Agent Builder console overview

Preview

This product or feature is subject to the "Pre-GA Offerings Terms" in the General Service Terms section of the Service Specific Terms. Pre-GA products and features are available "as is" and might have limited support. For more information, see the launch stage descriptions.

Note: The Agent Builder console still refers to playbooks as agents. This will be updated to playbook soon in the console.

This guide provides an overview of the Agent Builder console.

Introduction videos

Introduction

Getting Started Part 1 - Introduction

Getting Started Part 2 - Tools

Getting Started Part 3 - Data Stores

Getting Started Part 4 - Personalization and Examples

Left menu navigation

The Dialogflow user interface has the following left navigation menu items:

Name	Description
Playbooks	Used to create and edit playbooks for your agent.
Tools	Tools are used to connect to APIs or data stores.
Test cases	List and run test cases created with the simulator.
Conversation history	Provides the conversation history for all interactions with the agent.
Integrations	Integrate with other conversation platforms.
Agent settings	Change settings such as agent name, location, models, and logging.
Prebuilt playbooks	Example playbooks for popular domains.

Create an agent

To create an agent:

1. If you have not already, follow the Conversational Agents (Dialogflow CX) setup instructions.

2. Go to the Agent Builder console:

   Agent Builder console

3. Select your project from the console drop-down.

4. If you have not already activated the API, read and agree to the Terms of Service, then click Continue and activate the API.

5. Click Create a New App or New App.

6. Select Agent.

7. Provide a name for your agent.

8. Select a region.

9. Click Create.

10. The list of playbooks for the agent is shown. Click Create to create a new playbook for the agent.

11. Provide a name.

12. Provide a goal.

13. Provide instructions.

14. Click the Examples tab, then click +Example to provide playbook examples.

15. To enable conversation history, click the settings icon on the left navigation, then Logging, Enable Conversation History.

16. To enable logging for debug purposes, click the settings icon on the left navigation, then Logging, Enable Cloud Logging.

17. To select the model, click the settings icon on the left navigation, then select the Vertex AI model.

Test cases

The existing test case feature has been enhanced to support playbooks.

A required expected test case result field has been added, which provides a list of actions in the form of playbook examples. The test case verifies that the actions were performed as expected.

When viewing a playbook or playbook version, you can click the Test cases tab above the playbook data to see test case results and to execute a test case on demand.

You can also compare test case results for different versions of a playbook. Select a test case, then click Compare.

To see all test cases for the playbook, click Test cases in the left navigation.

Conversation history

The existing conversation history feature has been enhanced to support playbooks.

Information has been added for tool execution, playbook invocation, and flow invocation from a playbook.

Playbook versions

You can save playbook versions, which are immutable snapshots of playbooks.

To save a playbook version:

1. Load the playbook in the console.
2. Click Version history.
3. Click Create version.
4. Provide a version name and click Save.

To view version history:

1. Load the playbook in the console.
2. Click Version history.
3. Click View version history.
4. The version history panel opens on the right side. You can click each version to see its content.