Patterns
Implementation control library
Find the implementation control behind the gap.
138 implementation controls mapped to architecture, obligations and evidence. Search the problem; open implementation depth only when you need it.
Agent Checkpoint and Recovery
The Agent Checkpoint and Recovery Pattern defines the durable execution architecture that enables AI agents running lo…
EAAPL-AGT010 — AI Agent Cost Governance Architecture
Agentic AI systems that autonomously execute multi-step workflows—calling tools, querying APIs, writing and executing…
Agent Identity and Authorisation
The Agent Identity and Authorisation Pattern defines the security architecture governing who an AI agent is, what it i…
Agent Sandboxing
The Agent Sandboxing Pattern defines the secure execution environment that isolates AI agent tool executions from the…
Agent Tool Registry
The Agent Tool Registry Pattern defines the centralised catalogue and invocation framework through which AI agents dis…
Event-Driven Agent
The Event-Driven Agent Pattern defines the architecture for AI agents that are triggered by external events — system a…
Long-Running Agent
The Long-Running Agent Pattern defines the architecture for AI agents that execute tasks over hours or days — due dili…
Reflexive Agent
The Reflexive Agent Pattern defines an architecture in which an AI agent evaluates the quality of its own outputs thro…
Single Agent Pattern
The Single Agent Pattern defines the canonical architecture for a single autonomous AI agent capable of perceiving its…
Stateful Agent Memory
The Stateful Agent Memory Pattern defines the multi-tier memory architecture that allows AI agents to retain, recall,…
CodeAct Agent
The CodeAct Agent Pattern defines an architecture in which an agent's primary action mechanism is writing and executin…
Conditional Routing
The Conditional Routing Pattern defines control flow structures for agentic workflows: if/else branching based on LLM…