Agentic Blueprints 29

Chatbot Simulation Evaluation

io.github.langchain-ai/agent-simulation-evaluation

LangGraph

A simulated-user agent plays the customer against your chatbot so you can evaluate the whole conversation before real users do.

Corrective RAG

io.github.langchain-ai/corrective-rag

LangGraph

Grades retrieved documents for relevance and, when they fail the grade, falls back to web search before answering.

WebVoyager

io.github.langchain-ai/web-voyager

LangGraph

A vision-enabled browser agent that looks at annotated screenshots and decides where to click, scroll, and type until the task is done.

Agent Patterns Gallery

io.github.openai/agent-patterns-gallery

Custom

Sixteen single-file patterns from OpenAI: deterministic pipelines, agents-as-tools, parallelization, routing, LLM-as-judge, guardrails, human-in-the-loop.

Self-Evaluation Loop Flow

io.github.crewaiinc/self-evaluation-loop-flow

CrewAI

One crew writes in Shakespeare's voice, a second crew reviews the output, and the flow loops the feedback until the writing passes.