Starting the Tutorial
Starting the Tutorial
So you're ready to give Parlant a try—great choice!
The purpose of this tutorial is to do two things:
- Set up a customer-facing agent that's cooler and more controllable than any agent you've built before—and do it in 1/10th the time.
- Give you a taste of what Parlant can do and how it helps you control your agent's behavior: guidelines, glossary, context variables and tools.
What You'll Build
You're going to build a conversational assistant for a retail tech store. This assistant would streamline customer interactions and provide immediate, self-served assistance to customers who are trying to decide what to buy—such as a laptop, a phone, a printer, etc.
This guide will walk you through the complete setup process, including installing dependencies, setting up and configuring your agent, and integrating backend APIs.
In about 15 minutes, you'll understand how to create and deploy a conversational agent that can effectively handle customer inquiries and provide professional assistance in a tech retail context. Here's a quick example of what to expect:
Interaction Example
Customer: Hi there, I'm looking to buy a laptop for gaming
Assistant: Hey! I'd be happy to help you find a gaming laptop. Could you tell me what types of games you're planning to play and what's your budget range?
Customer: I want to play games like Cyberpunk 2077 and possibly heavier games than that
Assistant: Game on! So you're looking for a laptop that's more lag-free, overclockable, and high-performing with a touch of high-end screen resolution.
Customer: Yeah, something in that direction
Assistant: Cool. Do you have a budget, or would you like me to give you the 3 best ones we have in store?
Customer: My budget is between $1500 to $3000
Assistant: Okay. I can work with that. I have 2 models for you:
The Razer Blade 18 RTX 4090, which we're selling at $2899.99 (instead of $3989.00).
The HP OMEN 16 RTX 4070 at $1899.99.
- Customer: Which one would you recommend?
- Assistant: The Razer Blade 18 RTX has Intel i9-13950HX, 2TB SSD, and a 4K display. And at the discount we have right now, I think this fits better into your budget, so I would recommend that if you ask me.
To achieve this level of interaction, we’ll:
- Configure your assistant: Set up your Parlant agent with custom behavior settings and response patterns
- Create a basic frontend: Learn the ropes of how to eventually connect your agent to your own frontend application
- Build the backend: Create a tool service that connects to the store's database
Ready to begin? Let's dive in!