The Agentic AI Series
The Catalog
Seventeen volumes, 306 patterns, grouped into five clusters. A Fowler-style reference for agentic AI engineering — organized for retrieval, not linear reading. Start anywhere.
Workflow & Primitives
The foundational primitives — what agents do, what they use, what triggers them.Patterns of AI Agent Workflows
The workflow patterns: ReAct, Plan-Execute, Self-Reflection, Router, Hierarchical Decomposition, and the cluster of compound patterns. The first volume; established the format.
23 patterns Volume 02The Claude Skills Catalog
Skills as the unit of agent capability. The major repositories: Anthropic Claude Skills, Cursor commands, Grid Dynamics Rosetta, plus emerging ecosystems.
33 patterns Volume 03The AI Agent Tools Catalog
Function-calling primitives: tool definitions, schemas, MCP, sandboxing, web tools, code execution, the tool ecosystem.
34 patterns Volume 04The AI Agent Events & Triggers Catalog
Reactive orchestration: schedule, webhook, file-watcher, queue, message-bus, change-data-capture — the patterns that make agents respond rather than only execute.
23 patternsInfrastructure
The substrate on which agents run — memory, fabric, multi-agent coordination, human-in-the-loop, evaluation.The AI Agent Fabric Catalog
The infrastructure layer: agent runtime, sandboxing, networking, secrets, deployment, scaling primitives.
20 patterns Volume 06The AI Agent Memory Catalog
State and memory: vector DBs, dedicated memory layers (Mem0, Letta, Zep), shared state, Postgres+pgvector, embedding models, knowledge graphs.
19 patterns Volume 07The Human-in-the-Loop Catalog
Approval gates, observability for agents, human-agent UIs, intervention mechanisms.
17 patterns Volume 08The Evaluation & Guardrails Catalog
Eval frameworks, runtime guardrails, classifier safety models, red-teaming, OWASP / NIST / MITRE ATLAS standards.
18 patterns Volume 09The Multi-Agent Coordination Catalog
Protocols (MCP, A2A, ACP), topologies, frameworks (LangGraph, AutoGen, CrewAI, OpenAI Agents SDK, Claude subagents), coordination patterns.
16 patternsContext & Content
What agents work with — retrieved knowledge, prompts, context windows.The Retrieval Catalog
RAG patterns at the agent layer: chunking, embedding, retrieval pipelines, citation, multi-source retrieval.
16 patterns Volume 15The Prompting & Context Engineering Catalog
Prompt design, context window engineering, the discipline of structuring agent inputs.
11 patternsNon-Functional Concerns
Compliance, security, ops, economics — the substrate that makes production agents possible.The Compliance & Regulatory Catalog
EU AI Act, NIST AI RMF, ISO 42001, GDPR-for-AI patterns, the regulated-industry overlay.
15 patterns Volume 12The AI Infrastructure Security Catalog
Beyond runtime guardrails: supply-chain security for agent stacks, secrets management, network isolation, audit infrastructure.
13 patterns Volume 16The LLMOps Catalog
Operating LLM-augmented systems: model deployment, monitoring, A/B testing, drift detection, cost management at the model layer.
9 patterns Volume 17The AI Agent Economics Catalog
Pricing models, cost analysis, ROI patterns, build-vs-buy frameworks, the business-side discipline.
8 patternsUX & Products
The user-facing surfaces of agents and the product landscape.The Agent UX Patterns Catalog
Token streaming, intermediate state display, generative UI, approval and confirmation UX, citation and confidence display.
16 patterns Volume 14The AI Agent Products Survey
Comparison across major agent products: Cursor, Claude Code, ChatGPT Operator, Devin, Replit Agent, the cloud-provider offerings.
15 patterns