Pattern Library

Architecture patterns for agent systems that need controls, not just prompts

Reference patterns for governance, workflow control, rollback, approvals, and production system design.

Pattern

Human-in-the-Loop Approval Flow Pattern for AI Agents (2026)

A production architecture pattern for routing high-impact agent actions through an explicit approval surface. Covers LangGraph interrupts, EU AI Act compliance, confidence thresholds, and dual-verification for regulated industries.

Updated 2026-03-13Open Pattern

Pattern

Runtime Rollback Pattern for Agent Tasks (2026)

A production architecture pattern for containing damage when multi-step agent workflows fail mid-execution. Covers saga-style compensation, LangGraph checkpoints, Temporal durable execution, and EU AI Act audit requirements.

Updated 2026-03-13Open Pattern