IBM Cloud Docs
About Watson Assistant

Documentation for the classic Watson Assistant experience has moved. For the most up-to-date version, see About watsonx Assistant.

About Watson Assistant

Use IBM Watson® Assistant to build your own branded live chatbot into any device, application, or channel. Your chatbot, which is also known as an assistant, connects to the customer engagement resources you already use to deliver an engaging, unified problem-solving experience to your customers.
Create AI-driven conversational flows Your assistant leverages industry-leading AI capabilities to understand questions that your customers ask in natural language. It uses machine learning models that are custom built from your data to deliver accurate answers in real time.
Embed existing help content You already know the answers to customer questions? Put your subject matter expertise to work. Add a search skill to give your assistant access to corporate data collections that it can mine for answers.
Connect to your customer service teams If customers need more help or want to discuss a topic that requires a personal touch, connect them to human agents from your existing service desk provider.
Bring the assistant to your customers, where they are Configure one or more built-in integrations to quickly publish your assistant on popular social media platforms such as Slack, Facebook Messenger, Intercom, or WhatsApp. Turn the assistant into a member of your customer support call center team, where it can answer the phone and address simple requests so its human teammates can focus on more nuanced customer needs. Make your assistant the go-to help resource for customers by adding it as a chat widget to your company website. If none of the built-in integrations fit your needs, use the APIs to build your own custom app.
Track customer engagement and satisfaction Use built-in metrics to analyze logs from conversations between customers and your assistant to gauge how well it's doing and identify areas for improvement.

How it works

This diagram illustrates how the product delivers an exceptional, omnichannel customer experience:

Flow diagram of the service

  • Customers interact with the assistant through one or more of these channels:

    • An existing social media messaging platform, such as Slack, Facebook Messenger, or WhatsApp
    • A phone call or text message
    • A web chat that you embed in your company website and that can transfer complex requests to a customer support representative.
    • A custom application that you develop, such as a mobile app or a robot with a voice interface

  • The assistant receives a message from a customer and sends it down the appropriate resolution path.

    If you want to preprocess incoming messages, this is where you would use webhooks to inject logic that calls an external service that can process the messages before the assistant routes them. Likewise, you can process responses from the assistant before they are returned to the customer.

  • The assistant chooses the appropriate resolution from among these options:

    • A conversational skill interprets the customer's message further, then directs the flow of the conversation. The skill gathers any information it needs to respond or perform a transaction on the customer's behalf.

    • A search skill leverages existing FAQ or other curated content that you own to find relevant answers to customer questions.

    • If a customer wants more personalized help or wants to discuss a sensitive subject, the assistant can connect the customer with someone from your support team through the web chat integration.

For more information about the architecture, read the How to Make Chatbot Orchestration Easier blog on Medium.com.

To see how Watson Assistant is helping enterprises cut costs and improve customer satisfaction today, read the Independent study finds IBM Watson Assistant customers can accrue $23.9 million in benefits blog on ibm.com.

This documentation describes managed instances of Watson Assistant that are offered in IBM Cloud or in Cloud Pak for Data as a Service. If you are interested in on-premises or installed deployments, see this documentation.

Browser support

The Watson Assistant application (where you create assistants and skills) requires the same level of browser software as is required by IBM Cloud. For more information, see IBM Cloud Prerequisites.

For information about the web browsers that are supported by the web chat integration, see Browser Support.

Language support

Language support by feature is detailed in the Supported languages topic.

Terms and notices

See IBM Cloud Terms and Notices for information about the terms of service.

US Health Insurance Portability and Accountability Act (HIPAA) support is available with Enterprise with Data Isolation plans that are hosted in the Washington, DC location created on or after 1 April 2019. For more information, see Enabling HIPAA support for your account.

To learn more about service terms and data security, read the following information:

Next steps

Have questions? Contact IBM Sales.