Jarvie Music Writing Loop
Study the seed, brainstorm wide, lock a voice, then write a performance-ready lyric and style prompt.
- Stage
- Write & Theme
- Kind
- Ready to run
The repeatable skills behind AI-assisted music — packaged as loops you or your agent can run to take a song from idea to released track, then start again.
Making music is the same handful of moves run over and over — study a theme, write a hook, generate a take, master the album, ship it. So instead of one-off instructions, each skill is framed as a loop: a repeatable cycle with a clear input and output that you run once per song, per chapter, or per track. They're written for a person and an AI agent to follow together.
Some loops build on others — you must Create before you can Master. Each one lists what it depends on.
Different tools and tastes get different loops for the same job — DistroKid or another distributor, one generator or another. Pick the one that fits you.
The last loop hands its result to the next, and the catalog you build feeds the next idea — so the whole pipeline is itself a loop.
If an AI agent is helping you make music, point it here. Every loop is written to be run by an agent and a person together — it names the real skills it uses and how it connects to the others, so an agent can follow the whole path from idea to released track. The library keeps growing, with new loops and skills added over time.
Study the seed, brainstorm wide, lock a voice, then write a performance-ready lyric and style prompt.
A simpler, more universal writing loop — find a hook, pick a voice, structure it, and write a solid song.
Turn any sacred passage into replay-worthy songs by studying it deeply, then writing through it.
Investigate a reference song, break it into usable musical and lyrical parts, and record it in your research library.
Mimic a specific song's signature — turn a deep analysis into a directed style prompt AND placed performance instructions.
Sing the actual public-domain hymn — exact words intact — dressed as a modern record.
Turn a real person's public presence into a song so specific they feel truly seen.
Research an artist deeply once, store them in your Artist Library, then channel that voice on every future song — so the study compounds instead of repeating.
When someone says "make it like that song," study the song instead of copying it — turn it into a grounded style direction and a reusable artist entry.
Research a hymn and store its public-domain lyrics + reusable research in the library — once, for every project.
The Suno-native loop: a writing loop produces the words, then you format, prompt, and submit a finished song into Suno.
Capture a finished Suno take — its link, length, and structure — onto the right song in the planner.
Generate your tracks on a platform other than Suno — same loop, a different engine.
Download every finished track out of Suno as clean, numbered local files — MP3 or WAV — in one pass.
Turn a folder of raw WAVs into a loudness-matched, diagnosed, cleanly-named album that streams right.
Normalize a track or album to a streaming-ready loudness — and touch nothing else.
Scan your tracks for the problems that wreck a release — and change nothing until you say so.
Apply clean fades and trim dead air or tail artifacts from the ends of your tracks.
Drive the album-distribution wizard end to end, then stop one click short of publishing.
Release through a distributor other than DistroKid — CD Baby, TuneCore, Amuse, and more.
Get clean lyrics from your songs onto streaming — format and store them, then publish to DistroKid.
Turn a song's raw lyrics into DistroKid-clean plain text, stored on the song in the planner.
Add your formatted lyrics onto DistroKid per track to unlock lyric display across streaming services.
Hold each song's research and brainstorm, compare versions, classify by genre, and plan the next release.
Study the styles in the encyclopedia, write and create your song through these loops, then organize and plan it all in the workspace.