- Embedding: transforming legal queries and documents into highly compressed, high fidelity numerical representations to power semantic search, text classification, and clustering.
- Reranking: scoring and sorting legal documents based on their relevance to search queries.
- Extractive question answering: extracting answers to questions from legal documents with high precision and throughput.
- Universal classification: classifying and extracting clauses from legal documents based on your own criteria, with no prior examples necessary.