Developers

The app developer’s guide to creating your first Watson bot

Share this post:

You’re building your first chat bot and the pressure’s on. Never fear – the Watson team is here!

We know getting started can be tough, so we’ve compiled this list of resources that will help you easily jumpstart your first conversational application built with the Watson Conversation chat bot API.

Know your goal

First thing’s first: Do you have a use case or user story established? (A use case is the sequence of action steps between a user and a system to achieve a goal. A user story is an outcome-focused description of what your user will be able to do with your application.)

According to Brian Loveys, Program Director for Watson Emerging Technologies, “In many cases, it makes sense to start small on well-defined questions you know users will ask and expand from there. Experience has told us that it’s not until you release into production do you really find out what customers are going to ask.” To this effect, it is important to ensure that your use case or user story is clearly defined to provide a framework for development, but not so broad that your app’s purpose becomes muddled.

We would advise taking the time before you begin coding to document your use case or user story, so you can refer back to it later and use it as a tool to guide your efforts.

What customer challenge are you trying to solve with a chat bot? Your answer should be clear.

What customer challenge are you trying to solve with a chat bot? Your answer should be clear.

Create your roadmap

Next, you’ll want to have a general understanding of how to create a chat bot. We liken building a bot to taking a road trip: While you may spend some extra time at a particular stop, or skip one altogether, you still want to have a plan for where you’re going and (in general) how you’re going to get there.

Featured asset #1: This guide breaks down the process into simple steps: Getting started with Watson Conversation in 6 simple steps.

convo

“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.”

Featured asset #2: This guide provides a deeper dive: Build a chat bot in 10 minutes. (You can even keep it in a browser next to your coding space and follow the process step by step.)

“What I am going to share with you is a super simple chat bot designed for customer service. When I say super simple, I mean exactly that — it doesn’t do much, but it provides an opportunity to learn the core functionality of the Conversation service with a few best practices thrown in.”

“What I am going to share with you is a super simple chat bot designed for customer service. When I say super simple, I mean exactly that — it doesn’t do much, but it provides an opportunity to learn the core functionality of the Conversation service with a few best practices thrown in.”

Take a deeper dive

As you’re building your Watson bot, there will almost certainly be times when a more detailed demonstration will prove helpful. Check out these tutorial videos to find out more about the foundational elements of a Watson chat bot and see how they are built.

Featured asset #3: IBM Watson Conversation: Working with intents

 

Featured asset #4: IBM Watson Conversation: Working with entities

 

Featured asset #5: IBM Watson Conversation: Working with dialog

 

Go beyond the basics

Congratulations! You’ve used the tutorials and guides above to build your first working chat bot. But don’t stop there. Are there ways you can enhance your chat bot?

One benefit of working with Watson APIs is that they all work together seamlessly. Extend your bot’s capabilities to spoken conversation using the Speech to Text and Text to Speech APIs. Make your bot empathetic with Tone Analyzer, which analyzes emotions in a user’s text and can be used to tailor chat bot responses accordingly. Or create a bot that can be a subject matter expert by using Retrieve and Rank, which enhances information retrieval with machine learning.

Featured asset #6: See how it easy it is to extend your bot’s capabilities using the Retrieve and Rank API: How to Use Watson Conversation Service With Enhanced Information Retrieval

There, you’ve got it – the ultimate guide to creating your own Watson Conversation app. Happy developing! We can’t wait to see what you create.

* Not quite ready to build yet? No problem. Bookmark this post, then read up on conversational commerce to figure out how a chat bot can improve customer service at your organization. See why how you build a chat bot matters and find out how cognitive computing can help you build a better bot. Experiment with Watson Conversation for free and then come back to this post to jumpstart your conversational app development!

Experiment with Watson Conversation


More Developers stories
July 16, 2018

Building trust in the age of AI – How businesses can build fairness into their machine learning models

Every organization that develops or uses AI, or hosts or processes data, must do so in ways that allow them to rationalize the decisions or recommendations in a way that is easily consumable. Let's examine Forrester's recommendations how organizations can leverage AI for the good of humankind, while avoiding the ethical pitfalls associated with perceived discrimination.

Continue reading

July 13, 2018

Improving the accuracy & speed of translations with Neural Machine Translation

Neural Machine Translation technology comes standard in the IBM Watson Language Translator service. NMT is an advanced machine translation method based on deep learning, the development of which has led to remarkable improvements in translation fluency and the achievement of higher human evaluations.

Continue reading

July 12, 2018

Improving productivity: IBM ranked leader in AI-based text analytics platforms by Forrester Wave

IBM has been named a leader in AI-Based Text Analytics Platforms by The Forrester Wave ™, Forrester's rigorous evaluation of vendors in a software, hardware, or services market. Watson Discovery, Watson Explorer, and Watson Natural Language Understanding’s strengths and weaknesses were assessed alongside seven other providers.

Continue reading