AI coding

Agent decision-making and stopping rules

• Diff Budgets: Setting Hard Limits on Agent Changes
• Prompt Patterns for Stopping an Agent Mid-Task
• When an Agent Should Stop and Ask a Person
• A Stop Rule That Fires Too Often: Measuring Over-Asking
• Encoding a Refusal: Declining a Task Not to Start
• Instrumenting Agent Halts: Metrics for Stop Rate
• Setting a Time Budget for Each Agent Command
• Splitting Decisions: What an Agent May Settle and What It May Not
• Testing Stop Conditions: Simulating Risky Actions in a Sandbox
• Tuning Diff Budgets: Picking Numbers That Hold Across Task Types
• What a Stop Rule Costs in Tokens and Human Minutes
• When an Agent Should Stop and Ask a Person: A Decision Table
• Who May Raise an Agent's Stop Threshold: Roles and Approval