Skip to main content

Solutions

Products

Recommended products

Questions? We are here to help.
Contact us

Purchase

Questions? We are here to help.

Resources

Tools

Use Deep Research

Deep Research uses agentic AI to analyze vast amounts of legal content, surface key precedents, and deliver clear, transparent insights - all in a fraction of the time traditional research requires. Spend less time sorting through results and more time building winning arguments, backed by comprehensive, accurate answers you can trust.
You can use Deep Research to streamline complex research.
  • Expert AI-powered research that moves you forward faster and more confidently.
  • Transparent and interactive with real time insights into how results are generated with step-by-step research notes.
  • Accessible insights and actionable output with a detailed, comprehensive report sharing valuable insights and arguments on both sides of the issue.
Deep Research uses what is known as retrieval augmented generated (RAG), which limits errors by grounding the language model in trusted Westlaw legal content to help ensure that all citations and links are valid because we force the AI to use our content to answer the question. This technology will save you a tremendous amount of time, but it is not infallible. Deep Research should be part of, not a complete substitute for, your traditional research process.

How it works

Deep Research uses large language models - a type of generative AI - and focuses the models on the language of cases, statutes, and other primary law to improve accuracy.
In addition, primary law is referenced in the responses with the actual language from the source, and links are included to read the full primary law documents. Even with these and other precautions, Deep Research can occasionally produce inaccuracies, so it should always be used as part of a research process in connection with additional research to understand the nuance of the issues and further improve accuracy.
The AI-generated summary of results along with the list of primary law authority can be extraordinarily useful for getting an overview of the issues and pointers to primary authority, but it should
never
 be used to advise a client, write a brief or motion for a court, or otherwise be relied on without doing further research.
note
Use Deep Research to accelerate your research, not to replace it.

AI security and data usage

Protecting our customers’ information is at the core of our Information Security strategy. Thomson Reuters maintains its reputation for providing reliable and trustworthy information across all its offerings, including a comprehensive information security management framework supported by a wide range of industry-leading security policies, standards, and practices.
Thomson Reuters Westlaw and Practical Law platforms use multiple types of models throughout the product, but today the primary models include:
Thomson Reuters doesn’t use customer inputs to train generative AI.
  • Machine learning: This model drives the primary search engines in Westlaw and Practical Law, learns and adapts by using algorithms to analyze and draw inferences from patterns in data. The data used is primarily driven by user interactions in the platform. The non-text generating machine learning models used were developed by Thomson Reuters.
  • Generative AI: This model focuses on generating new text based on language patterns and probabilities. Thomson Reuters uses third-party generative AI models.

This article applies to:

  • PRODUCT: Westlaw Advantage

Related Content