How Thomson Reuters Uses Claude in Amazon Bedrock to Power CoCounsel

Thomson Reuters integrated Claude via Amazon Bedrock into its AI platform, CoCounsel, to make the expertise of 3,000+ subject matter experts and 150 years of authoritative content accessible to legal and tax professionals. The solution combines Retrieval-Augmented Generation (RAG) architecture with multi-model deployment to deliver comprehensive, accurate professional analysis. Early adopters report dramatic efficiency gains, with some estimating task time cut in half or more.

Outcomes

3,000+Subject matter experts' knowledge delivered via AI
150+Years of authoritative content leveraged
50%+Estimated task time reduction

Models

1CS
Claude Sonnet 4.6
Anthropic's multimodal model with 1M-token context balancing performance and efficiency for coding and reasoning.
2C3
Claude 3 Haiku
Anthropic's fast multimodal LLM with a 200K-token context for vision-language tasks.

Tools & Technologies

1C
CoCounsel
AI-powered legal and tax research platform by Thomson Reuters for attorneys and compliance professionals.
2AB
Amazon Bedrock
Fully managed service for accessing foundation models from leading AI companies via AWS.
3PC
Prompt Caching
API optimization feature by Anthropic reducing latency and cost for repeated context in Claude requests.
4RG
Retrieval-Augmented Generation (RAG)
AI retrieval pattern combining language models with document retrieval for grounded, accurate answers.

AI Categories

Challenge

Thomson Reuters needed to make the deep expertise of 3,000+ subject matter experts and 150+ years of authoritative content accessible to legal and tax professionals at scale, while meeting extraordinarily high accuracy and reliability standards where incorrect advice carries substantial professional risk.

Solution

Thomson Reuters deployed Claude via Amazon Bedrock as the AI backbone of CoCounsel, building a comprehensive RAG architecture that processes complex legal and tax documents, with Claude 3 Haiku handling rapid processing and Claude 3.5 Sonnet powering deeper analysis, all within AWS's secure enterprise infrastructure.

Full Story

Thomson Reuters is one of the world's leading providers of information and technology solutions for legal, tax, and accounting professionals. With a content library spanning over 150 years and a network of more than 3,000 domain experts, the company holds an extraordinary depth of professional knowledge — but the challenge was making that expertise readily accessible to practitioners at the moment they need it most.

Access 449+ AI use cases, 414+ tools, and adoption signal rankings.

Source

CLAUDE
March 2026
Original case study

Similar Cases

1P
How Petrobras Uses Generative AI to Uncover $120M in Tax Savings
Petrobras
$120MTax savings identified
2WM
How West Monroe Cut IT Costs by $1.4M Annually with Moveworks AI
West Monroe
$1.4 millionAnnual IT support cost savings
3BO
Blue Origin Builds AI Agent Platform for Lunar Hardware Design
Blue Origin
2,700+AI agents deployed
4P
How PwC Saves $150M with Microsoft 365 Copilot Across 200,000+ Employees
PwC
$150 millionTime Savings from Copilot
5K
How KPMG Achieves 60-80% Content Time Savings with Writer AI
KPMG
60-80%Time savings on derivative content creation
6C
How CACI's DarkBlue Uses Elasticsearch and Claude to Accelerate Dark Web Criminal Investigations
CACI
Seconds per query regardless of data age or volumeCriminal investigation acceleration
7B
How Brainlabs Uses Claude Cowork to Automate Work Across 1,000 Employees
Brainlabs
~400Skills authored by employees
8P
How PwC Uses CrewAI to Accelerate Enterprise-Scale GenAI Adoption
PwC
70%+Code generation accuracy
9N
How N26 Uses Claude on AWS Bedrock to Automate 70% of Customer Operations
N26
70%Task automation in targeted processes
10A
How ASAPP Uses Amazon Bedrock to Achieve 91% First-Call Resolution
ASAPP
91%First-call resolution rate
See all use cases →