to Queues
• When a Reviewer Says Restore and the Index Says No
• When Agent and Reviewer Disagree: A Decision Log and Tie-Break
• When the Approver Says Restore and the Index Says No
• When the Gate Refuses: Escalation Queues by Reason Code