Building Conversational AI Applications with Vertex AI Conversation and Dialogflow CX

Learn to create advanced conversational AI experiences using Google Cloud's latest Generative AI features in a comprehensive technical session led by Google Cloud Champion Innovator Xavier Portilla Edo and Developer Advocate Alessia Sacchi. Master the integration of traditional agent design techniques with large language models (LLMs) through Vertex AI Conversation and Dialogflow CX. Explore practical implementations including data store agents for retrieval-augmented generation, generative fallback mechanisms for handling unexpected user inputs, and native LLM integration through generators. Watch live demonstrations showcasing real-world applications and discover best practices for implementing conversational AI solutions. Access hands-on resources including the Dialogflow CX CLI tool and step-by-step codelabs for building generative chat applications, implementing fallback mechanisms, and utilizing generators with data stores. Perfect for developers and businesses looking to create sophisticated, personalized conversational interfaces for both employee and customer interactions.

Syllabus

High level overview of natural language understanding for Conversational AI
Generative AI applied to Conversational AI
Common user needs, use cases, and capabilities
Solution: Data store agent uses retrieval-augmented generation to generate responses grounded to the content of your knowledge repository
Solution: Generative fallback use LLMs to generate virtual agent responses to handle unexpected intents and invalid parameter values
Solution: Generators allows you to make a call to an LLM natively from Dialogflow CX to do anything you would normally ask an LLM to do
Live demo
Best practices when using Generative AI with Conversational AI
Resources and what's next
Q&A