diff --git a/README.md b/README.md
index 9e04e50..9706b2d 100644
--- a/README.md
+++ b/README.md
@@ -1,42 +1,63 @@
-# Minimal ASGI Middleware
+# Human‑in‑the‑Loop Agent
 
-## Overview
-This repository contains a simple ASGI middleware implementation that can be used with frameworks such as FastAPI or Starlette. It logs the path of every incoming HTTP request.
+This repository implements a simple command‑line agent that pauses before each tool call and asks the user to approve or reject the action. It uses **LangChain** and **LangGraph**'s `HumanInTheLoopMiddleware`.
 
-## Installation
-No external dependencies are required. Just copy the files into your project.
+## Prerequisites
+
+- Python 3.11+ (tested with 3.11 and 3.12)
+- An OpenAI API key or a local LLM compatible with the OpenAI API (e.g., Ollama)
+
+## Setup
 
 ```bash
-# If you prefer a virtual environment
+# Create a virtual environment
 python -m venv .venv
 source .venv/bin/activate
 
-# Install any dependencies (none for this minimal example)
-# pip install -r requirements.txt
+# Install dependencies
+pip install -r requirements.txt
+```
+
+## Configuration
+
+*OpenAI API key*
+
+```bash
+export OPENAI_API_KEY="YOUR_KEY"
+```
+
+*Local model (e.g., Ollama)*
+
+If you run a local model, edit **agent.py** and uncomment/adjust the `base_url` and `api_key` arguments in the `ChatOpenAI` constructor:
+
+```python
+ChatOpenAI(
+    base_url="http://localhost:11434/v1",
+    api_key="ollama",
+    model="llama3",
+)
 ```
 
 ## Usage
-Import the `get_middleware` helper and wrap your ASGI application:
-
-```python
-from fastapi import FastAPI
-from middleware import get_middleware
-
-app = FastAPI()
-app = get_middleware(app)
-
-@app.get("/")
-async def root():
-    return {"message": "Hello World"}
-```
-
-Run the app with Uvicorn or any ASGI server:
 
 ```bash
-uvicorn main:app --reload
+python agent.py
 ```
 
-You should see log messages for each request in the console.
+You will be prompted to enter a question. The agent will invoke the `get_weather` tool and pause for confirmation.
+
+```
+Enter your question: What is the weather in Kazan today?
+
+Action 1: get_weather
+Arguments: {'city': 'Kazan', 'date': 'today'}
+Decision (a=approve, r=reject): a
+
+Agent response:
+Weather in Kazan on today
+```
+
+*If you reject an action, you will be asked for a reason, which is sent back to the agent as feedback.*
 
 ## License
 MIT