Metadata-Version: 2.4
Name: trustqe
Version: 0.0.1
Summary: Test your AI app before you ship it, and prove it is safe. Early release.
Author-email: TrustQE <contact@trustassay.com>
License-Expression: LicenseRef-Proprietary
Project-URL: Homepage, https://trustassay.com
Keywords: llm,evaluation,ai-safety,red-team,rag,agents,compliance
Classifier: Development Status :: 1 - Planning
Classifier: Intended Audience :: Developers
Classifier: Programming Language :: Python :: 3
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development :: Testing
Requires-Python: >=3.9
Description-Content-Type: text/markdown

# TrustQE

TrustQE tests your AI app before you ship it and gives you proof that it is
safe. It runs your test cases through your own app, on your machine or in
CI, scores every answer for quality, safety, security, fairness and
compliance, and returns one verdict your CI can act on. Your app is never
exposed to the internet.

**This is an early release.** It contains no SDK functions yet. The full
SDK (`run_eval`, test sets and the `trustqe` command) arrives in a later
version.

Learn more at https://trustassay.com or email contact@trustassay.com.
