Xavier Portilla Edo

Creating bots with Dialogflow CX

Stop writing static chatbot responses. Learn to integrate generative AI into Dialogflow CX for truly dynamic, human-like conversations.

Creating bots with Dialogflow CX
#1about 2 minutes

What is Dialogflow CX and its state machine approach

Dialogflow CX uses a state machine approach with visual flows to simplify the management of complex conversational states.

#2about 2 minutes

Organizing conversations with flows and pages

Structure complex assistants using flows for high-level features and pages for individual states to create reusable conversational components.

#3about 3 minutes

How NLU works with intents and entities

Natural Language Understanding (NLU) works by matching user utterances to defined intents and extracting key parameters as entities.

#4about 1 minute

The four-step NLU design and training process

Follow the iterative lifecycle of designing, building, training, and evaluating the NLU model to improve your assistant's accuracy.

#5about 3 minutes

Understanding the end-to-end system architecture

The system architecture involves a client application calling the Dialogflow CX API, which processes the state and can trigger external webhooks.

#6about 2 minutes

Building a serverless backend on Google Cloud

A recommended backend uses Google Cloud Functions for serverless webhooks, Cloud Storage for assets, and Firebase for a persistent database.

#7about 2 minutes

Using client SDKs and the development lifecycle

Use the available client SDKs in languages like Python and JavaScript to programmatically manage agents as part of a structured development workflow.

#8about 2 minutes

Testing your agent in the console and with automated tests

Validate your assistant using the built-in test agent for manual checks and save interactions to create automated test cases for CI/CD.

#9about 3 minutes

Integrating with built-in and custom platforms

Connect your bot using plug-and-play integrations like Facebook Messenger or build a man-in-the-middle service for custom channels like Telegram.

#10about 4 minutes

A live demo of the Dialogflow CX console

This walkthrough of the user interface shows how to navigate flows, pages, routes, intents, and entity types to build a bot.

#11about 2 minutes

Managing resources with a custom CLI tool

A community-built command-line interface allows developers to perform CRUD operations and test Dialogflow CX agents from the terminal.

#12about 3 minutes

Validating NLU models with an automated profiler

The CLI's NLU profiler uses YAML files to create and run automated test suites for validating intent and entity matching.

#13about 4 minutes

Integrating generative AI for dynamic responses

Use webhooks to call large language models like Google's PaLM or Vertex AI to generate more natural and varied bot responses.

#14about 4 minutes

Comparing Dialogflow CX on advantages and security

Dialogflow CX offers an easier development experience than competitors while leveraging the security and compliance of the Google Cloud Platform.

#15about 4 minutes

Strategies for multilingual bots and migrating from Dialogflow ES

Create separate agents for languages with very different interaction patterns and use official tools to help migrate from Dialogflow ES.

#16about 10 minutes

Practical applications, integrations, and adoption strategies

Connect to external systems like CRMs via the API and justify bot development to leadership by presenting data on time saved.

Related jobs
Jobs that call for the skills explored in this talk.

Matching moments

Building a custom voice AI with WebRTC and Google APIs
00:17 MIN

Building a custom voice AI with WebRTC and Google APIs

Raise your voice!

Developing the bot's technical and conversational framework
18:51 MIN

Developing the bot's technical and conversational framework

Design as an algorithm, not as a feature

The shift from developer experience to AI experience
15:53 MIN

The shift from developer experience to AI experience

Postgres in the Age of AI (and Devin)

GenAI applications and emerging professional roles
18:03 MIN

GenAI applications and emerging professional roles

Enter the Brave New World of GenAI with Vector Search

Practical examples of using AI in daily life
01:32 MIN

Practical examples of using AI in daily life

Collaborative Intelligence: The Human & AI Partnership

Building a dialogue skill with intents, entities, and nodes
13:12 MIN

Building a dialogue skill with intents, entities, and nodes

Integrate your Cognitive Assistant with 3rd-party DBs and software

Exploring the future of AI beyond simple code generation
38:07 MIN

Exploring the future of AI beyond simple code generation

Innovating Developer Tools with AI: Insights from GitHub Next

Live demo of building a chat with your data app
38:46 MIN

Live demo of building a chat with your data app

Inside the AI Revolution: How Microsoft is Empowering the World to Achieve More

Featured Partners

Related Videos

See all videos
Building Products in the era of GenAI59:39

Building Products in the era of GenAI

Julian Joseph

Multimodal Generative AI Demystified56:55

Multimodal Generative AI Demystified

Ekaterina Sirazitdinova

From Syntax to Singularity: AI’s Impact on Developer Roles58:06

From Syntax to Singularity: AI’s Impact on Developer Roles

Anna Fritsch-Weninger

Creating Industry ready solutions with LLM Models58:00

Creating Industry ready solutions with LLM Models

Vijay Krishan Gupta & Gauravdeep Singh Lotey

Multilingual NLP pipeline up and running from scratch52:37

Multilingual NLP pipeline up and running from scratch

Kateryna Hrytsaienko

ChatGPT: Create a Presentation!30:24

ChatGPT: Create a Presentation!

Markus Walker

MLOps and AI Driven Development49:57

MLOps and AI Driven Development

Natalie Pistunovich

Raise your voice!30:59

Raise your voice!

Lee Boonstra

From learning to earning

Jobs that call for the skills explored in this talk.