Creating Agents

Symphona Converse’s Agent Editor allows you to easily create automated Agents that work over chat and voice channels.

In the following sections, we are going step-by-step on how to create an Agent from scratch. Let’s dive in!

Generative Agents

Overview

Generative Agents in Symphona Converse empower AI-driven service by automating chat and voice interactions, providing quick, accurate responses based on company documentation and procedures. These Agents maintain focused conversations, handle tasks like querying knowledge bases, transferring to human Agents, and triggering automated processes, all aimed at enhancing efficiency and improving service quality.

You can test out an example Generative Agent by interacting with our AI Consultant in the bottom right corner of this web page. Configured to use this documentation portal as a Knowledge Base, this Agent is designed to provide you with support on how to use Symphona and help generate conceptual automation solutions.

Tutorial Video

Follow along with us as we create a new Generative Agent, design a Chat Widget, and link it to the Agent, ready to be embedded on an existing web page or connected to a phone number.

Creating Generative Agent

Creating a generative Agent in Symphona Converse involves several steps - let’s go through each of them:

1. Log In and Access Agent Manager: First, log in to Symphona. Once you're in, you'll land on the My Summary page. To start creating your Agent, navigate to Converse, then click on Agent Manager. This takes you to the Agent Manager view, where you'd typically see any Agents you have already set up. Since we're starting from scratch, let's move on by clicking Create New Agent on the top right.

2. Set Up Basic Information: Now, you'll need to fill out some basic details for your new Agent. Enter an Agent name. For the Agent type, select "Generative." You can also add tags or a description for better organization. Once ready, click Confirm to proceed.
3. Entering the Agent Editor: After confirming, you’ll be directed to the editor. Here, you’ll define what your Agent should do, also known as setting up its objectives. Think of these objectives as the various tasks your Agent can handle in conversations. For instance, an objective might be "search for answer," which allows the Agent to query a knowledge base for information.

4. Define Actions for Objectives: With the objectives in place, you need to specify actions by clicking Add Action. Actions define what the Agent does to achieve an objective. You can add one or more actions to an objective. For example, if your objective is "search for answer," you should set the action to "Query Knowledge Base." All possible actions include:
1. Create Service Ticket: Creates a service ticket that will be sent to Serve.
2. Query Knowledge Base: Searches for an answer to a question within a created Knowledge Base. You can learn more about how to configure Knowledge Bases here.
3. Execute Process: Executes an existing Symphona Flow Process.

Additional help for executing processes can be found here.

4. Invoke REST API: Executes a REST API (commonly used to get data from or send data to an existing digital platform).
5. Transfer to Agent: Transfers the conversation to another automated Agent (commonly used to create a modular Agent support structure).
6. Transfer to Human: Transfers the conversation to a human where support is provided in the Live Chat view (for text-based conversations) or to the transfer phone number (for voice-based conversations).

5. Fine-Tuning: Customize finer details such as greeting messages or specific behavioral guidelines. For instance, specify topics to avoid or how the Agent should phrase responses.
1. Greeting: in the Greeting section, you can define how your Agent initially greets the user. You can toggle whether the Agent says a greeting or not, and provide guidance on how the Agent should greet the user. Since the chatbot will generate organic messages, being specific with the guidance will help if you want the chatbot to speak in a certain way.

2. Topics to Avoid: In the Topics to Avoid section, you can specify what topics the Agent should not discuss. Topics can be defined using a single word (e.g. politics, religion, etc.) or multiple sentences. For the best results, write only one topic per field.

6. Model Configurations: In the Model Configurations section, you can configure the AI model you want to power the Agent and fine-tune responses. You can configure the following:
1. Model: Choose the AI LLM model you want to use.

For most users, we recommend starting with a general-purpose model, as they performs reliably across a wide range of conversations. However, if you notice that the complexity of your interactions is causing performance issues, consider trying more advanced models. See a list of all of our models here.

2. Max Response Length: The maximum response length based on the number of tokens. Note that 1 token corresponds to roughly 4 characters.
3. Response Variability (Temperature): The response variability (or temperature) of your Agent. Higher values introduce some degrees of unpredictability and creativity, while lower values keep Agent behavior predictable. We recommend keeping variability low if you want Agent responses to be fairly standardized and consistent.


7. Behavior Configurations: In the Behavior Configurations section, you can give the agent response directions and features that tailor it for your use cases. You can configure the following:

4. Response Directions: Give instructions to your Agent on their purpose and how they should speak. We generally recommend that Agents speak politely and formally with some guidelines on the structure of expected responses.

For additional information and detailed explanations on how to fully utilize our AI, see our AI Prompting section here.

5. Enable Multi-Lingual Support: Whether to automatically translate the received messages from their original language to English. This is useful to enable support in any major language.
6. Confirm Memory Values Before Using: Prompts the agent to check with the user before utilizing any auto-identified conversation memory values as Action parameters.
7. Collect Feedback: Whether to collect feedback data on how the agent interacts with the user.
8. Include References in Response: Whether to include references in response. This is useful for knowledge centralization Agents where you want sources for the information they recalled.
9. Validate Response Before Sending: Agent will double-check its response for accuracy, reducing the chance of hallucinations but increasing response time.

7. Deploy Your Agent: Once you’re satisfied with your Agent’s configuration, click Deploy. You can now link this Agent to various channels like chat widgets or phone lines. To create a chat widget, you can review the article here.

And there you have it! You’ve just created a generative Agent that can handle various tasks and enhance service quality for your organization.

• Creating Agents
• Generative Agents
• Overview
• Tutorial Video
• Creating Generative Agent