Use Case Intelligence RSS Search use cases Search
In-house Software / SaaS global Company newsroom

Thomson Reuters

Document Processing · Enterprise Knowledge Search

General-purpose LLMs can produce subtle but consequential errors in legal and compliance work, where professionals need trustworthy, citation-backed analysis across very large document sets.

Read the original story Explore all use cases
As of Q1 2026, CoCounsel has crossed one million users
Monthly CoCounsel SKUs in legal have quadrupled year-over-year
The share of our business that's Gen AI-enabled has doubled in a little over a year
up to 10,000 documents

Reported impact

Business outcome

Thomson Reuters launched Thomson in production to power CoCounsel Legal's Tabular Analysis, enabling scalable, more consistent and verifiable document analysis for legal professionals while supporting broad commercial adoption of its GenAI-enabled legal products.

  • Productivity Improvement
  • Risk Reduction
  • Scalability

Solution

Thomson Reuters built Thomson as a proprietary large language model for legal and compliance work, then deployed it inside CoCounsel rather than exposing the model as a standalone end-user product. The source says Thomson was built on Thomson Reuters proprietary legal content, specifically Westlaw and Practical Law, plus input from human legal experts, giving the model domain depth beyond general-purpose AI. In production, CoCounsel serves as the agentic workspace and application layer, and its Tabular Analysis feature orchestrates the workflow: users define up to 100 questions and submit up to 10,000 documents, then CoCounsel calls Thomson to extract structured answers with linked citations. The page does not name a separate storage platform, but it explicitly identifies Westlaw and Practical Law as the authoritative content foundation and says Thomson is governed through enterprise-grade frameworks for transparency, traceability, verifiability, structured evaluation, and expert validation.

Data flow

Authoritative legal content from Westlaw and Practical Law, together with Thomson Reuters expert input, is used to build and refine Thomson. In production, legal professionals use CoCounsel's Tabular Analysis to submit up to 10,000 documents and up to 100 questions. CoCounsel calls Thomson to analyze the corpus and return structured, citation-linked answers that attorneys can review and rely on.

Solution architecture

5 components · 4 layers
  1. Ingest
    • Westlaw Authoritative proprietary legal content used to build and deepen Thomson's legal understanding.
    • Practical Law Proprietary legal content source used to build and refine Thomson for professional legal tasks.
  2. Compute
    • Thomson Proprietary LLM that provides legal comprehension, reasoning, and citation-grounded extraction for high-stakes professional workflows.
  3. Serving
    • CoCounsel User-facing agentic workspace that invokes Thomson within legal workflows used by professionals every day.
  4. Orchestration
    • Tabular Analysis CoCounsel feature that runs large-scale structured extraction across document sets and user-defined questions.

Architecture clues

  • Deployment is governed within enterprise-grade frameworks grounded in transparency, traceability, verifiability, structured evaluation, and expert validation.
  • First implementation launched in CoCounsel Legal's Tabular Analysis feature.
  • Outputs are described as verifiable and citation-grounded for attorney review.
  • The model was built on open-source foundations that Thomson Reuters can evolve over time.
  • Thomson is one of the LLMs that CoCounsel calls on rather than the end-user product itself.

Evidence from the source

"As of Q1 2026, CoCounsel has crossed one million users."
"CoCounsel is the product — the agentic workspace, skills, and workflows legal professionals use every day. Thomson is one of the LLMs CoCounsel calls on."
"It was built on our proprietary content, including Westlaw and Practical Law, two of the most authoritative legal data sources in the world, and reflects input from our vast network of human legal experts."
"Monthly CoCounsel SKUs in legal have quadrupled year-over-year."
"Thomson Reuters built Thomson, a proprietary LLM designed specifically for high-stakes legal and compliance work."
"You can extract structured answers from up to 10,000 documents across up to 100 questions you define."
Transparency Evidence & methodology 71/100 reference value · 92% confidence · 1 source

Review how this reference was scored and trace each normalized claim back to its documented source.

01

Scoring methodology

How scores are calculated

Customer Reference Value measures usefulness as a customer reference. Evidence Confidence measures the quality and traceability of available evidence, not independent verification.

Customer reference value71/100
  • Problem clarity20/20
    Measures whether the customer's operational problem is specific enough to compare.
  • Implementation depth25/25
    Rewards named components, data flow, integrations, and architecture detail.
  • Outcome specificity16/20
    Measures whether the reported benefit is concrete rather than a generic claim.
  • Quantified impact0/25
    0 metrics describe measurable impact.
  • Deployment scale10/10
    Rewards evidence of a live or scaled deployment and meaningful integration scope.
Evidence confidence92%
  • Source authority25/25
    The deployment is described by the adopting organization or a government source.
  • Claim traceability21/25
    10 of 12 key fields link to a named source.
  • Direct evidence20/20
    6 direct source quotes retained.
  • Date provenance10/10
    The publication date comes from the source page or publisher.
  • Source transparency8/10
    1 source reference document publisher, URL, authority, retrieval, and supported fields.
  • Implementation specificity8/10
    Rewards source-backed components, data flow, quantified impact, and a specific outcome.
02

Traceability

Sources & provenance

Field coverage shows which facts each source supports. Dates are shown only when documented by the source.

  1. Thomson Reuters

    Thomson Reuters customer story

    First-party
    https://www.thomsonreuters.com/en-us/blog/why-we-built-thomson-llm/
    Source type
    Customer-published story
    Published
    Sep 1, 2026
    Supports
    • Customer
    • Business problem
    • Solution
    • Products
    • Solution components
    • Data flow
    • Integrations
    • technical area
    • use case category
    • Business outcome
    • outcome category
    • Metrics
    • Architecture
    • evidence quotes
    • Publication date

Date evidence

  • Published on source page Sep 1, 2026 · Thomson Reuters · First-party
    Open date source
Not separately sourced Industry, Region, Company size. Treat these normalized attributes as lower-confidence until a dedicated source is added.

Related

Similar use cases

See all like this
MongoDB Sep 9, 2026 Squary AI Software / SaaS United States Squary AI needed to eliminate slow, outage-prone legal search infrastructure that combined MongoDB with OpenSearch and hurt document review speed, cost, and trust. At Quatrini Law Group, Squary AI analyzed more than 460,000 pages and saved over 400 attorney and paralegal hours. Document ProcessingEnterprise Knowledge Search Amazon Bedrock · Claude · MongoDB Atlas OpenAI Aug 20, 2026 Stampli Software / SaaS North America Stampli needed to launch complex new products and keep product knowledge current without waiting on scarce design, contractor, and operations bandwidth. 243 modeled active role-hours compressed to about 77 for the Deep Finance launch Document ProcessingEnterprise Knowledge Search ChatGPT Work · Codex · Deep Finance Google Cloud Modified · Jun 9, 2026 igot.ai Software / SaaS Vietnam igot.ai needed a governed AI operating model for audit and enterprise workflows, where teams could search and reason over complex document repositories without maintaining heavy custom infrastructure. Document ProcessingEnterprise Knowledge Search BigQuery · Gemini Enterprise Agent Platform · Gemini Pro