Discussion on Human in the Loop for Agents

[julian-risch]

This is the discussion board for Human in the Loop features for Agent tool calls.

This new feature allows to require human confirmation for an Agent's tool calls. In short, when you build an Agent, you can define which tools require a confirmation from the user and you can choose how that confirmation should be requested. For example, you can define that a tools always requires confirmation, whereas another tool requires confirmation only when the Agent uses it for the first time:

agent = Agent(
    chat_generator=OpenAIChatGenerator(model="gpt-4.1"),
    tools=[balance_tool, addition_tool, phone_tool],
    system_prompt="You are a helpful financial assistant. Use the provided tool to get bank balances when needed.",
    confirmation_strategies={
        balance_tool.name: BlockingConfirmationStrategy(
            confirmation_policy=AlwaysAskPolicy(), confirmation_ui=RichConsoleUI(console=cons)
        ),
        addition_tool.name: BlockingConfirmationStrategy(
            confirmation_policy=NeverAskPolicy(), confirmation_ui=SimpleConsoleUI()
        ),
        phone_tool.name: BlockingConfirmationStrategy(
            confirmation_policy=AskOncePolicy(), confirmation_ui=SimpleConsoleUI()
        ),
    },
)

Here are code examples, including one that shows how to combine the feature with breakpoints:

• Intro Example
• Breakpoint Example
• Multi-Agent Example

Try it out and let us know what you think in the comments 👇

Note: Experimental features live in this repository for a fixed period of time. We don't guarantee that we will continue maintaining experimental features. But if they are successful, stable and if you like it, we will move the feature to the core Haystack package.

[Hansehart]

This is an incredibly valuable feature. I would love to see it graduate from experimental! For me its the foundation for reliable agentic workflows.