EAAPLEnterprise AI Architecture Pattern Library

Pattern Library

AI Governance Pattern Library

138 patterns across 16 domains. Filter by regulatory framework to find the control that satisfies a specific obligation.

138 patterns
Agentic AIProven

Agent Checkpoint and Recovery

The Agent Checkpoint and Recovery Pattern defines the durable execution architecture that…

EU AI ActNIST AI RMF
Agentic AIProven

EAAPL-AGT010 — AI Agent Cost Governance Architecture

Agentic AI systems that autonomously execute multi-step workflows—calling tools, querying APIs, writing…

Agentic AIProven

Agent Identity and Authorisation

The Agent Identity and Authorisation Pattern defines the security architecture governing who…

EU AI ActNIST AI RMF
Agentic AIProven

Agent Sandboxing

The Agent Sandboxing Pattern defines the secure execution environment that isolates AI…

EU AI ActNIST AI RMF
Agentic AIProven

Agent Tool Registry

The Agent Tool Registry Pattern defines the centralised catalogue and invocation framework…

EU AI ActISO/IEC 42001+1
Agentic AIProven

Event-Driven Agent

The Event-Driven Agent Pattern defines the architecture for AI agents that are…

EU AI ActISO/IEC 42001+1
Agentic AIProven

Long-Running Agent

The Long-Running Agent Pattern defines the architecture for AI agents that execute…

EU AI ActNIST AI RMF
Agentic AIProven

Reflexive Agent

The Reflexive Agent Pattern defines an architecture in which an AI agent…

EU AI ActISO/IEC 42001+1
Agentic AIProven

Single Agent Pattern

The Single Agent Pattern defines the canonical architecture for a single autonomous…

APRA CPS234EU AI Act+2
Agentic AIProven

Stateful Agent Memory

The Stateful Agent Memory Pattern defines the multi-tier memory architecture that allows…

EU AI ActISO/IEC 42001+2
Agentic WorkflowsEmerging

CodeAct Agent

The CodeAct Agent Pattern defines an architecture in which an agent's primary…

EU AI ActISO/IEC 42001
Agentic WorkflowsIndustry Standard

Conditional Routing

The Conditional Routing Pattern defines control flow structures for agentic workflows: if/else…

EU AI ActISO/IEC 42001
Agentic WorkflowsEmerging

Context Compression

The Context Compression Pattern defines techniques for managing an agent's context window…

ISO/IEC 42001
Agentic WorkflowsEmerging

Dynamic Sub-agent Spawning

The Dynamic Sub-agent Spawning Pattern defines an architecture in which a parent…

EU AI ActISO/IEC 42001+1
Agentic WorkflowsProven

Iterative Constraint Satisfaction

The Iterative Constraint Satisfaction Pattern defines an architecture in which an agent…

EU AI ActISO/IEC 42001
Agentic WorkflowsEmerging

Mixture of Agents

The Mixture of Agents (MoA) Pattern defines an architecture in which multiple…

EU AI ActISO/IEC 42001+1
Agentic WorkflowsProven

Parallel Fan-Out / Fan-In

The Parallel Fan-Out / Fan-In Pattern defines an architecture in which a…

ISO/IEC 42001NIST AI RMF
Agentic WorkflowsProven

Plan-and-Execute

The Plan-and-Execute Pattern defines a two-phase agentic architecture: a dedicated Planner decomposes…

ISO/IEC 42001NIST AI RMF
Agentic WorkflowsProven

ReAct Agent Loop

The ReAct (Reason + Act + Observe) Agent Loop Pattern defines an…

EU AI ActISO/IEC 42001+1
Agentic WorkflowsMature

Router / Dispatcher

The Router / Dispatcher Pattern defines a central classifier that receives all…

EU AI ActISO/IEC 42001
Agentic WorkflowsIndustry Standard

Sequential LLM Chain

The Sequential LLM Chain Pattern defines a deterministic multi-step pipeline in which…

ISO/IEC 42001
Agentic WorkflowsProven

Streaming Progressive Output

The Streaming Progressive Output Pattern defines how agentic workflows deliver partial, incremental…

EU AI ActISO/IEC 42001
Agentic WorkflowsIndustry Standard

Tool Call Orchestration

The Tool Call Orchestration Pattern defines the execution mechanics for structured tool…

EU AI ActISO/IEC 42001
Agentic WorkflowsProven

Workflow State Machine

The Workflow State Machine Pattern defines an explicit finite-state machine (FSM) that…

EU AI ActISO/IEC 42001
Agentic WorkflowsEmerging

Workflow Tracing and Replay

The Workflow Tracing and Replay Pattern defines the instrumentation, storage, and replay…

EU AI ActISO/IEC 42001
Regulatory ComplianceProven

APRA CPS230 AI Compliance

APRA Prudential Standard CPS230 Operational Risk Management (effective 1 July 2025) imposes…

APRA CPS230
Regulatory ComplianceProven

EAAPL-CMP002 — APRA CPS234 AI Security Architecture

Australian Prudential Regulation Authority (APRA) Prudential Standard CPS234 Information Security applies in…

Regulatory ComplianceProven

EAAPL-CMP007 — Data Residency for AI Architecture

AI systems introduce new vectors for cross-border data transfer that existing data…

Regulatory ComplianceProven

EAAPL-CMP003 — EU AI Act Compliance Architecture

The EU Artificial Intelligence Act (Regulation (EU) 2024/1689) establishes legally binding obligations…

Regulatory ComplianceProven

EAAPL-CMP008 — GDPR-Compliant AI Architecture

The General Data Protection Regulation (Regulation (EU) 2016/679) applies in full to…

Regulatory ComplianceProven

EAAPL-CMP005 — ISO/IEC 42001 AI Management System Implementation

ISO/IEC 42001:2023 is the first international standard providing requirements for an Artificial…

Regulatory ComplianceProven

EAAPL-CMP006 — NIST AI Risk Management Framework Implementation

The NIST AI Risk Management Framework 1.0 (NIST AI RMF, published January…

Regulatory ComplianceProven

EAAPL-CMP004 — Privacy-Preserving AI Architecture

AI systems that ingest, process, or generate personal information must comply with…

Data ArchitectureProven

AI Data Mesh Integration

Enterprises adopting Data Mesh architectures face a structural challenge when integrating AI:…

EU AI ActISO/IEC 42001+1
Data ArchitectureProven

AI Training Data Governance

AI training data governance is the foundation of responsible AI.

EU AI ActISO/IEC 42001+2
Data ArchitectureProven

Data Lineage for AI

Regulators, auditors, and risk committees increasingly demand that organisations explain not just…

EU AI ActISO/IEC 42001+2
Data ArchitectureProven

Data Quality for AI

AI systems are uniquely sensitive to data quality failures in ways that…

EU AI ActISO/IEC 42001+1
Data ArchitectureProven

Federated Learning Pattern

Federated learning enables multiple organisations or devices to collaboratively train a shared…

EU AI ActISO/IEC 42001+2
Data ArchitectureProven

Privacy by Design for AI Data

Privacy-by-design mandates that privacy controls are embedded into AI data pipelines at…

EU AI ActISO/IEC 42001+3
Data ArchitectureProven

Real-Time Feature Engineering

AI models that make real-time decisions — fraud detection, personalised recommendations, credit…

EU AI ActISO/IEC 42001
Data ArchitectureProven

Synthetic Data Generation

Many of the most valuable enterprise AI use cases — fraud detection,…

EU AI ActISO/IEC 42001+2
AI GovernanceProven

AI Approval Workflow

The AI Approval Workflow establishes a multi-stage, evidence-gated approval process that every…

APRA CPS230EU AI Act+2
AI GovernanceProven

AI Audit Trail

The AI Audit Trail pattern establishes an immutable, tamper-evident log of every…

APRA CPS230APRA CPS234+4
AI GovernanceProven

AI Ethics Review Board

The AI Ethics Review Board (AERB) is a standing organisational governance structure…

EU AI ActISO/IEC 42001+1
AI GovernanceProven

AI Incident Management

The AI Incident Management pattern implements a specialised incident management lifecycle for…

APRA CPS230APRA CPS234+3
AI GovernanceProven

AI Model Register

The AI Model Register is the foundational governance artefact for any enterprise…

APRA CPS230EU AI Act+2
AI GovernanceProven

AI Policy Enforcement

The AI Policy Enforcement pattern implements runtime governance controls that ensure AI…

APRA CPS234EU AI Act+2
AI GovernanceProven

AI Regulatory Compliance Gateway

The AI Regulatory Compliance Gateway is a centralised, runtime compliance validation layer…

APRA CPS230EU AI Act+1
AI GovernanceProven

AI Risk Assessment Framework

The AI Risk Assessment Framework provides a systematic, repeatable methodology for evaluating…

APRA CPS230EU AI Act+2
AI GovernanceProven

Model Bias Detection

The Model Bias Detection pattern implements a continuous pipeline for detecting, measuring,…

APRA CPS230EU AI Act+1
AI GovernanceProven

Responsible AI Framework

The Responsible AI Framework operationalises the five core responsible AI principles—fairness, transparency,…

APRA CPS230EU AI Act+2
Human-in-the-LoopProven

Active Learning Loop

The Active Learning Loop pattern establishes a structured, closed-loop process by which…

Human-in-the-LoopProven

AI Confidence Threshold Routing

The AI Confidence Threshold Routing pattern dynamically routes inference requests to different…

Human-in-the-LoopProven

Annotation and Feedback Loop

The Annotation and Feedback Loop pattern defines the end-to-end architecture for collecting…

Human-in-the-LoopProven

Collaborative AI Decision

The Collaborative AI Decision pattern defines an architecture in which humans and…

Human-in-the-LoopProven

Human Approval Gateway

High-stakes AI systems — those authorising transactions, making clinical recommendations, or influencing…

EU AI ActISO/IEC 42001+2
Human-in-the-LoopProven

Human Escalation Pattern

The Human Escalation Pattern defines the architecture for routing AI-handled requests to…

Human-in-the-LoopProven

Human Override Pattern

The Human Override Pattern provides a lightweight, universally applicable mechanism by which…

Human-in-the-LoopProven

Hybrid Intelligence Pattern

The Hybrid Intelligence Pattern defines an architecture for systematically allocating each component…

AI IntegrationProven

EAAPL-INT007 — AI Circuit Breaker

AI IntegrationProven

EAAPL-INT003 — AI-Powered API Composition

AI-Powered API Composition uses large language models with function-calling capability to dynamically…

AI IntegrationProven

EAAPL-INT006 — AI Webhook Pattern

The AI Webhook Pattern delivers AI-generated notifications, inference results, and asynchronous AI…

AI IntegrationProven

EAAPL-INT005 — Batch AI Processing

Batch AI Processing applies AI inference to large volumes of data through…

AI IntegrationProven

EAAPL-INT008 — Bidirectional AI Sync

AI IntegrationProven

EAAPL-INT001 — Enterprise AI Service Bus

The Enterprise AI Service Bus pattern establishes an event-driven integration backbone that…

AI IntegrationProven

EAAPL-INT002 — Legacy System AI Augmentation

The Legacy System AI Augmentation pattern adds AI capabilities to existing enterprise…

AI IntegrationProven

EAAPL-INT004 — Real-Time AI Stream Processing

Real-Time AI Stream Processing applies AI inference directly to streaming data pipelines,…

Knowledge ManagementProven

EAAPL-KNW003: AI Knowledge Corpus Management

The AI Knowledge Corpus Management pattern defines the complete operational lifecycle for…

Knowledge ManagementProven

EAAPL-KNW006: Corpus Quality Assurance

Corpus Quality Assurance (CQA) is the automated pipeline that evaluates the fitness…

Knowledge ManagementProven

EAAPL-KNW001: Enterprise Knowledge Graph

An Enterprise Knowledge Graph (EKG) is a persistent, curated, machine-readable representation of…

Knowledge ManagementProven

EAAPL-KNW005: Knowledge Graph for Explainability

The Knowledge Graph for Explainability pattern uses a structured knowledge graph to…

Knowledge ManagementProven

EAAPL-KNW002: Semantic Data Layer

The Semantic Data Layer (SDL) is a governed translation layer that sits…

Knowledge ManagementProven

EAAPL-KNW004: Vector Database Management

Vector databases are the retrieval backbone of enterprise AI systems.

Model Context ProtocolEmerging

MCP Server Design

The MCP Server Design Pattern describes how to design, implement, and operate…

EU AI ActISO/IEC 42001+2
Model Context ProtocolEmerging

MCP Gateway

The MCP Gateway Pattern introduces a dedicated intermediary layer between MCP clients…

EU AI ActISO/IEC 42001+2
Model Context ProtocolEmerging

Multi-Server Orchestration

The MCP Multi-Server Orchestration Pattern describes how an AI model or agent…

EU AI ActISO/IEC 42001+2
Model Context ProtocolEmerging

MCP Authentication & Authorisation

The MCP Authentication & Authorisation Pattern defines the identity, authentication, and authorisation…

EU AI ActISO/IEC 42001+2
Model Context ProtocolEmerging

Stateful MCP Sessions

The Stateful MCP Sessions Pattern defines how to design, manage, and secure…

EU AI ActISO/IEC 42001+2
Model ManagementProven

EAAPL-MDL003 — Canary Model Release

Canary model release is the controlled, incremental exposure of a new AI…

Model ManagementProven

EAAPL-MDL006 — Fine-Tuning Pipeline

Fine-tuning is the process of adapting a pre-trained foundation model to an…

Model ManagementProven

EAAPL-MDL008 — Model Access Governance

Model access governance controls who can invoke, export, copy, and administer AI…

Model ManagementProven

EAAPL-MDL007 — Model Compression and Optimisation

Model compression reduces the computational footprint of an AI model — memory…

Model ManagementProven

EAAPL-MDL004 — Model Rollback

Model rollback is the capability to revert production AI model serving to…

Model ManagementProven

EAAPL-MDL001 — Model Versioning and Lineage Tracking

AI models are long-lived, continuously evolving artefacts.

Model ManagementProven

EAAPL-MDL005 — Multi-Model Ensemble

Multi-model ensemble combines the outputs of two or more AI models to…

Model ManagementProven

EAAPL-MDL002 — Shadow Model Deployment

Shadow model deployment allows an organisation to validate a new AI model…

Multi-Agent SystemsProven

EAAPL-MAG006 — Agent Handoff Protocol

Multi-Agent SystemsProven

EAAPL-MAG004 — Agent Swarm

Multi-Agent SystemsProven

EAAPL-MAG005 — Debate Agent

Multi-Agent SystemsProven

EAAPL-MAG003 — Human-in-the-Loop Agent

Multi-Agent SystemsProven

EAAPL-MAG001 — Multi-Agent Orchestration

Multi-Agent SystemsProven

EAAPL-MAG002 — Supervisor Agent

Observability & MonitoringProven

A/B Model Evaluation

Upgrading the LLM powering a production AI application carries risk that cannot…

EU AI ActISO/IEC 42001+1
Observability & MonitoringProven

EAAPL-OBS006 · AI Cost Observability

AI inference costs have a fundamentally different cost structure than traditional compute:…

Observability & MonitoringProven

EAAPL-OBS004 · AI Incident Management

AI system failures are qualitatively different from traditional software failures.

Observability & MonitoringProven

EAAPL-OBS008 · AI Performance Benchmarking

AI system quality degrades silently between benchmarking events.

Observability & MonitoringProven

EAAPL-OBS001 · AI Telemetry Architecture

AI systems present unique observability challenges that traditional APM tooling does not…

Observability & MonitoringProven

EAAPL-OBS007 · Distributed AI Tracing

AI pipelines are not single API calls.

Observability & MonitoringProven

EAAPL-OBS003 · Hallucination Detection

Large language models fabricate plausible-sounding content with confidence.

Observability & MonitoringProven

LLM Evaluation Pipeline

Deploying an LLM update to production without a structured evaluation gate is…

EU AI ActISO/IEC 42001+1
Observability & MonitoringProven

EAAPL-OBS005 · Model Drift Detection

AI models degrade silently.

Observability & MonitoringEmerging

Prompt Drift Detection

LLM providers update their underlying models without breaking API contracts.

EU AI ActISO/IEC 42001+1
Observability & MonitoringProven

EAAPL-OBS002 · Prompt Monitoring

Prompts sent to large language models in production are the primary control…

Platform EngineeringProven

AI API Gateway

The AI API Gateway pattern establishes a purpose-built control plane that sits…

EU AI Act
Platform EngineeringProven

EAAPL-PLT010 — AI Developer Portal Architecture

Enterprise AI capabilities—LLM APIs, embedding services, vector stores, AI agent frameworks, fine-tuning…

Platform EngineeringProven

AI Experiment Tracking

AI systems that cannot demonstrate systematic evaluation before production deployment are a…

EU AI ActISO/IEC 42001
Platform EngineeringProven

Enterprise AI Platform

The Enterprise AI Platform pattern establishes a shared, governed infrastructure layer that…

APRA CPS230EU AI Act+2
Platform EngineeringProven

Feature Store Integration

Feature stores solve a deceptively simple problem: when an ML model needs…

EU AI ActISO/IEC 42001+1
Platform EngineeringProven

LLM Caching Layer

LLM inference is expensive and often redundant.

Privacy ActGDPR
Platform EngineeringProven

LLM Cost Control

LLM inference costs exhibit a dangerous property shared with no previous enterprise…

ISO/IEC 42001
Platform EngineeringProven

Model Routing

The Model Routing pattern establishes intelligent, policy-driven dispatch of AI inference requests…

EU AI ActISO/IEC 42001+1
Platform EngineeringProven

Multi-Tenant AI Platform

When an AI platform serves multiple tenants—whether internal business units within an…

EU AI ActPrivacy Act+1
Platform EngineeringProven

Prompt Version Control

Prompts are the primary programming interface for LLM-based systems, yet most organisations…

EU AI ActISO/IEC 42001+1
Retrieval-Augmented GenerationProven

Agentic Retrieval-Augmented Generation

Agentic RAG places a reasoning AI agent in the orchestration loop of…

EU AI ActISO/IEC 42001+1
Retrieval-Augmented GenerationProven

Contextual RAG with Metadata Filtering

Contextual RAG with Metadata Filtering extends the foundational RAG pattern with a…

APRA CPS234EU AI Act+2
Retrieval-Augmented GenerationProven

Enterprise Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) is the foundational architecture pattern that grounds Large Language…

APRA CPS234EU AI Act+2
Retrieval-Augmented GenerationProven

Federated Retrieval-Augmented Generation

Federated RAG enables retrieval across multiple organisationally or geographically distributed knowledge bases…

APRA CPS234EU AI Act+2
Retrieval-Augmented GenerationProven

Graph Retrieval-Augmented Generation

Graph RAG combines vector-based semantic retrieval with structured knowledge graph traversal to…

EU AI ActISO/IEC 42001
Retrieval-Augmented GenerationProven

Hybrid Retrieval-Augmented Generation

Hybrid RAG combines dense (semantic) vector retrieval with sparse (keyword-based BM25) retrieval…

ISO/IEC 42001NIST AI RMF
Retrieval-Augmented GenerationProven

Multi-Source Retrieval-Augmented Generation

Enterprise knowledge is never stored in a single system.

APRA CPS230ISO/IEC 42001+2
Retrieval-Augmented GenerationProven

Multimodal Retrieval-Augmented Generation

Multimodal RAG extends the retrieval-augmented generation paradigm to knowledge corpora that include…

EU AI ActISO/IEC 42001+1
Retrieval-Augmented GenerationProven

Secure Retrieval-Augmented Generation

Secure RAG is the enterprise access-control overlay that must be applied to…

APRA CPS234EU AI Act+3
Retrieval-Augmented GenerationProven

Streaming Retrieval-Augmented Generation

Streaming RAG extends the foundational RAG architecture to continuously ingest and index…

APRA CPS230ISO/IEC 42001
Reasoning ModelsEmerging

Extended Thinking Gate

The Extended Thinking Gate is an inference-time routing pattern that activates a…

EU AI ActISO/IEC 42001+1
Reasoning ModelsEmerging

Think Budget Allocation

Think Budget Allocation is the pattern of dynamically sizing the thinking-token budget…

EU AI ActISO/IEC 42001+1
Reasoning ModelsEmerging

Reasoning-then-Act

Reasoning-then-Act (R-then-A) is an agentic architecture pattern that separates the thinking phase…

EU AI ActISO/IEC 42001+1
Reasoning ModelsProven

Cost-Quality Router

The Cost-Quality Router is an LLM gateway pattern that dynamically selects from…

EU AI ActISO/IEC 42001+1
Reasoning ModelsEmerging

Multi-Step Verification

Multi-Step Verification is the pattern of using one or more independent reasoning…

EU AI ActISO/IEC 42001+1
AI SecurityProven

Adversarial Input Defence

Adversarial Input Defence addresses a class of attacks specifically designed to manipulate…

APRA CPS234EU AI Act+2
AI SecurityProven

AI Data Classification

AI Data Classification defines the automated detection, labelling, and enforcement architecture that…

APRA CPS234EU AI Act+3
AI SecurityProven

AI Gateway

The AI Gateway pattern establishes a centralised, enterprise-grade control plane through which…

APRA CPS234EU AI Act+2
AI SecurityProven

AI Output Filtering

AI Output Filtering is the post-generation inspection and transformation pipeline that evaluates…

APRA CPS234EU AI Act+2
AI SecurityProven

LLM Input Sanitisation

LLM Input Sanitisation is a pre-processing pipeline that transforms raw application inputs…

APRA CPS234EU AI Act+3
AI SecurityProven

Model Isolation

Model Isolation defines the architectural pattern for constraining the execution environment of…

APRA CPS234EU AI Act+1
AI SecurityProven

Prompt Firewall

The Prompt Firewall is an inline defensive layer that inspects every user…

APRA CPS234EU AI Act+1
AI SecurityProven

Secrets Management for AI

Secrets Management for AI addresses one of the most prevalent and consequential…

APRA CPS234EU AI Act
AI SecurityProven

Secure Tool Invocation

Secure Tool Invocation defines the security architecture for AI agents that can…

APRA CPS234EU AI Act+2
AI SecurityProven

Zero-Trust AI Pipeline

The Zero-Trust AI Pipeline applies the "never trust, always verify" security architecture…

APRA CPS234EU AI Act+1