Prerequisites
Before creating training examples, ensure you have:Account & Agent Setup
- StateSet account with API access
- At least one agent created and configured
- API credentials from the StateSet Dashboard
Technical Requirements
- Node.js 16+ installed (for SDK examples)
- Basic understanding of REST APIs and JavaScript
- Text editor for JSON/code editing
Training Data
- Collection of real customer conversations for training data
- Access to your customer support team for example validation
- Understanding of your brand voice and service standards
Domain Knowledge
- Familiarity with machine learning concepts (helpful)
- Understanding of conversational AI training principles
- Knowledge of your customer service workflows and scenarios
Introduction
Examples are the cornerstone of training effective AI agents in StateSet ReSponse. By providing real conversation examples, you teach your agents how to handle various scenarios, maintain consistent tone, and deliver accurate responses. This guide will show you how to create, manage, and optimize examples for maximum agent performance.What are Examples?
Examples are curated conversation snippets that demonstrate ideal agent behavior. They consist of:- User Input: The customer’s question or statement
- Agent Response: The ideal response from your agent
- Context: Metadata about the scenario (tags, categories, sentiment)
- Annotations: Notes about why this response is effective
Why Examples Matter
Consistency
Ensure uniform responses across all agents and channels
Accuracy
Reduce hallucinations and improve factual correctness
Brand Voice
Maintain your unique brand personality in every interaction
Getting Started
1
Install the SDK
2
Initialize the Client
3
Create Your First Example