Seeded legal-tech company
It answers legal research questions from Indonesian regulations, with the source and citation trail attached.
Seeded legal-tech company
Klaussa collects all 297K of them and keeps collecting, reads the scans with OCR run on its own hardware, links every citation from one regulation to another, and answers a legal question with the clause each part of the answer came from.
One pass through the product: a legal question answered from the collection, the regulations behind it searched and mapped, then a document reviewed and another drafted against the same source.
A legal question is answered from the corpus, with the plan it followed and the articles it relied on.
Drawn product mockup: the company names, people and contract files in it are invented, while the regulations, article numbers and platform figures are real. The impact figures are recorded ones.
Impact
Delivered
Stage-based ETL where every stage is idempotent and resumable, with an isolated coding agent that has shipped six production fixes on its own.
Run on a rented 16x RTX 5090 cluster, with low-confidence pages dead-lettered instead of silently indexed.
An in-text citation algorithm that links each regulation to the ones it amends, implements or is tested by.
Planner, tool use, supervisor and grounded citation over a self-hosted Qdrant index.
Llama-3.1-8B with continued pretraining on 1.27B tokens of Indonesian law, then SFT, then RLVR with GRPO.