Agentic AI
A visual catalog of battle-tested patterns for building AI agents. From simple prompt chains to multi-agent swarms.
A visual catalog of common failure modes in AI agent systems. Learn what to avoid before you build.
Pattern Categories
Browse patterns by the problem domain they address
Featured Patterns
Essential patterns every AI engineer should know
ReAct
Interleave reasoning (thinking about what to do) with acting (using tools) in a Thought → Action → Observation loop.
Orchestrator-Workers
A central LLM dynamically breaks down a task, delegates subtasks to worker LLMs, and synthesizes their results.
Retrieval-Augmented Generation
Retrieve relevant information from an external knowledge base before generating a response, grounding the LLM in facts.
Human-in-the-Loop
Require human approval at critical decision points, balancing agent autonomy with human oversight.
Reflexion
The agent reflects on its past failures, stores verbal self-critiques in memory, and uses them to improve future attempts.
Model Context Protocol
A standardized, open protocol for connecting LLMs to external tools, data sources, and services through a universal interface.
Context Rot
🚫Agent context fills with stale, irrelevant information over time, silently degrading output quality.
Hallucination Cascade
🚫Agent hallucinates a fact or tool output, then reasons on the hallucination as truth, compounding errors through every subsequent step.
God Prompt
🚫Cramming an entire complex task into a single monolithic prompt, expecting the LLM to handle everything at once.
Infinite Loop
🚫Agent enters an unbounded execution cycle — retrying failed actions, oscillating between states, or generating plans it never completes.