Human in the Loop (HITL)

<video src="https://cdn.copilotkit.ai/docs/copilotkit/images/coagents/human-in-the-loop-example.mp4" className="rounded-lg shadow-xl" loop playsInline controls autoPlay muted /> {/* <Callout> This video shows an example of our AI Travel App using HITL to get user feedback.

</Callout> */}

What is Human-in-the-Loop (HITL)?

Human-in-the-loop (HITL) allows agents to request human input or approval during execution, making AI systems more reliable and trustworthy. This pattern is essential when building AI applications that need to handle complex decisions or actions that require human judgment.

<Frame className="my-0"> </Frame>

When should I use this?

HITL combines the efficiency of AI with human judgment, creating a system that's both powerful and reliable. The key advantages include:

• Quality Control: Human oversight at critical decision points
• Edge Cases: Graceful handling of low-confidence situations
• Expert Input: Leverage human expertise when needed
• Reliability: More robust system for real-world use

How can I use this?

Read more about the approach to HITL in Pydantic AI Agents.

<CTACards columns={1} cards={[ { iconKey: "share2", title: "Flow-based", description: "Utilize Pydantic AI Agents to create Human-in-the-Loop workflows.", href: "/pydantic-ai/human-in-the-loop/agent", }, ]} />