AI Agent Guide: Basics
This guide explains how to configure and refine an AI agent on the Flametree portal using a production-oriented approach. Each section explains what configuration controls, why it matters, and how to apply best practices. By the end of this guide, you will be able to structure configurations, evaluate conversations, and iteratively improve agent performance.
While the Quick Start tutorial helps you launch your first AI agent, this guide focuses on designing stable and predictable agent behavior.
An AI agent in Flametree is configured through several key areas that together define how it behaves during conversations:
- Identity — defines agent's role, expertise and responsibilities.
- Style and communication — defines how the agent presents itself to customers. Determines tone of voice, communication style, and supported languages.
- Task — describes the agent’s primary objective and operational boundaries.
- Workflow — controls conversation logic, available tools, and interaction flow.
- Knowledge Sources — include Fast Access Knowledge Base (on the screenshot below) and external Knowledge Bases used to answer customer questions.
- Conversation Results — specify which data the agent collects during interactions for follow-up and reporting.
- Testing and Analytics — provide session history, logs, and performance insights used to evaluate and refine agent behavior.
Each of the following sections focuses on configuring one of these areas.
