LegalCheck: Retrieval- and Context-Augmented Generation for Drafting Municipal Legal Advice Letters

TL;DR

LegalCheck is an AI system that automates drafting municipal legal advice letters by combining retrieval of legal knowledge with context-aware generation, improving efficiency and consistency in legal workflows.

Contribution

This work introduces LegalCheck, a novel retrieval- and context-augmented generation system that enhances legal drafting with expert-in-the-loop validation and real-world deployment insights.

Findings

LegalCheck reduced drafting time from hours to minutes.

The system achieved 80-100% coverage of essential legal reasoning.

Legal professionals reported decreased workload and increased consistency.

Abstract

Public-sector legal departments in the Netherlands face acute staff shortages, increased case volumes, and increased pressure to meet regulatory compliance. This paper presents LegalCheck, a novel system that addresses these challenges by automating the drafting of objection response letters through a combination of Retrieval-Augmented Generation (RAG) and Context-Augmented Generation (CAG). Using a large language model (LLM) alongside curated legal knowledge bases, LegalCheck performs retrieval of relevant laws and precedents, and uses controlled prompting to incorporate both external knowledge and case-specific details into a coherent draft. An expert-in-the-loop review ensures that each generated letter is legally sound and contextually appropriate. In a real-world deployment within the Municipality of Amsterdam, LegalCheck produced near-final advice letters in minutes rather than hours, while maintaining high legal consistency and factual accuracy. The output is based on actual regulations and prior cases, providing explainable outputs that captured the vast majority of required legal reasoning (often 80\% to 100\% of essential content). Legal professionals found that the system reduced their workload and ensured a consistent application of legal standards, without replacing human judgment. These results demonstrate substantial efficiency gains, improved legal consistency, and positive user acceptance. More broadly, this work illustrates how responsible AI can be deployed in the legal domain by augmenting LLMs with domain knowledge and governance mechanisms.