About Discovery

The IBM Watson™ Discovery service makes it possible to rapidly build cognitive, cloud-based exploration applications that unlock actionable insights hidden in unstructured data — including your own proprietary data, as well as public and third-party data.

This is the architecture of a complete Discovery service solution:

Discovery architecture diagram

With Discovery, it only takes a few steps to prepare your unstructured data, create a query that will pinpoint the information you need, and then integrate those insights into your new application or existing solution.

How does Discovery do it? By using data analysis combined with cognitive intuition to take your unstructured data and enrich it so you can discover the information you need.

IBM Watson™ Discovery brings together a functionally rich set of integrated, automated Watson APIs to:

  • Crawl, convert, enrich and normalize data.
  • Securely explore your proprietary content as well as free and licensed public content.
  • Apply additional enrichments such as concepts, relations, and sentiment through natural language processing.
  • Simplify development while still providing direct access to APIs.

Watson Discovery News, a public data set that has been pre-enriched with cognitive insights, is also included with Discovery. You can use this public, unstructured data set to query for insights that you can integrate into your applications. See Watson Discovery News for more information. See a demo of what you can build with Watson Discovery News here.

The Discovery service is available on Bluemix

Next steps

Questions and feedback

Find answers to your questions about the Discovery service in our developer communities:

  • For programming questions, go to the Watson forums on Stack Overflow.
  • For questions and comments about Watson products and services, go to the Watson forum on developerWorks.
  • To read posts about Watson services, go to the Watson blog.