Crisp AI tutorial

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.

​

✨ Final result

User: How do I get started?

Bot: Welcome! You can create projects, view reports, and manage your
team from the main menu. Let me know if you need help with anything!

(Generic onboarding reply. No idea where the user is or what they've
already tried. Doesn't move them forward.)

User: How do I get started?

Bot: Great question! I can see you've already explored the Dashboard
and had a look at Reports — nice start!

The next step most users take is creating their first project:

1. Click "My Projects" in the left sidebar
2. Hit the "Add Project" button at the top right
3. Choose a template or start from scratch
4. Fill in the name and settings, then click "Create"

Once your project is set up, the Reports tab you were just on will
start showing real data for it. Want me to walk you through what
each report tracks?

(Acknowledges what they've already seen, gives them a concrete next
step, and connects it back to a feature they showed interest in.)

​

📋 Prerequisites

• PostHog in the browser — snippet, API key, product_id on identify (and email after login if you use it)
• Connector credentials — URL, API token, stream URL (e.g. https://your-connector.onrender.com/stream/ plus your product id from the dashboard)
• autoplay-sdk installed — and a successful test stream from the Quickstart
• A Crisp account — with Plugin-tier API access enabled

​

The building blocks

1. Connect real-time events — Set up the webhook server and event listener so Crisp replies with real-time context.
2. Define proactive triggers — Proactively message users in Crisp based on what they’re doing in your product. (Coming soon)