Pathors home page
English
Search...
⌘K
Dashboard
Dashboard
Search...
Navigation
Tutorials
Create Conversational Agent
Guides
API Reference
Get Started
Introduction
Quick Start Guide
Quick Start
Building a Phone Assistant with Vapi
Quick Start Guide to Chat Integration
Quick Start Guide to LINE Bot Integration
Tutorials
Create Conversational Agent
Build a Complex Conversational Agent
Connect Knowledge Base to Agent
Custom Models & Google Calendar Integration
Usage Analytics
On this page
Tutorial Video
Overview
Steps
Related Resources
Tutorials
Create Conversational Agent
Learn how to create your first conversational agent using Pathors platform.
This tutorial will walk you through building a restaurant Q&A chatbot using Pathors.
Tutorial Video
Overview
In this example, we’ll create a restaurant Q&A bot, covering conversation flow, nodes, prompts, and testing agent responses—showcasing Pathors basics.
Steps
Set Up Conversation Flow and Nodes
Design the conversation flow with nodes and edges.
Set a welcome message in the start node, e.g., “Hello, I am the smart assistant of Dongfeng Restaurant.”
Allow users to ask questions.
Configure Prompts and Conditions
Add prompts to nodes, including restaurant info (business hours, phone, etc.).
Route the conversation to different nodes based on user questions, customizing responses.
You can pre-configure tools or knowledge base (covered in later tutorials).
Design the End Node
Set a closing message for the end of the conversation, such as “Thank you” or an invitation to fill out a survey.
Test Agent Responses
Ask questions like “What are your restaurant’s business hours?” to verify the agent responds correctly based on the prompts.
Advanced Settings
Use Global Prompts to adjust tone, timezone, etc.
You can enable system prompt mode to combine all node prompts into a single system prompt, suitable for scenarios requiring full context.
Related Resources
Pathors Official Documentation
Next Tutorial: Appendix - Build a Complex Conversational Agent
Quick Start Guide to LINE Bot Integration
Build a Complex Conversational Agent
Assistant
Responses are generated using AI and may contain mistakes.