Agentic Design Patterns

This repository contains an interactive, single-file tutorial on essential agentic design patterns for building intelligent AI systems.

Overview

The included index.html file is a self-contained interactive tutorial and reference guide to various patterns used in modern AI development. It's designed to make complex architectural concepts accessible through simple visual representations, detailed explanations, and real-world examples.

Within a single file, it brings together an overview page, a pattern-relationships view, detailed pattern entries, and case studies.

Online Use

Open https://zeljkoavramovic.github.io/agentic-design-patterns/ in your browser to load it.

Offline Use

Simply download the index.html file and open it in any modern web browser.

Pattern Relationships

The following diagram illustrates how different agentic patterns often connect and rely on each other. This provides a high-level view of the ecosystem.

hljs language-mermaid

            graph LR
                subgraph "Core Patterns"
                    P1("Prompt Chaining")
                    P2("Routing")
                    P5("Tool Use")
                    P3("Parallelization")
                    P28("Dynamic Scaffolding")
                    P27("Code-Then-Execute")
                end
                subgraph "Reasoning & Strategy Patterns"
                    P4("Reflection")
                    P6("Planning")
                    P18("Reasoning Techniques")
                    P22("Exploration & Discovery")
                    P24("Parallel Fusion")
                    P21("Prioritization")
                end
                subgraph "Orchestration Patterns"
                    P11("Goal Setting & Monitoring")
                    P7("Multi-Agent Collaboration")
                    P15("Inter-Agent Communication")
                    P17("Resource-Aware Optimization")
                    P16("Awareness")
                end
                subgraph "Reliability & Control Patterns"
                    P19("Guardrails & Safety")
                    P13("Human-in-the-Loop")
                    P12("Exception Handling & Recovery")
                    P23("The Stop Hook")
                    P25("The Ralph Wiggum Loop")
                    P29("Spec-First Agent")
                end
                subgraph "Infrastructure & State Patterns"
                    P14("Knowledge Retrieval RAG")
                    P20("Evaluation & Monitoring")
                    P8("Memory Management")
                    P10("MCP")
                    P26("Session Isolation")
                    P9("Learning and Adaptation")
                end

                P7 -- "requires" --> P15
                P7 -. "uses" .-> P6
                P7 -. "uses" .-> P8
                P6 -- "can be composed of" --> P1
                P6 -- "often requires" --> P5
                P14 -- "is a form of" --> P5
                P2 -- "is used by" --> P17
                P4 -- "is a form of" --> P20
                P9 -- "is enabled by" --> P13
                P13 -- "is triggered by" --> P19
                P13 -- "is triggered by" --> P12
                P18 -- "can be improved by" --> P4
                P22 -- "is a form of" --> P6
                P1 -- "often needs" --> P12
                P6 -- "detects" --> P16
                P17 -- "detects" --> P16
                P7 -- "detects" --> P16
                P16 -- "provides facts for" --> P6
                P16 -- "provides facts for" --> P17

                %% New Connections
                P23 -- "is a form of" --> P19
                P25 -- "relies on" --> P23
                P25 -- "requires" --> P26
                P24 -- "requires" --> P26
                P24 -- "is an evolution of" --> P3
                P5 -- "is used by" --> P23

                %% Connections for New Patterns
                P26 -- "supports" --> P27
                P26 -- "supports" --> P28
                P5 -- "evolves to" --> P27
                P23 -- "validates" --> P29
                P18 -- "is a form of" --> P27
                P5 -- "extended by" --> P28
                P19 -- "enforces" --> P29

Patterns Included

The tutorial covers the following 29 patterns, grouped into categories:

Core Patterns

Prompt Chaining
Routing
Parallelization
Tool Use
Code-Then-Execute
Dynamic Scaffolding

Reasoning & Strategy Patterns

Reflection
Planning
Reasoning Techniques
Parallel Fusion
Prioritization
Exploration & Discovery

Orchestration Patterns

Multi-Agent Collaboration
Goal Setting & Monitoring
Inter-Agent Communication
Awareness
Resource-Aware Optimization

Infrastructure & State Patterns

Memory Management
Learning and Adaptation
Model Context Protocol (MCP)
Knowledge Retrieval (RAG)
Evaluation & Monitoring
Session Isolation

Reliability & Control Patterns

The Stop Hook
Exception Handling & Recovery
Human-in-the-Loop
The Ralph Wiggum Loop
Guardrails & Safety
Spec-First Agent

License

MIT - use freely, improve openly, credit kindly.

Support the Project

If this project has helped you, support is most welcome:

⭐ Star the repository to show your appreciation.
💬 Spread the word.

Related Projects

CLAUDE.md That Works - Discipline your AI coding sessions across tools and projects: core coding principles (think before coding, simplicity first, surgical changes, goal-driven execution), collaborative working model (human/AI partnership with explicit boundaries), order of precedence, operating modes (default, ambiguity, cleanup), wording conventions (Must / Should / May), shared vocabulary / interpretation layer, scope control for existing code, hard stops with rule citation and authorization gate, verification by task type with manual fallback, broken baseline handling, structured post-task reporting, documentation rules, and full multi-dimensional agnosticism. Each feature is designed to keep AI coding more disciplined, safer, and more predictable across languages, frameworks, tools, operating systems, and project types.

Credits

The patterns and diagrams are distilled from extensive research on agentic AI systems. For more information visit the following links:

Special thanks to user Thaddy from the Lazarus forum for pointing out the Brahms research.

agentic-design-patterns