The Isaacus API — the world’s first legal AI API — supports a wide range of legal information retrieval, extraction, and classification tasks, including:
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.
We plan on launching the following new capabilities by December 2025:
Grounding: feed enormous amounts of rich legal data, including case law, legislation, regulations, and commentary, to your own LLMs to improve accuracy and reduce hallucinations.
The best way to get notified about the introduction of new capabilities is to sign up for an Isaacus account and follow us on LinkedIn.If there’s something else you’d like to see added to the Isaacus API, please let us know and we’ll do our best to prioritize it.
