Human-in-the-Loop (HITL) Patterns

Overview

The "Human-in-the-Loop" (HITL) skill provides a standardized framework for integrating human oversight into agentic workflows. By tiering actions based on risk, we ensure autonomy is utilized safely for low-impact tasks while maintaining rigorous human control over high-impact operations. This skill aligns with the C4 Runtime Protocol to prevent "black box" agent behavior.

When To Use

• Before performing destructive file operations (e.g., rm -rf, bulk overwrites).
• Before triggering deployment pipelines or infrastructure changes.
• Before making financial or security-impacting decisions.
• When an agent's confidence in a plan or outcome is below a critical threshold.
• When the user requires explicit auditability of agent intent.

Risk-Tiered Action Matrix

To manage friction, apply the appropriate gate based on the action category: