Google Cloud Dialogflow CX integration overview

AI-generated summary

Genesys Cloud integrates with Google Cloud Dialogflow CX to enable natural language understanding and conversational bot interactions within Architect IVR flows, allowing customers to communicate naturally while companies better understand intent and route interactions more efficiently to skilled agents. The integration leverages Google machine learning to recognize customer intent and extract entities such as dates, times, and numbers from open-ended questions, supporting omnichannel customer service delivery through automated intent recognition and intelligent routing capabilities. Key technical requirements include setting correct language locale with language and region code combinations in the Dialogflow CX console for multilingual support, creating multiple agent versions and environments, and enabling the barge-in feature for customer interruptions. Configuration best practices recommend an add-only approach when managing intents and languages; intent removal requires exporting the current agent configuration into a new Dialogflow CX agent and updating the Architect flow reference. Administrators can configure any available Architect text-to-speech provider to override the bot's native engine and maintain consistent voice profiles across flows and bot executions. The integration supports PCI DSS compliance for secure call flows and requires outbound network traffic from Edge systems to regional DNS entries on TCP Port 443. Typical use cases involve customers initiating interactions through Architect IVR, where Dialogflow CX interprets intent, executes tasks such as order placement or delivery status retrieval, and routes unresolved requests to human agents. The system supports seamless handoff during extended wait times, outside business hours, or when intent cannot be established, with customers able to request agent connection or end the interaction after task completion. Notable limitations include lack of support for BYOC Premises and premises-based Edge (LDM) deployments, and HTTP Proxy configuration on Edge systems is incompatible with this integration. Pricing is calculated monthly by Google based on edition, pricing plan, number of requests, audio processing duration, and total interaction duration. Customers using unsupported alternative architectures do so at their own discretion and are ineligible for Genesys support.

Companies use Google Cloud Dialogflow CX to design conversational interface bots, like the bots which power Google Assistant. This integration allows Genesys Cloud to call Google Dialogflow CX bot actions in Architect call and message flows.

Google Cloud Dialogflow CX bots use Google machine learning. This machine learning implements natural language understanding (NLU) to recognize a customer’s intent and then extracts prebuilt entities such as time, date, and numbers. With the evolving functionality of artificial intelligence tools, conversational interactions with computers are now mainstream. Contact centers are a natural progression into this world of virtual assistants.

When a customer can speak naturally, your company can better understand the customer’s intent and more quickly route the interaction to a highly skilled agent. The Google Cloud Dialogflow CX integration within Genesys Cloud enables customers to use NLU within inbound synchronized customer interaction flows.

Notes:

This feature is PCI DSS compliant. You can use this integration in secure call flows. For more information, see PCI DSS compliance.
Administrators can use any text-to-speech provider that is available in Architect flows for use with their installed bot integrations. The default text-to-speech provider for the Architect flow overrides the default text-to-speech engine provided natively by the bot in spoken text, providing a consistent text-to-speech voice profile across the Architect flow and the bots executed in that flow. For more information, see About text-to-speech (TTS) integrations.
Google Cloud Dialogflow CX is not supported with BYOC Premises.
Google Cloud Dialogflow CX is not supported with premises-based Edge (LDM).
Customers who choose to use alternative, non-supported architectures, whether during migration or as part of the initial configuration, may do so at their own discretion. However, such configurations are not supported by Genesys Cloud and are therefore not eligible for Genesys support.

Before you begin, review Google Cloud’s Dialogflow CX documentation.

Set the correct Bot language locale in the Google Cloud Dialogflow CX console

Make sure to set the correct language locale for your bot in the Google Cloud Dialogflow CX console. Architect flows do not run in language codes only, such as “en.” Add the locale to the bot’s language. The locale includes the language and region code combination. You can also add multiple languages to make your bots multilingual. For more information, see Languages in Agent Settings in the Google Cloud Dialogflow CX documentation.

Note: To display the Add locale option, make sure to hover over the existing listed language.

Work with enabled environments for the Google Cloud Dialogflow CX bot

Best practice recommends, when you enable environments for a Google Cloud Dialogflow bot, that you do not remove intents or supported languages for the bot.

Implications of removing intents for a Google Cloud Dialogflow CX agent

If you choose an environment in the Call Dialogflow bot action and remove intents from the draft version of the agent, then the flow takes the failure path. This action occurs because the flow cannot reach the deleted intents. Therefore, even though the agent fulfills the intent, the flow takes the failure path.

To ensure that the Draft environment always includes the entire set of intents in the published environment, only add intents during the life cycle of an agent throughout various environments. Do not remove them. You can also export the agent configuration into a new agent and then set the intents as appropriate. Then, update the Architect flow to reference the new agent.

For example, if you treat Dialogflow CX agents in an add-only manner but want to remove an intent, create a new agent. Export the current agent’s configuration into a new Google Cloud Dialogflow CX agent, then remove intents and slots as appropriate. Then, reference the new agent from the Architect flow instead. Going forward, follow the add-only approach described previously.

Create versions and environments in the Google Cloud Dialogflow CX console

You can create multiple versions of your Google Cloud Dialogflow CX agents and then enable them in different environments. For more information, see Versions and environments in the Google Cloud Dialogflow CX documentation.

Enable barge-in in the Google Cloud Dialogflow CX console

When you build an agent in the Google Cloud Dialogflow CX console, you can enable barge-in to allow customers to interrupt a bot’s response. For more information, see Speech and IVR settings in the Google Cloud Dialogflow CX documentation.

Understand Google Cloud Dialogflow CX pricing

Google prices Dialogflow CX monthly based on the edition, pricing plan, number of requests, the total duration of audio processed, and the total duration of the interaction. For more information about Google Cloud Dialogflow CX pricing, see the Google Cloud Dialogflow pricing page.

Example use case

When a customer interacts through Architect IVR, the Dialogflow CX bot begins. The system asks the customer an open question, such as “How may I help?”.

After the customer responds, Dialogflow CX attempts to interpret the intent of the request and then decides the next step. For example, if the customer replies, “I want to place an order for delivery,” then Dialogflow CX prompts the customer for the order and returns delivery status.

If Dialogflow CX cannot establish or understand the customer’s intent, the system routes the interaction to an agent.

After the task ends, Dialogflow CX asks if the customer needs any additional help. The customer can ask another question, request to speak to an employee, or indicate that they need no further assistance. If the customer needs no further assistance, the interaction ends.

If the customer wants to connect to an agent but faces a long wait time or the request is outside normal business hours, then the IVR routes the interaction appropriately.

For more information, see About the Google Cloud Dialogflow CX integration.

[NEXT] Was this article helpful?

Get user feedback about articles.