---
title: README
emoji: 📉
colorFrom: blue
colorTo: blue
sdk: static
pinned: false
---

# Argentis Labs

Evaluation-first ML for decisions in regulated domains: lending, legal, insurance.

We build systems where a wrong answer has a cost: constrained decision models,
human-in-the-loop agents, and the benchmarks that hold them accountable.
Benchmarks are frozen and hashed before any model is trained against them.

- Research: [Locally Correct, Globally Wrong](https://argentislabs.io/research/locally-correct):
  LLM judges versus deterministic predicates on authorization records
- Code: [github.com/argentislabs](https://github.com/argentislabs) and
  [liquid-legal](https://github.com/j-a-marin/liquid-legal)
- Benchmark: [Argentis-Decision Bench](https://huggingface.co/datasets/argentislabs/argentis-decision-bench): evidence-grounded decisions with abstention