Dialogflow provides a web user interface called the Dialogflow CX Console (visit documentation, open console). You use this console to create, build, and test CX agents. The CX Console has a similar purpose as the ES Console, but the CX Console user interface is much more visual. It graphs each flow as a conversational state machine diagram, which makes complex agents easier to design and understand.
The Dialogflow CX Console is different from the Google Cloud Platform (GCP) Console (visit documentation, open console). The Dialogflow CX Console is used to manage Dialogflow CX agents, while the GCP Console is used to manage GCP-specific Dialogflow CX settings (for example, billing) and other GCP resources.
In most cases you should use the Dialogflow CX Console to build agents, but you can also use the Dialogflow CX API to build agents for advanced scenarios.
Quickstart, concept, and how-to guides take you through the steps of using the console. This guide provides a high-level summary of the console.
How the console is used
The console is used to create, build, manage, fine-tune, and test your projects and agents. With it, you can:
- Create projects.
- Create agents that contain all settings and data that define the conversational experience.
- Create flows and pages that are the building blocks for conversation control.
- Create entities to extract useful data from end-user input.
- Create intents that categorize end-user input.
- Test your agent via the simulator.
- And more ...
When you initially load the console, you must select a project. The project selector interface is used to:
- Select pre-existing projects
- Create new projects
Once you select a project, you must select an agent. The agent selector interface is used to:
- Select existing agents
- Create new agents
- Create prebuilt agents
- Export and restore agents
- Delete agents
- Configure location settings
- Filter agents by location
Once a project and agent has been selected, the agent builder loads. The builder is arranged in the following panels:
Console menu (1)
You can use this menu to switch between Dialogflow consoles.
Project and agent selection (2)
You can use these menus to change the project, agent, or currently active language for multilingual agents.
Task indicator (3)
This indicator shows the status of tasks like training.
Build and Manage tabs (4)
The Build tab contains sections for managing flows and pages. When you select a flow in the flow section, the pages contained within the flow are listed in the pages section.
The Manage tab contains resources and tools available to the agent: intents, entity types, webhooks, etc.
Graph settings (5)
These buttons provide various controls for viewing and interacting with the agent graph.
Agent settings and simulator buttons (6)
The Agent Settings button opens the agent settings panel. The Test Agent button opens the simulator panel.
The graph shows a visual representation of the selected flow, similar to a state machine diagram. Each node of the graph represents a page or flow start page. You can click a node to expand or contract it. When expanded, you can edit a nodes data.
The first node of the graph, called Start, is the start page of the flow. Connecting lines from one node to another represent possible transitions. When a transition can lead to another flow, the target flow is shown as a node.
Editing and simulator panels (8)
When editing agent content or testing the agent with the simulator, content-specific panels open on the right side of the console. These panels can be expanded to fill available console area, contracted to fill a portion of the right side of the console, or closed when you are finished.
The simulator is used to test your agent. You can have a conversation with your agent while monitoring changes in session state.
You can also use the simulator to create executable test cases.