Developers + APIs

Getting started with Watson Conversation in 6 simple steps

Share this post:

You’ve heard the hype about bots. You understand the opportunity, but you’re not sure if you have the right skills. You’re interested in building a bot, but you don’t know where to start. Sound familiar?

With the launch of Watson Conversation, we’ve designed a service that can allow almost anyone, even users without deep technical skills, to build a bot from scratch. Our intuitive user interface means you don’t have to write lines of code or have any machine learning background.

Best of all it’s free to get started, so what’s stopping you? Follow these six simple steps and you can build a simple bot within minutes.

  1. Head over to the Watson Conversation homepage. Here you can view sample apps, read the documentation and more. When you’re ready, click the link to visit IBM Bluemix.Picture1
  2. Here you can choose between the Free or Standard Plans for Watson Conversation. If you’re new to IBM Bluemix, you’ll need to register, but don’t worry, that’s free to get started too.Picture2
  3. Next you need to name your service and click “Create”. You can launch the tooling from here and create and name your Workspace.Picture3
  4. When you get into the tooling interface, start by defining some “Intents”. An intent is the purpose or goal of a user’s input. For example, the intent of a question like “Will it rain today” might be #weather_forecast.Picture4
  5. Defining “Entities” is that part of the user’s input that can be extracted to better answer their question. In our previous example, “today” is an example of an entity called @time.Picture5
  6. And once you’ve identified a user’s questions correctly using intents and entities, use the Dialog builder to answer the question.Picture6

Pretty simple, right? Try Watson Conversation for yourself, and build your very own Bot in no time.

Free trial
Try Watson Conversation for free with a Bluemix account.

Add Comment

Leave a Reply

Your email address will not be published.Required fields are marked *


Yes, Watson gives many interesting possibilities to improve common life


    Lisa Kay Davis

    Couldn’t agree more! Thanks for stopping by.


James Taylor

To help get started with new Conversation workspaces, I’m trying to collect a few useful resources in a github repository ->

There is already a basic workspace available with some basic pre-canned intents and a starter dialog node. If you’re interested in trying it out, import the workspace instead of creating a new one in step 3. The import icon is just next to the “Create” button.


    Lisa Kay Davis

    Thanks, James!

More Developers + APIs Stories
October 29, 2016

A quick deep learning tutorial

If you ask 10 experts for a definition of deep learning, you will probably get 10 correct answers. Even though businesses of all sizes are already using deep learning to transform real-time data analysis, it can still be hard to explain and understand. Even if you haven’t recognized it, you’ve benefited from deep learning. We […]

Continue reading

June 2, 2017

IBM engineer Rama Akkiraju featured on list of top 20+ leading women in AI research

Very few earn the title of “Distinguished Engineer and Master Inventor” at IBM, but Rama Akkiraju’s contributions warrant the distinction. Akkiraju's teams are responsible for many of Watson cognitive services and leverage AI, psychology, sociology, decision theory and consumer behavior.

Continue reading

May 17, 2016

The most popular trends in cognitive computing

With over 500 companies developing cognitive systems, we’re seeing patterns emerge around the creation of cognitive systems at the business unit, business process, and application levels.  By selecting a subset of these companies to compare, we can see a few of the leading business units and processes that are going cognitive.  We also discover how […]

Continue reading