Watson Knowledge Studio benefits

Teach by example

Empower domain subject matter experts to teach Watson the language of your industry or organization without requiring deep technical skills or coding.

Engage your experts

You won’t need a single line of code. With a multi-user collaborative environment and a powerful user interface, SMEs easily build custom models without any coding expertise.

Use everywhere

Apply what you’ve taught Watson in multiple applications by using models from Watson Knowledge Studio in Watson Discovery, Watson Natural Language Understanding and Watson Explorer.


Watson Knowledge Studio features

Point-and-click model development

Annotation, training, evaluation, and deployment are all included in a single, intuitive UI. Annotation is as simple as highlighting words in your sample documents.

Intuitive model evaluation

Built-in quantitative measurements like precision, recall, and inter-annotator agreement, all presented in a model performance dashboard with suggestions for improvement.

Secure to the core

Data is encrypted at rest and in transit, and is PII, ISO27001, ISO27017 and ISO27018 certified, as well as GDPR compliant. Your data, your model, your IP.

Fast model deployment

Simple dashboard to manage model deployments; deploy and undeploy models to Watson Discovery, Watson Natural Language Understanding, or Watson Explorer with just a few clicks.

Dashboard for users and storage

Workspace administrators can easily monitor users and storage from within the WKS UI, enabling you to only spend money on users and gigabytes you need.

Collaborative environment

Team members, from subject matter experts to data scientists, are brought together in a collaborative environment. Easily invite users, assign annotation tasks, and adjudicate among conflicting annotations.


Preannotation relies on your dictionaries of industry-specific terms, or Natural Language Understanding, to automatically annotate words and thus bootstrap the annotation process.

Rule-based annotators (experimental)

Rule-based annotators can automatically recognize text written in specific patterns, like license plates, ICD-10 codes, or phone numbers; no human annotation needed.

Watson for Customer Feedback

Derive more value from every client interaction with Watson. Packaged options to suit your budget and use case.


Related products

Watson Natural Language Understanding

Analyze text to extract metadata from content such as concepts, entities, keywords, categories, sentiment, emotion, relations and semantic roles using natural language understanding.

Watson Discovery

Uncover connections in data by combining automated ingestion with advanced AI functions with Watson Discovery.