# AI Agent Webhooks > HTTP callbacks that notify external systems when specific events occur in an AI agent's lifecycle, such as new messages, completed actions, or user sign-ups. Category: Architecture Source: https://chipp.ai/ai/glossary/ai-agent-webhooks AI agent webhooks are HTTP callbacks that send real-time notifications to external systems when specific events occur within an AI agent. They enable integration between AI agents and the rest of your technology stack without requiring constant polling. Common webhook events include: new conversation started, message received, message sent, tool/action executed, user signed up, credits purchased, conversation ended, and error occurred. When these events fire, the agent sends an HTTP POST request to a configured URL with relevant event data. Webhooks enable powerful integrations. For example: when a lead is qualified by the AI agent, a webhook can create a record in Salesforce; when a support ticket is resolved, a webhook can update Zendesk; when a new user signs up through the agent, a webhook can trigger a welcome email sequence. The typical webhook payload includes: event type, timestamp, conversation ID, user information, message content, and any metadata relevant to the event. Webhook receivers should respond with a 2xx status code to acknowledge receipt. Best practices include: implementing retry logic for failed deliveries, using webhook signatures for security verification, processing webhooks asynchronously to avoid timeout issues, and logging all webhook activity for debugging. ## Related Terms - [Webhook](https://chipp.ai/ai/glossary/webhook.md): An automated HTTP callback that sends real-time data to a specified URL when a specific event occurs in a system. - [AI Agent Hooks](https://chipp.ai/ai/glossary/ai-agent-hooks.md): Event-driven callbacks that execute custom logic at specific points in an AI agent's lifecycle, such as before/after message processing or tool execution. - [API](https://chipp.ai/ai/glossary/api.md): Application Programming Interface — a set of rules allowing different software applications to communicate and exchange data. - [Function Calling](https://chipp.ai/ai/glossary/function-calling.md): The ability of AI models to identify when a conversation requires calling an external function or API, and to generate the structured parameters needed to make that call. --- This term is part of the [Chipp AI Glossary](https://chipp.ai/ai/glossary), a reference of AI concepts written for builders and businesses. Build AI agents with no code at https://chipp.ai.