> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agno.com/llms.txt
> Use this file to discover all available pages before exploring further.

# HITL

> This example shows how to implement human-in-the-loop functionality in your Agno tool calls.

This example shows how to implement human-in-the-loop functionality in your Agno tools.

* Add pre-hooks to tools for user confirmation
* Handle user input during tool execution
* Gracefully cancel operations based on user choice

## Prerequisites

* Install dependencies: `uv pip install openai httpx rich agno`

```python theme={null}


import json
from typing import Iterator

import httpx
from agno.agent import Agent
from agno.exceptions import StopAgentRun
from agno.models.openai import OpenAIChat
from agno.tools import FunctionCall, tool
from rich.console import Console

# ---------------------------------------------------------------------------
# Create Agent
# ---------------------------------------------------------------------------


# This is the console instance used by the print_response method
# We can use this to stop and restart the live display and ask for user confirmation
console = Console()


def pre_hook(fc: FunctionCall):
    """Pre-hook that asks for user confirmation before running a tool."""
    print(f"\n⚠️  About to run: {fc.function.name}")
    print(f"   Arguments: {fc.arguments}")

    message = input("Do you want to continue? [y/n] (default: y): ").strip().lower()

    if message == "n":
        raise StopAgentRun(
            "Tool call cancelled by user",
            agent_message="Stopping execution as permission was not granted.",
        )


@tool(pre_hook=pre_hook)
def get_top_hackernews_stories(num_stories: int) -> Iterator[str]:
    """Fetch top stories from Hacker News.

    Args:
        num_stories (int): Number of stories to retrieve

    Returns:
        str: JSON string containing story details
    """
    # Fetch top story IDs
    response = httpx.get("https://hacker-news.firebaseio.com/v0/topstories.json")
    story_ids = response.json()

    # Yield story details
    for story_id in story_ids[:num_stories]:
        story_response = httpx.get(
            f"https://hacker-news.firebaseio.com/v0/item/{story_id}.json"
        )
        story = story_response.json()
        if "text" in story:
            story.pop("text", None)
        yield json.dumps(story)


# Initialize the agent
agent = Agent(
    model=OpenAIChat(id="gpt-4o-mini"),
    tools=[get_top_hackernews_stories],
    markdown=True,
)

# ---------------------------------------------------------------------------
# Run Agent
# ---------------------------------------------------------------------------
if __name__ == "__main__":
    agent.print_response(
        "Fetch the top 2 hackernews stories?", stream=True, console=console
    )
```

## Run the Example

```bash theme={null}
# Clone and setup repo
git clone https://github.com/agno-agi/agno.git
cd agno/cookbook/91_tools/other

# Create and activate virtual environment
./scripts/demo_setup.sh
source .venvs/demo/bin/activate

python human_in_the_loop.py
```