Build hybrid conversational agents with both deterministic and generative AI functionalities. This allows you to have strict controls and use generative AI to better meet customer needs.
Support rich, intuitive customer conversations, powered by Google's leading generative AI
Ensure predictable and safe performance with deterministic tools to harness the power of generative AI
One comprehensive development platform for text and voice-based virtual agents
Create agents with a few clicks using the Conversational Agents UI
Benefits
Human-like multilingual conversations
Easily build AI agents with no code
Personalized customer interactions at scale
Bring your own CRM and data sources
Multimodal interaction with voice, text, or images
Generative responses grounded for accuracy
Key features
By combining generative AI and rules-based controls, the new Conversational Agents console enables users to rapidly build AI agents for self-service experiences, with realistic, natural-sounding inflection and expressive conversations that are grounded in both business and customer logic.
The console provides users with new evaluation capabilities to benchmark agent performance, understand single turn and multi-turn conversational metrics, and build feedback loops to help create and manage their AI agents.
To improve reliability and quality at large enterprise production scale, we also introduced observability, evaluation, and test case instrumentation to enable customers and partners to validate agent quality at scale, with tools to consistently monitor and improve their self-service experiences.
Our latest voice models provide human-sounding emotions and intonations, with steerable voice instructions and configurable pauses, pronunciation, and emotion to provide the life-like conversational experiences. 30 new voices with various tones to choose from are available now.
These quickstart reference agents allow users to get started easily with consumer commerce.
We are initially launching four prebuilt agents: flight booking, movie ticketing, shopping assistance, and appointment booking. They demonstrate various capabilities, including geolocation API use, connecting to Google products like BigQuery for data retrieval, Google Calendar for appointment booking, and rich-text formatting to build beautiful interfaces for end users.
We are making it easy to expand AI agent capabilities by introducing 30+ data retrieval connectors to augment the knowledge of your agent, and 70+ action connectors to allow your agent to take actions with or without human-in-the-loop for approvals.
Connectors include common data sources like BigQuery, Salesforce, SharePoint, Jira, ServiceNow, and more. With the new Conversational Agents connectors, customers get out-of-the-box, click-to-deploy tools that speed up time to production, provide seamless customer personalization, and quickly help realize the business impact of Conversational AI.
Customers
See how organizations are transforming their customer interactions.
Documentation
Learn how to get started with Conversational Agents (Dialogflow CX) from setting up, to building using the console, and to interacting with an agent using the API.
Review the basics of using Conversational Agents (Dialogflow CX) and an overview of the most important concepts.
Learn the basics of using Dialogflow ES with an overview of the most important concepts.
See how you can get started and running with Dialogflow ES.
Dialogflow is available in two editions. The agent type, features, pricing, and quotas vary for each edition.
Advanced agents with most innovative capabilities for large or complex use.
Standard agents for small to medium and simple to moderately complex use.
Multilingual support: Engage with your global user/customer base
30+ languages and variants supported
30+ languages and variants supported
Analytics: Gain insights into agent performance and customer engagements
Advanced performance dashboards
Data export to custom dashboards
State-based visualizations
Performance dashboards
Data export to custom dashboards
Omnichannel integration: Build once, deploy across your contact center and digital channels
Integration across digital channels, including web, mobile, messenger, and others
Advanced one-click telephony integration
Integration into popular channels, such as Google Assistant, Slack, Twitter, and others
One-click telephony integration
Prebuilt agents: Accelerate time to production with a library of agents prepared for common use cases
Nine production-ready agents for use cases across industries: Telco, retail, financial services, travel, and more
40+ template agents for building conversations for dining out, hotel booking, navigation, IoT, and more
Advanced AI: Take advantage of best machine learning models developed by Google Research
State-of-the-art BERT-based natural language understanding (NLU) models
Cutting-edge speech recognition and speech synthesis models
Standard high-quality natural language understanding (NLU) models
Cutting-edge speech recognition and speech synthesis models
Visual flow builder: Quickly see, understand, edit, and share work with interactive flow visualizations
Reduce development time by 30% with an intuitive visual builder for visual state machine
Form-based bot builder
State-based models: Switch between topics and manage complex flows with ease
Reuse intents and intuitively define transitions and data conditions
Flat data model for simple use cases
Supplemental questions: Handle deviations in conversations, then gracefully return to the main flow
Models capable of easily defining and detecting minor conversation detours
Not supported
Native IVR settings: Optimize for Contact Center AI deployments
Supports settings such as DTMF, live agent handoff, barge-in, speech timeouts
Not supported
Flow-based modules: Manage your agents easily and work on independent flows simultaneously
Supports up to 20 independent conversation flows with 40,000 intents
Shared intents and training phrases across flows
Supports up to 10 sub-agents with as many as 20,000 intents
Intents and training phrases not shared across sub-agents
Testing: Evaluate the quality of your agents to uncover bugs and prevent regressions
Advanced multi-turn simulator
Create and manage test cases for continuous evaluation
Standard simulator
Test cases not supported
End-to-end management: Take care of all your agent management needs inside Dialogflow
Flow-level versions and environments support for testing and deployment
Experiments and traffic-splitting natively supported
Basic versions/environments support
Experiments and virtual agent evaluation not supported
Speaker ID: Leverage biometric voice identification to identify and verify users
Quickly identify users with just their voice
Increase security with an extra layer of verification
Reduce user frustration by eliminating pins and passcodes
Not supported
Advanced agents with most innovative capabilities for large or complex use.
Multilingual support: Engage with your global user/customer base
30+ languages and variants supported
Analytics: Gain insights into agent performance and customer engagements
Advanced performance dashboards
Data export to custom dashboards
State-based visualizations
Omnichannel integration: Build once, deploy across your contact center and digital channels
Integration across digital channels, including web, mobile, messenger, and others
Advanced one-click telephony integration
Prebuilt agents: Accelerate time to production with a library of agents prepared for common use cases
Nine production-ready agents for use cases across industries: Telco, retail, financial services, travel, and more
Advanced AI: Take advantage of best machine learning models developed by Google Research
State-of-the-art BERT-based natural language understanding (NLU) models
Cutting-edge speech recognition and speech synthesis models
Visual flow builder: Quickly see, understand, edit, and share work with interactive flow visualizations
Reduce development time by 30% with an intuitive visual builder for visual state machine
State-based models: Switch between topics and manage complex flows with ease
Reuse intents and intuitively define transitions and data conditions
Supplemental questions: Handle deviations in conversations, then gracefully return to the main flow
Models capable of easily defining and detecting minor conversation detours
Native IVR settings: Optimize for Contact Center AI deployments
Supports settings such as DTMF, live agent handoff, barge-in, speech timeouts
Flow-based modules: Manage your agents easily and work on independent flows simultaneously
Supports up to 20 independent conversation flows with 40,000 intents
Shared intents and training phrases across flows
Testing: Evaluate the quality of your agents to uncover bugs and prevent regressions
Advanced multi-turn simulator
Create and manage test cases for continuous evaluation
End-to-end management: Take care of all your agent management needs inside Dialogflow
Flow-level versions and environments support for testing and deployment
Experiments and traffic-splitting natively supported
Speaker ID: Leverage biometric voice identification to identify and verify users
Quickly identify users with just their voice
Increase security with an extra layer of verification
Reduce user frustration by eliminating pins and passcodes
Standard agents for small to medium and simple to moderately complex use.
Multilingual support: Engage with your global user/customer base
30+ languages and variants supported
Analytics: Gain insights into agent performance and customer engagements
Performance dashboards
Data export to custom dashboards
Omnichannel integration: Build once, deploy across your contact center and digital channels
Integration into popular channels, such as Google Assistant, Slack, Twitter, and others
One-click telephony integration
Prebuilt agents: Accelerate time to production with a library of agents prepared for common use cases
40+ template agents for building conversations for dining out, hotel booking, navigation, IoT, and more
Advanced AI: Take advantage of best machine learning models developed by Google Research
Standard high-quality natural language understanding (NLU) models
Cutting-edge speech recognition and speech synthesis models
Visual flow builder: Quickly see, understand, edit, and share work with interactive flow visualizations
Form-based bot builder
State-based models: Switch between topics and manage complex flows with ease
Flat data model for simple use cases
Supplemental questions: Handle deviations in conversations, then gracefully return to the main flow
Not supported
Native IVR settings: Optimize for Contact Center AI deployments
Not supported
Flow-based modules: Manage your agents easily and work on independent flows simultaneously
Supports up to 10 sub-agents with as many as 20,000 intents
Intents and training phrases not shared across sub-agents
Testing: Evaluate the quality of your agents to uncover bugs and prevent regressions
Standard simulator
Test cases not supported
End-to-end management: Take care of all your agent management needs inside Dialogflow
Basic versions/environments support
Experiments and virtual agent evaluation not supported
Speaker ID: Leverage biometric voice identification to identify and verify users
Not supported
Pricing
Conversational Agents are priced monthly based on the edition and the number of requests made during the month.
New customers receive a $600 credit for a $0 trial of Dialogflow CX. This credit is automatically activated upon using Dialogflow CX for the first time and expires after 12 months. This is a Dialogflow-specific extension of the Google Cloud $0 trial.
Partners
Integrate Converstional Agents (Dialogflow CX) into your contact center and channels with Google Cloud CCaaS or our trusted partners.
Start building on Google Cloud with $300 in free credits and 20+ always free products.