Prompt Library · every prompt is a benchmark

Same prompt. Two systems. One obeys.

A generator gives you a song. THIRI gives you the session.

Each prompt below went to two places: a leading text-to-music generator, and an AI assistant with THIRI connected. Listen to both. Then check the receipts — every claim on this page is backed by the engine's actual output, rendered right here. Copy any prompt and use it today.

How these benchmarks work
Pre-registered, reproducible, fair. Every card's pass criteria were written before any system was run. The THIRI column renders live in your browser from the engine's exact output — the same notes are in the downloadable MIDI and the receipts JSON. The generator column is that system's unedited first result for the identical prompt.
  1. These are different kinds of products. A text-to-music generator produces finished audio — often beautiful. THIRI produces directed, editable musical structure. The test is not which sounds more produced; it is which one did what the musician asked.
  2. Audio stems are not parts. Some generators export stems. A stem is a frozen performance — you can turn it down, but you cannot change its ii chord to a tritone sub. MIDI is editable intent.
  3. Determinism is a feature. Every THIRI result on this page reproduces byte-for-byte on re-run. Generator output changes on every run — by design.
  4. The produced render is the same MIDI. Where a produced version appears, it is this page's downloadable MIDI dragged into a DAW with instrument sounds chosen — minutes of sound selection, zero notes changed.

Every prompt above works today.

Add the hosted MCP to Claude or Cursor and these prompts become your tools — same engine, same receipts, your music. Free tier: 1,000 calls a month.

Get a free key MCP quickstart
Prompt copied