We’ve changed our name! API.AI is now Dialogflow. Learn more here.

Introducing two beta releases: Dialogflow API V2 and new Enterprise Edition

November 16, 2017

When we joined Google, our vision was to use Google’s infrastructure and resources to accelerate improvements to our platform, making the best technologies in AI and machine learning available to our developer community.

Today, we’re launching two new important updates– in beta–that bring us even closer to that day-one vision:

Dialogflow API V2 BETA

Dialogflow API V2 BETA is the next iteration of our developer API adding new features and capabilities. API V2’s updates include:

  • Google Cloud Speech integration, allowing developers to send audio directly to Dialogflow for speech recognition and natural language understanding
  • Importing, exporting and restoring agents through API calls, for improved integration with developers’ change management processes
  • Support for gRPC, an RPC framework offering improved performance, scalability and integration

We will continue support for our existing API V1, while any future features and improvements will be added to API V2. If you wish to try out the new API V2 BETA, please review our FAQ page and follow these instructions.

Dialogflow Enterprise Edition BETA

Many of our clients have asked for enterprise support, and today we’re excited to be launching Dialogflow Enterprise Edition BETA. Dialogflow Enterprise Edition BETA combines our new API V2 with Google Cloud Platform’s enterprise-grade compliance and customer support. Head over to the Google Cloud Platform to learn more.

What do today’s announcements mean for me?

In short, no action is necessary for your existing agents – they will continue working as before. We recommend that most users continue development with API V1 unless they would like to evaluate API V2 BETA or require features only available in API V2 BETA. Using Dialogflow Enterprise Edition BETA requires the use of API V2 BETA.

As we improve API V2 tooling in the coming months, we’ll provide additional resources for migrating your existing agents from V1 to V2.

If you have more questions about trying API V2, don’t forget to check out our FAQ page.

Posted by Artem Goncharuk, Engineering Lead





7 new prebuilt agents to simplify your development process

November 1, 2017

Back in March 2017, we launched 33 prebuilt agents to help you simplify your agent development process. Prebuilt agents are templatized agents our team has built for a variety of use cases and verticals that you can download to your account and fully customize. Today, we’re releasing 7 more prebuilt agents in English to make development easier and faster:

New use cases
  • Jokes
  • Events Search
  • Dining Out
  • Local Services
  • Reminders
New verticals
  • Coffee Shop
  • Tourism

Let’s take a look at some examples of how each of them can be used:

Coffee Shop

User: I'd like a coffee to go.
User: I'm hungry.
User: I would like to order a gift card with $50 on it.

Jokes

User: Make me laugh.
User: Tell me a witty joke.
User: Another one.

Events Search

User: Art exhibitions in Japan?
User: Where to go for a date?
User: How can I kill time nearby?

Dining Out

User: Find a cheap and top rated place to eat in NYC.
User: Show only open ones.
User: How about Queens?

Local Services

User: I'm looking for a beauty salon with Wi-Fi.
User: How about spa?
User: Filter for closest.

Tourism

User: Where should I stay for 5 nights in Barcelona?
User: How about Madrid?
User: Show me the best sights in Rome that have parking and good reviews.

Reminders

User: Set a reminder for 9am tomorrow: Yoga.
User: For Monday also.
User: Reschedule my 11am reminder to 8am.

Head over to your developer console and give these a try! And if you need support, find us over on StackOverflow or contact us here.

Posted by Mary Chen, Product Marketing Manager





Introducing Dialogflow, the new name for API.AI

October 10, 2017

When we started API.AI, our goal was to provide developers like you with an API to add natural language processing capabilities to your applications, services and devices. We’ve worked hard towards that goal and accomplished a lot partnering with all of you. But as we’ve taken a look at our work over the past year and where we’re heading, from new features like our Analytics tool to the 33 prebuilt agents, we realized that we were doing so much more than just providing an API. So with that, we’d like to introduce Dialogflow – the new name for API.AI.

Dialogflow

Our new name doesn’t change the work we’re doing with you or our mission. Our mission continues to be that Dialogflow is your end-to-end platform for building great conversational experiences and our team will help you share what you’ve built with millions of users. In fact, here are 2 new features we’ve just launched to help you build those great experiences:

  1. In-line code editor: you can now write fulfillment logic, test, and implement a functional webhook directly in the console.
  2. Multi-lingual agent support: building for multiple languages is now easier than ever. You can now add additional languages and locales to your new or existing agent.

Thanks for being a part of API.AI – we can’t wait to see what we do together with Dialogflow. Head over to your developer console and give these new features a try. And, as always, contact us if you have any questions.

Dialogflow Team
Hi from the Dialogflow team!

Posted by Ilya Gelfenbeyn, Lead Product Manager, on behalf of the entire Dialogflow team





Introducing a new import feature for Alexa skills

August 10, 2017

We want to make it easy for you to share the conversational apps you build with more users, across more platforms. Starting today, you can import your Alexa skills into API.AI and make them available to other platforms and surfaces such as Slack, Facebook, and the Google Assistant, as well as websites and native apps. You’ll be able to reach new users, while managing a consistent cross-platform experience all in one place.

How it works

Import your skill as an API.AI agent using these instructions. API.AI expands the training data from the skill to create corresponding intents and entities for your agent. You can then customize your agent to work with other platforms. Here’s a quick start guide to help you with this process.

More platforms = more training and improvement opportunities

Once your agent is ready, you can launch it as a conversational app with any of our 32 one-click integration and platform SDK options. By launching to other platforms, you’ll get more user and traffic analytics. These can help you train your agent and improve the user experience on all your integrations, including your original Alexa skill if you export it back.

We hope the new import feature makes it easy for you to take something you’ve already built to reach new and existing users in more ways. And, by developing conversations in one place, also a more consistent and better cross-platform user experience for your product!

Give the importer a try and let us know if you have questions in the API.AI forums or with our Stack Overflow tag.

Posted by Pavel Sirotin, Solutions Consultant





2 new features: New Analytics tool and more Google Assistant surfaces

June 14, 2017

Today, we’re launching 2 major features in API.AI to help you improve your agents and reach new audiences. First, you can now track your agent’s performance with our new Analytics tool. Second, you can reach Google Assistant users across eligible Android phones and iPhones.

1. Track performance with our new Analytics tool

We’ve heard your feedback to have analytics on how your agents are performing. Our new Analytics tool lets you view data around session traffic and intent usage. We hope the new tool can help you drive improvements to your agents by identifying usage patterns, latency issues, and high- and low-performing intents. We’re working on adding more stats and functionalities so stay tuned for updates.

alt text

2. Reach more Google Assistant users across eligible Android phones and iPhones

At Google I/O today, it was announced that developers can now reach Google Assistant users on eligible Android phones and iPhones. Starting today, you can use API.AI’s Actions on Google integration to build and launch Assistant apps on these phones.

Example of a CNBC rich card on the Google Assistant

Enter your Assistant app in the Actions on Google Developer Challenge for a chance to win great prizes, including a trip to Google I/O 2018!

Check out the livestream of our Google I/O session tomorrow as we demo these new features. We look forward to seeing how you’ll utilize them. As always, let us know if you have any questions or comments.

Build on,

The API.AI team.





Next Page >