When I built an AI research assistant for a law firm, the feature I thought would be a nice-to-have turned out to be the one they use most. The system has an annotation feature. Any user can select text in a document and leave a comment. Something like…
I built an AI research assistant for a German law firm and the retrieval pipeline took maybe 30% of the total development time. The other 70% was fighting the LLM to cite sources correctly. Lawyers have a very specific standard for citation. You don…
I built an AI research assistant for a German law firm and the retrieval pipeline took maybe 30% of the total development time. The other 70% was fighting the LLM to cite sources correctly. Lawyers have a very specific standard for citation. You don…
I built a RAG system that needs to answer in German or English depending on the query language. Sounds simple. It was not. The source documents are mostly in German but some contain French legal terminology, Latin phrases, and occasional English citati…
I build AI systems for professional services firms. During testing of a legal research assistant I built for a German law firm, one of the senior lawyers flagged something that could have been a serious problem. The system was asked about a specific GD…
Got some good engagement on my earlier post "I made €2,700 building a RAG system for a law firm — here's what actually worked technically" so I wanted to go deeper into the actual architecture for anyone building something similar. Shippe…
