[null,null,["上次更新時間：2025-07-26 (世界標準時間)。"],[[["\u003cp\u003eActions Builder offers a visual workflow and faster prototyping for building Conversational Actions.\u003c/p\u003e\n"],["\u003cp\u003eMigrating Dialogflow projects to Actions Builder provides benefits like improved tooling, better conversation design integration, and easier localization.\u003c/p\u003e\n"],["\u003cp\u003eActions Builder enhances conversation implementation with intent reusability, improved visualization of conversation flow, and customizable prompts.\u003c/p\u003e\n"],["\u003cp\u003eBuilt-in conversation design best practices in Actions Builder include customizable \u003ccode\u003eNO_MATCH\u003c/code\u003e and \u003ccode\u003eNO_INPUT\u003c/code\u003e handlers for better error handling.\u003c/p\u003e\n"],["\u003cp\u003eActions Builder leverages scenes and transitions for managing conversation flow, replacing Dialogflow's context mechanism.\u003c/p\u003e\n"]]],["Actions Builder, a web-based IDE, streamlines Conversational Action development for Google Assistant. It features a visual, state-based workflow, faster prototyping, and a single interface for building, analyzing, and debugging. Key actions include transitioning between scenes using conditional logic and intent matching, allowing intent reusability with independent webhooks. Customizable prompts, managed through a queue, enable scenario-based responses. It includes `NO_MATCH` and `NO_INPUT` global intents to improve conversation error handling and customize prompts in each scene.\n"],null,["# Dialogflow to Actions Builder migration tool\n\nActions Builder is the best way to build for Google Assistant, as it helps you build Conversational Actions in a simplified and streamlined manner. Actions Builder is a web based IDE that is integrated into the Actions console, and provides the following features:\n\n- Visual workflow and state-based way to control your Action's conversations.\n- Faster prototyping and reduced latency.\n- Single interface for building, analyzing, and debugging your Conversational Actions.\n\nIf you have a Conversational Action you built with Dialogflow, you can choose [migrate your project to Actions Builder](/assistant/conversational/project-migration) within the Actions console.\n| **Note:** Migrating your Dialogflow project to Actions Builder is optional.\n\nReasons to migrate\n------------------\n\nWhile there's no requirement for migrating your Dialogflow agent, and your Action will continue to function for Google Assistant devices, there are benefits to using Actions Builder and the Actions SDK.\n\n- Improved tooling with the Actions SDK and CLI\n\n - The Actions SDK and CLI enable you to build complex projects and easily collaborate with your teams. Conversation designers can first build the conversation flow in Actions Builder. Developers can then download the project into a file-based structure and continue building functionality using their favorite development tools and version control systems. By pushing the project back to Actions Builder, other teammates can continue to build, test, and deploy the Action.\n- Better integration with conversation design best practices\n\n - Customization of fallback intents within each scene allows you to provide no-input and no-match responses at any point in the conversation.\n - Easy collaboration between designers and developers due to the graphical, state-based method of building a conversational experience.\n- Easier localization\n\n - All localizable content for intents, scenes, and types (like training phrases, prompts, and type synonyms) can be edited on one page.\n\nConversational implementation improvements\n------------------------------------------\n\nActions Builder brings a lot of improvements to Actions console and simplifies the development processes. This section describes how Actions Builder streamlines and simplifies the process of developing your Action.\n\n### Intent reusability\n\nIn Dialogflow, webhook logic is tied to intents, which means intents cannot be reused with other webhooks. If you want to use the same training phrases, but have different webhook logic, you have to create additional intents that refer to different handler names for each webhook logic case.\n\nIn Actions Builder, an intent includes training phrases and entities, but the webhook is independent. This approach means you can use different webhook handlers for the same intent, giving you more flexibility.\n\n### Improved visualization of conversation flow\n\nIn Dialogflow, [contexts](https://cloud.google.com/dialogflow/docs/contexts-input-output) indicate what intents are more likely to match, at a certain point in the conversation.\n\nInstead of contexts, Actions Builder uses [*scenes*](/assistant/conversational/scenes) to handle which intents are accessible in different parts of the conversation\n\nWhen a user enters a scene, [*transitions*](/assistant/conversational/scenes#transition) define conversational paths the user can take. Transitions can be based on conditional logic, as well as custom or system intent matching.\n\nBuilder's UI makes it easy to understand how transitions connect scenes. In Figure 1, the scene `guess_game` transitions to the `suggested_new_game` scene (1). You can also see the two accessible intents within the scene: `generic_no` and `generic_yes`. Depending on which intent gets matched, the `suggested_new_game` scene transitions to either the `show_menu` or `routing_game` scene (2).\n**Figure 1.** Graphical view of a scene, with the scene's transition (1) and intent handling (2).\n\n### Customizable prompts based on scenarios\n\nIn Dialogflow, you can send a simple response in the webhook or define a static response in the Dialogflow console.\n\nActions Builder introduces the concept of a [prompt queue](/assistant/conversational/prompts). You can define prompts in multiple sections of a scene, as well as in your webhook. All prompts are added to the prompt queue, merged to one response, and delivered to the user. This approach allows you to piece together responses based on what users have said or done, and not just based on the intent they matched.\n\nFor example, if prompts are defined in a scene *and* the webhook, the webhook prompt is added to the prompt queue first, and the scene prompt is added second.\n\nThe following list outlines where you can define prompts in Actions Builder, and the order they're added to the prompt queue:\n\n1. On enter\n2. Conditions\n3. Slot filling\n4. Scenes\n\n| **Note:** Webhooks calls can be enabled everywhere prompts can be defined within scenes. In all cases, when both scene prompts and webhook prompts are provided, the webhook prompt is added to the queue before the scene prompt.\n\n### Built-in conversation design best practices\n\nWhen a Dialogflow project is set up, a global fallback intent is automatically generated, just like the default welcome intent. The default fallback intent gets matched when a user says something that can't be matched to existing intents or when there is no user input.\n\nIn order to handle errors gracefully, follow up intents need to be added to the fallback intent for each conversational turn.\n\nIn Actions Builder, two separate global intents are automatically included in new projects: `NO_MATCH` and `NO_INPUT`.\n\nWhen the Assistant NLU matches the `NO_MATCH` or `NO_INPUT` system intent, the respective default or customized prompt is sent to the user. Once `NO_MATCH` or `NO_INPUT` is matched three times, the respective final message is sent to the user and the Assistant ends the conversation with your Action.\n\nYou can add three `NO_MATCH` and `NO_INPUT` handlers to each scene. This feature allows for customizable prompts for specific error handling, instead of a general fallback caused by no match or no input from the user.\n**Figure 2.** Three `NO_MATCH` intent handlers assigned to a single scene."]]
