"""
Pattern 06.01: Feedback Loop
Output fed back as input for self-correction
"""
from typing import TypedDict
from langgraph.graph import StateGraph, END
from langchain_openai import ChatOpenAI
from langchain_core.messages import HumanMessage


class FeedbackLoopState(TypedDict):
    """State for Feedback Loop pattern."""
    input: str
    output: str


def agent_function(state: FeedbackLoopState) -> FeedbackLoopState:
    """Feedback Loop agent implementation."""
    llm = ChatOpenAI()
    prompt = f"Process this using Feedback Loop pattern: {state['input']}"
    response = llm.invoke([HumanMessage(content=prompt)])
    state["output"] = str(response.content)
    return state


def create_feedback_loop():
    """Create Feedback Loop workflow."""
    workflow = StateGraph(FeedbackLoopState)
    workflow.add_node("agent", agent_function)
    workflow.set_entry_point("agent")
    workflow.add_edge("agent", END)
    return workflow.compile()


if __name__ == "__main__":
    workflow = create_feedback_loop()
    result = workflow.invoke({"input": "Test Feedback Loop", "output": ""})
    print(f"\n=== Feedback Loop Pattern ===\nOutput: {result['output'][:200]}...")

    

Agentic Orchestration Pattern: Feedback Loop Pattern

01 Feedback Loop Pattern – Detailed Documentation

Overview

File: 06_feedback_control/01_feedback_loop.py
Pattern Category: 06 Feedback Control
Implementation: LangGraph/CrewAI

Pattern Description

Pattern 06.01: Feedback Loop Output fed back as input for self-correction

---

Code Structure

Imports

from typing import TypedDict
from langgraph.graph import StateGraph, END
from langchain_openai import ChatOpenAI
from langchain_core.messages import HumanMessage

Purpose of imports: – TypedDict: For type-safe state definitions – StateGraph: LangGraph’s graph-based workflow orchestration – ChatOpenAI: OpenAI LLM integration – HumanMessage: LangChain message formatting

State Definition

class FeedbackLoopState(TypedDict):
    """State for Feedback Loop pattern."""
    input: str
    output: str


def agent_function(state: FeedbackLoopState) -> FeedbackLoopState:

FeedbackLoopState: State for Feedback Loop pattern.

State Fields: – input: Stores input – output: Stores output – def agent_function(state: Stores def agent function(state – prompt = f"Process this using Feedback Loop pattern: Stores prompt = f”Process this using Feedback Loop pattern – def create_feedback_loop(): Stores def create feedback loop()

---

Functions

agent_function()

Line: 17
Arguments: state

Feedback Loop agent implementation.

def agent_function(state: FeedbackLoopState) -> FeedbackLoopState:
    """Feedback Loop agent implementation."""
    llm = ChatOpenAI()
    prompt = f"Process this using Feedback Loop pattern: {state['input']}"
    response = llm.invoke([HumanMessage(content=prompt)])
    state["output"] = str(response.content)
    return state


def create_feedback_loop():

create_feedback_loop()

Line: 26
Arguments: “

Create Feedback Loop workflow.

def create_feedback_loop():
    """Create Feedback Loop workflow."""
    workflow = StateGraph(FeedbackLoopState)
    workflow.add_node("agent", agent_function)
    workflow.set_entry_point("agent")
    workflow.add_edge("agent", END)
    return workflow.compile()


if __name__ == "__main__":

---

Line-by-Line Explanation

Line 5: Import statement

from typing import TypedDict

Imports TypedDict for creating type-safe state dictionaries.

Line 6: Import statement

from langgraph.graph import StateGraph, END

Imports StateGraph – the core LangGraph class for building workflows.

Line 7: Import statement

from langchain_openai import ChatOpenAI

Imports ChatOpenAI for LLM interactions.

Line 8: Import statement

from langchain_core.messages import HumanMessage

Imports HumanMessage for formatting prompts to the LLM.

Line 11: Class definition

class FeedbackLoopState(TypedDict):

Defines the state structure using TypedDict for type safety.

Line 12: Module docstring

    """State for Feedback Loop pattern."""

Describes the pattern and its purpose.

Line 17: Function agent_function definition

def agent_function(state: FeedbackLoopState) -> FeedbackLoopState:

Defines the agent_function function that processes the workflow state.

Line 18: Module docstring

    """Feedback Loop agent implementation."""

Describes the pattern and its purpose.

Line 26: Function create_feedback_loop definition

def create_feedback_loop():

Defines the create_feedback_loop function that processes the workflow state.

Line 27: Module docstring

    """Create Feedback Loop workflow."""

Describes the pattern and its purpose.

---

Usage Example

if __name__ == "__main__":
    workflow = create_feedback_loop()
    result = workflow.invoke({"input": "Test Feedback Loop", "output": ""})
    print(f"\n=== Feedback Loop Pattern ===\nOutput: {result['output'][:200]}...")

---

Key Concepts

1. State Management: Uses TypedDict to maintain workflow state
2. Graph-Based Flow: LangGraph orchestrates execution flow
3. Agent Functions: Each node processes and updates state
4. LLM Integration: Uses ChatOpenAI for intelligent processing

Pattern Benefits

• ✅ Type-safe state management
• ✅ Clear workflow visualization
• ✅ Modular and reusable components
• ✅ Easy to test and debug
• ✅ Scalable architecture

Related Patterns

• See other patterns in the same category
• Explore combination possibilities
• Check the main documentation for pattern relationships