{"slug":"delivering-agentic-ai-to-law-firms-globally-using-aws-with-stp-one","url":"https://findausecase.com/use-cases/delivering-agentic-ai-to-law-firms-globally-using-aws-with-stp-one","title":"Delivering agentic AI to law firms globally using AWS with stp.one","description":"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.","company":"stp.one","industry":"Legal","country":"Germany","aiCapabilities":["Agentic AI","Document Intelligence"],"technology":["Amazon Bedrock","Anthropic Claude","Amazon Titan embedding model","Amazon Aurora PostgreSQL","Model Context Protocol"],"deployment":"Hybrid","problemStatement":"From case filings to dockets, legal professionals often review and draft hundreds, and even thousands, of documents over the course of a single case. As case law becomes more complex and the talent pool shrinks, law firms face the challenge of delivering the best outcomes for their clients while managing growing caseloads. Even while faced with talent shortages and evolving regulatory requirements, law firms are managing more and more cases, each involving critical deadlines for filing motions and responding to requests.","solutionApproach":"To develop AI-powered capabilities, stp.one adopted Amazon Bedrock, which provides its teams with access to hundreds of foundation models from leading AI companies. The company developed six unique AI-powered capabilities for Legal Twin, which range from intelligent contract risk analysis to automated receivables processing. To generate documents and answers using natural language processing, stp.one uses Anthropic's Claude in Amazon Bedrock. The company built Legal Twin on top of the document management system STP Documents, which uses Amazon Aurora PostgreSQL to power semantic searches with high performance and availability at global scale for PostgreSQL. To perform semantic searches across its cloud-based vector store, stp.one selected the Titan embedding model in Amazon Bedrock. Legal Twin also features flexible integration options: clients can embed the solution directly into their workflows using the Model Context Protocol (MCP), and clients that must meet stringent data retention and data sovereignty requirements can also choose to store and process all their data locally, connecting on-premises storage solutions with cloud-based processing.","businessValue":"Certain claims traditionally take 6-10 minutes to file, and by using Legal Twin, users can process those same claims in under 30 seconds. Legal Twin is helping law firms around the world accelerate their legal research, litigation discovery, case records analysis, document retrieval, invoicing and collections, and more. Benefits cited include a productivity increase of up to 3x for users at the upper end.","evidence":{"band":"high"},"sourceUrl":"https://aws.amazon.com/solutions/case-studies/stp-one-case-study/","dates":{"publishedAt":"2026-08-30T20:31:20.450Z","publishedAtSource":"pipeline","updatedAt":"2026-08-30T20:31:20.450Z"},"license":"Open for reading and citing with a link to https://findausecase.com/use-cases/delivering-agentic-ai-to-law-firms-globally-using-aws-with-stp-one. Bulk republication requires permission."}