MCP Mastery
About
lab-02-pairwise-preference

Pairwise Preference

README

# Pairwise Preference

Choose the better output using deterministic criteria.

## Good / Bad / Ugly

- **Good**: deterministic inputs, explicit expected behavior, and a result a reviewer can reproduce.
- **Bad**: hard-coded sample strings that pass the happy path and collapse under a new example.
- **Ugly**: partial production data and noisy labels; the lab keeps the contract small enough to test anyway.

Run locally with `uv run pytest` or `python -m pytest`.

pyproject.toml

[project]
name = "lab-02-pairwise-preference"
version = "0.1.0"
requires-python = ">=3.11"
dependencies = []

[project.optional-dependencies]
dev = ["pytest>=8.0"]

[tool.uv]
dev-dependencies = []

Starter Python