Skip to content

1. Introduction

← Guide contents · Next: Philosophy →

There is a point where adding another genre name stops helping.

A prompt such as Liquid Drum and Bass, Chiptune, Spectral may describe the neighbourhood, but it does not say what should lead, what should support it, which features must survive, or how the arrangement should move. Those decisions are still hiding inside the genre labels.

Semantic prompting is my way of making those decisions visible. I separate a musical idea into roles—bass, rhythm, harmony, texture, motion, priority, structure—and give each role a clear responsibility. The result is not perfect control. It is a better way to think, listen and revise.

A guide to thinking about generative music

Section titled “A guide to thinking about generative music”

Despite its title, this is not primarily a guide to writing prompts. Prompts are one interface within a larger creative process. The real subject is how to decompose a musical problem, build source material, assign responsibility, listen diagnostically and refine an idea across multiple generations.

The approach borrows useful working principles from software engineering:

  • Separation of concerns — let different prompt fields, source tracks or workflow stages solve different musical problems.
  • Iterative refinement — revise in response to a result instead of trying to specify the finished song perfectly in advance.
  • Provenance — keep the source, intermediate generations, settings and creator relationships visible.
  • Documentation — record what each stage was meant to do, what happened and why the next decision followed.

Music is not software, and a generative model is not a deterministic compiler. These principles do not make the process predictable in that sense. They provide a practical structure for working creatively with uncertainty.

This guide is written for people who already know their way around Suno. It does not explain where the prompt box is or how to press Generate. It concentrates on the more interesting problem: deciding what to ask for and understanding why a result needs another pass.

This guide is not a reverse-engineering of Suno.

It is not a list of magic words.

It does not guarantee specific outputs.

It is a collection of repeatable creative practices and observations: ways of structuring musical intent, testing ideas and learning from the results.

Suno remains generative and variable. The aim is not to eliminate that uncertainty, but to work with it more deliberately.

A common misconception is that great Suno songs come from discovering a single perfect prompt.

In practice, many of my strongest results have come from designing a workflow where each step has one clear responsibility. Rather than asking one prompt to solve every musical problem, I break the process into stages that build, test, combine and refine ideas.

This principle underpins the entire guide. Prompts matter, but they are only one part of the creative process. Equally important are the order in which they are used, the source material they act upon, and the clear responsibility assigned to each stage of the workflow.


← Guide contents · Next: Philosophy →