LegalDocument Intelligence

Daxte Builds LegalMap, a Generative AI Search Tool for French Legal Documents, on AWS

Daxte· FranceAmazon SageMaker · Amazon Textract · AWS Trainium +2

French startup Daxte built LegalMap, one of the first French generative AI solutions for legal documents, on AWS. The company fine-tuned open-source LLMs such as Llama2 7b on Amazon SageMaker, used Amazon Textract to digitize 30 years' worth of legal documents, and changed names, addresses and other sensitive information to remain GDPR compliant. As of December 2023 LegalMap had a dataset of nearly 125 million documents, and in 2023 Daxte worked with Data Reply France to optimize training costs by migrating to AWS Trainium and AWS Inferentia.

Overview

French startup Daxte built LegalMap, one of the first French generative AI solutions for legal documents, on AWS. The company fine-tuned open-source LLMs such as Llama2 7b on Amazon SageMaker, used Amazon Textract to digitize 30 years' worth of legal documents, and changed names, addresses and other sensitive information to remain GDPR compliant. As of December 2023 LegalMap had a dataset of nearly 125 million documents, and in 2023 Daxte worked with Data Reply France to optimize training costs by migrating to AWS Trainium and AWS Inferentia.

This entry has 13 published fields tied to exact passages in an immutable source capture.

Inspect the highlighted source

The challenge

LegalMap needed to scan 30 years' worth of legal documents, digitizing them for its AI models to use, so that it could search French legal documents and systematically source answers from millions of documents.

The solution

Daxte built LegalMap, a generative AI search solution for French legal documents, on AWS. The team fine-tuned open-source large language models such as Llama2 7b from Hugging Face with its own datasets on Amazon SageMaker, and used Amazon Textract to accurately scan and digitize the legal documents. In 2023, Daxte worked with Data Reply France, an AWS Partner, to optimize training costs by migrating from GPU resources to AWS Trainium and AWS Inferentia. When preparing the data for generative AI, LegalMap changed names, addresses and other sensitive information to remain GDPR compliant.

Document IntelligenceGenerative AI

Reported business value

As of December 2023, LegalMap had a dataset of nearly 125 million documents comprising legal, financial and marketing data. Daxte is launching LegalMap in September 2024 with its first service, Watch, for real-time information monitoring and alerts for legal firms across France, and estimates that LegalMap will scan 600 million documents by 2026.

Sources

Open any source and check the claim yourself — that is the point of the register.

This record was researched and written with AI assistance, and its claims were checked against the sources above. (EU AI Act art. 50 transparency notice.)

Related entries

Other legal entries in the register.

All entries
LegalPredictive AnalyticsUnknown

Darrow raises $35M for an AI that parses public documents for class action lawsuit potential

Darrow, a legal tech startup founded in 2020, built an AI-based data engine that crawls thousands of sources of publicly available information (newsfeeds, social media, consumer complaints, regulatory filings, SEC filings, environmental reports, court dockets) to identify class-action litigation potential in areas such as data privacy violations, environmental contamination, and discrimination, and to predict likely legal outcomes and case value. A team of legal data specialists, including former lawyers, reviews the AI-surfaced insights before lawyers use the platform for case review and discovery. Around 50 law firms, covering hundreds of lawyers, were using the product, and active cases stemming from Darrow's data insights totaled around $10 billion in claims at the time of the funding round.

92/100HighPrimary source
Darrow· United Stateslarge language models
LegalAgentic AIHybrid

Delivering agentic AI to law firms globally using AWS with stp.one

stp.one, a Karlsruhe, Germany-based legal tech provider founded in 1993, built Legal Twin, an AI-driven platform integrated with its document management system STP Documents, using Amazon Bedrock (including Anthropic's Claude and the Titan embedding model) and Amazon Aurora PostgreSQL. Legal Twin offers six AI-powered capabilities including intelligent contract risk analysis and automated receivables processing, with responses grounded in case documents and court decisions and citations shown so lawyers can verify sources. It supports Model Context Protocol integration and lets clients with data sovereignty requirements store and process data locally, connecting on-premises storage with cloud-based processing. Certain claims that traditionally took 6-10 minutes to file can now be processed in under 30 seconds using Legal Twin, and productivity gains for users reach up to 3x at the upper end. The platform must comply with GDPR and Germany's federal code for lawyers.

100/100HighPrimary source
stp.one· GermanyAmazon Bedrock · Anthropic Claude · Amazon Titan embedding model +2
LegalDocument IntelligenceUnknown

IDEXX Laboratories cuts contract sanctions review from weeks to 20 minutes with Luminance AI

IDEXX Laboratories used the AI-powered contract automation platform Luminance to review its entire contract database for connections to sanctioned countries and entities following Russia's invasion of Ukraine, completing in 20 minutes a review that would typically have taken weeks manually. Separately, Koch Industries' in-house legal team uses Luminance Corporate to automate generation of NDAs, master service agreements and IT-related contracts, including self-service contract generation for non-legal business units, and Deloitte used Luminance on a project standardizing 4,500 contracts across 14 European entities for client BT in two weeks, estimating a 50% time savings versus manual review.

92/100HighPrimary source
IDEXX LaboratoriesLuminance
LegalDocument IntelligenceUnknown

Spellbook runs 530,000 contract reviews a month with Claude

Spellbook, a contract drafting and review platform serving 5,000 customers across 80 countries including in-house legal teams at companies like LG, Dropbox and eBay, built Claude-powered agents that review and redline contracts inside Microsoft Word, apply each legal team's own review standards automatically, and orchestrate about 15 different Claude agent configurations matched to task complexity. Spellbook's agents now run about 530,000 contract reviews a month and field more than 700,000 lawyer chat messages a month, cutting the time to complete an agreement roughly 10x, from about 10 hours of lawyer work to about one hour.

92/100HighPrimary source
SpellbookClaude Platform · Claude Code

Was this helpful?

Your feedback helps us improve our use case database