epochs

Projects · Intermediate · 3–4 hours

An evaluation harness

Build the tool every AI team needs: run a fixed test set, see what passed, and know whether a change really helped.

What you'll build

A small harness that scores any system on your test cases, breaks results down by tag, compares two versions case by case and tells you if the difference is real.

You'll need

Python 3 and NumPy where the code imports it. 30 to 50 real inputs for something you're building, each with the expected output and a tag.

Learn first

This project is part of Pro

The first two projects are free. Pro opens every lesson and every project.

See Pro plansFrom ₹119 a month. No auto-renewal.