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

# Tidio tutorial

> Pipe live user data from the Autoplay SDK directly into Tidio's Lyro AI Agent for real-time context-aware conversations.

Discover how to pipe live user data from the **Autoplay SDK** directly into your **Tidio Lyro AI Agent**. This guide covers wiring a Lyro Action that pulls a user's live activity on demand from the Autoplay MCP server — no server to host, no events to store.

## ✨ Final result

<iframe width="100%" height="400" src="https://www.youtube.com/embed/9cf5BhQydCI" title="Tidio Lyro AI Agent responding with real-time user context" frameBorder="0" allow="accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture" allowFullScreen />

***

## 📋 Prerequisites

Complete the [Quickstart](/quickstart). You should have:

* **Your activity source set up** — PostHog (or Amplitude) capturing events, with `identify` setting a stable `user_id` (and email after login if you use it)
* **A registered product** — your `product_id`, `mcp_url`, and `mcp_key` from the Quickstart
* **A [Tidio](https://tidio.com) account**

***

## The building blocks

Follow the steps in order — each page stands alone so you can ship incrementally.

1. **[Connect real-time events](./step-1-connect-real-time-events)** — Wire a Lyro Action that calls the Autoplay MCP server for a user's live activity.
2. **[Define proactive triggers](./step-2-define-proactive-triggers)** — Proactively message users in Tidio based on what they're doing in your product. *(Coming soon)*
