Overview

​

Introduction

Thoughtly’s Agent Builder was developed as the fist-of-its-kind no-code interface for building Voice Agents. Before, building a Voice Agent required a team of developers, and no-code tools were limited to simple chatbots that required advanced technical prompting.

In this guide, we’ll show you how the Thoughtly Agent Builder works, and how you can use it to build your own Voice Agents in minutes.

​

Creating a New Agent

Start by heading to the Agents page in the Thoughtly dashboard. This is where you’ll find all of your Voice Agents, and where you can create new ones. Click the Create button to get started.

Next, you’ll be prompted to give your Agent a name and description. This is how you’ll internally identify your Agent in the platform, so make sure to choose a name that makes sense to you.

Creating a new Voice Agent on Thoughtly

You can choose whether to start with a blank slate, import a script, or use a template. For this example, we’ll start with a blank slate.

​

The Agent Builder

The Agent Builder is where you’ll spend most of your time building your Voice Agent. It’s a visual interface that allows you to create a conversation flow, add nodes, and connect them together.

The Thoughtly Agent Builder

The Thoughtly Agent Builder is based on the logic of a decision tree (also referred to as a flowchart). Each Node represents a step in the conversation, and you can connect them together to create your Voice Agent’s flow.

When the conversation begins, the Agent will start at the Start Node. From there, it will move to the next node based on the user’s input and the logic you’ve defined using Outcomes.

​

Why a decision tree?

A decision tree is a simple and intuitive way to represent a conversation. It’s easy to understand and visualize, but also lends itself well to triggering unique actions at different points in the coversation.

Since you can specifically instruct your Voice Agent for every possible scenario, you can do things like small talk with the caller while waiting for a human agent, transfer a call under certain conditions, and use variables output by an integration to refer to data from external systems in real-time.

In Voice Agent development, a decision tree is by far the most powerful, intuitive, and flexible way to build a conversation. Without it, you’d be limited to simple chatbots that can’t handle complex scenarios.

​

Configure your Voice Agent

Now that you have a blank canvas to build your Voice Agent, let’s start by configuring the Agent’s settings.