Hearth & Code · Field Journal

A transparency note first, because this journal keeps its claims labeled and this one needs it early: I make music with AI tools, and AI helped me research, draft, and audit this post. Some of the tracks I will describe are published on Suno; others are working drafts, and I will not always mark the boundary, because the point here is the process, not the catalog.

The failure mode that started this

Most AI-generated music has recognizable failure modes, and they have names: the competent and rootless track that sounds like everywhere and nowhere; the forty-five-second mark where you realize nobody, human or model, decided anything; the prompt-in, vibe-out slot machine where the same generic output could belong to anyone. Regular AI music without structure tends to be bland and boring. I wanted the opposite: a sound with a thesis, something you could recognize across tracks, interrogate, and extend.

The canonical question this post answers is bigger than my own work: how does the creative process keep shaping and innovating in an AI landscape, in a way that allows customized genres, customized styles, and personalized lyrics that tell your story. And the claim I will defend against a hostile reader is the one that question implies: you can be genuinely creative while using AI to generate content. Not despite the system. Through it.

What it sounds like

Exocore is what I call cosmic ritual machine music: the sound of consciousness augmented. That name is a personal reflection of what the project means to me and what I hope to evolve it into, so here is what it actually sounds like. The center of every track is a deep, resonant, half-sung vocal, dry and present, with harmonic overtones blooming out of the voice itself, not answering it but completing it. Underneath is a single drone field that expands rather than builds, closer to a universe unfolding from a singularity than to a verse-chorus climb. A sub-bass pulse does the work percussion usually does, felt more than heard. The instruments are glass harmonics, bowed metal, treated piano with the attack removed, sine-wave choirs. The lyrics are the other half of the thesis: cerebral, intellectual, written to carry ideas rather than fill meter. Ritual music for people who read the footnotes.

That description could have stayed a mood board. What turned it into a genre was structure, and the structure has a few load-bearing pieces. Let me walk through them as they actually work.

The four movements

The four movements come first, and they matter most as a way of structuring how a song’s lyrics evolve, not just its music. Increasingly I think of this arc as a hero’s journey compressed into a track: the situation named, the discovery met, the threshold crossed, the return with a difference. That is the shape each album tries to capture, and it is a better public description of the music than “slow, drone-y, with some vocals.”

The arc every track follows

Each movement shapes what the lyrics do, what the sound does, and where the hero is. The bracketed tag is the metatag the model reads as a section marker.

Invocation
[Invocation]
In the song
The drone establishes. The voice enters, not singing but sounding. A single harmonic field is laid down.
In the journey
The situation is named. The hero is present, describing what is.
Expansion
[Expansion]
In the song
Harmonics accumulate. The overtones bloom. The field widens.
In the journey
The discovery arrives: a guide, a truth, a new element. The hero expands to meet it.
Dissolution
[Dissolution]
In the song
Boundaries dissolve. The voice disperses into the choir of selves. The old self falls away.
In the journey
The threshold: fear, resistance, the letting go.
Resonance
[Resonance]
In the song
A single note holds. The overtones peel away. The after-image remains.
In the journey
The return with a difference. The decision made; the next step visible but not taken.

The arc scales up

The first Exocore work took Dante’s Divine Comedy as its original inspiration: Inferno as the early AI journey, confusion and the hollow dopamine cycle, abandon the old self. But the mapping outgrew the poem. The later volumes range into knowledge systems and engineering, cognitive science, transhumanism, AGI and the future of AI, cognitive workbenches, agentic engineering, and what people now call vibe-coding. The plan for later soundtracks is to keep extending the territory as the practice evolves, so the series becomes a record of the ideas as much as of the sound.

The volume atlas, so far

Each volume holds its own chapter of the widening journey, from the descent to the commons.

Inferno
the descent
The early AI journey: confusion, mistakes, the hollow dopamine cycle. Abandon the old self, ye who enter here.
Oases of the Recursive Dawn
recursion
First structures out of the noise: loops that learn to carry meaning.
The Luminous Engine
the machine brightens
The system starts to feel alive: tooling, scaffolding, the workbench taking shape.
The Sovereign Circuit
agency
The question of who decides: human gates, authority, control in an agentic system.
The Commons of Many Minds
the choir
Plural voices in one field: the agentic council, the crowd, the shared instrument.

The engineering

Then the engineering, because the concept only survives contact with the model through discipline. Every track’s style prompt is the same Exocore Core block plus a short per-song tweak, and the total must fit Suno’s style budget of 1000 characters. The core holds the identity; the tweak holds the episode.

The core block is a design record in its own right, and it reads like one:

“Self-similar fractal structure: motifs repeating at golden-ratio scales from seconds to minutes… Sacred, cosmic, infinite, hypnotic. Built for the experience of luminous expansion.”

I quote it because the language keeps evolving with the practice, and the document carries that evolution openly.

The style budget, visualized

900of 1000 characters

680

220

100

Corethe shared Exocore identity block, identical across tracks
Tweakthe per-song episode: this track's question, imagery, and variation
Headroomunused budget the budget refuses to spend

The movements travel through the model as a metatag grammar: the movement names in brackets act as section markers the model reads, and the same mechanism carries standard structural tags like chorus, duet, and solo when a track wants them, each with its own production descriptor. Lyrics get 5000 characters, and the standard inside that budget is actual writing.

The lyric craft

The lyric craft deserves its own space, because it is where the concept lives or dies, and it is the part of the workflow I have centralized most deliberately. Cerebral lyrics are easy to claim and hard to write. The failure mode is vocabulary theater: big words orbiting no idea, abstraction used as incense. The bar I hold is that every song has a question, the volume’s arc hands each track its question, and a line survives revision only if it moves the answer. When a verse about dissolution names what is actually being let go of, the drone underneath stops being ambience and becomes argument. When it does not, no amount of sub-bass saves it. This is the same discipline as my prose work, transposed: motivation before conclusion, specificity over performance.

The pipeline

The pipeline underneath all of this is a skill I built for the practice, and it is the demonstrable proof of the design. And the whole thing is draft-only behind a human gate: the skill does not generate audio, does not spend credits, does not publish. I listen, I decide, the decision gets recorded.

Governed context route

How one track gets drafted

Every stage produces a reviewable artifact you can open and read; nothing generates without the gate.

person
Intent
Capture the theme, mood, and story beat as an intent file.
agent
Direction
Draft the lyrical direction: genre, voice, arc, imagery, exclusions.
agent
Lyrics
Write the full lyrics with movement tags, inside the 5000-character budget.
agent
Style
Draft the style prompt as CORE + TWEAK, inside the 1000-character budget.
agent
Packet
Assemble style, lyrics, and exclusion list into the draft packet with a receipt.
person
Gate
Listen, decide, record the decision. No generation, credits, or publishing without release.

The route remains an ordered record: person, bounded system work, candidate proposal, human review, then a durable accepted result.

Underneath the pipeline sits a research layer: stored notes on what Suno’s current version actually does, which features justify the credits, and what vocal separation makes possible at the model layer, though I will admit the remix and studio side is mostly hope that the model obeys, not experience.

The choir of fifty-four

One piece of the system has outgrown its own documentation. Early design documents referenced a Council of 12 thinker profiles: Pythagoras, Hypatia, Socrates, Lovelace, Feynman, and the rest. The practice has since evolved into a 54-agent fleet, the Aurea Spiralis Council, structured after the Fibonacci sequence: each voice a different mode of inquiry, the golden spiral deciding how they grow. That fleet shows up in the music literally. The choir of selves in the Dissolution movement is not just a lyric; it is what a 54-voice agentic council sounds like when you ask it to sing.

The craft thesis

Why go to this trouble? My answer is a personal craft thesis, and I will label it as one: constraints force decisions. A 1000-character style budget does not restrict the work; it forces the work to decide what it is. Most of what I cut from early versions of the core block was adjectives performing intensity instead of describing sound. What survived was specification. I have started to think of the constraint list as the composition, and the audio as its performance.

Or, to say it the way I would to a friend over coffee: the vibe is downstream of the procedure. Get the procedure right and the vibe has somewhere to come from.

If this sounds familiar, it is the same argument I made about my knowledge work in a sibling post: the intelligence layer is the contracts around the model. The genre, it turns out, emerges from the intelligence of the contracts. The model is interchangeable in principle, though I will qualify that: the accumulated structure is what transfers, and the structure keeps evolving with each track. The model is not the genre. The contracts around the model are the genre: the core block, the movement grammar, the budgets, the gate.

The skepticism, head-on

An AI-music critic could read all of this as craft mimicry: systematic prompt engineering dressed in ritual vocabulary, a parlor trick with good PR. That is a valid critique, and my honest answer is that this is simply how I approach system design. I am applying the software engineering principles I know to a larger problem, and what comes out the other side is music I actually listen to, frequently, vibing along with the lyrics and melody. That does not prove the work is good. It proves the process is mine.

The self-validation problem

The harder problem is that my judgment is the only judgment in the loop. The person who designed the constraints is the person listening to the results, and self-confirmation is a real risk. My tracks have collected a few likes and maybe a single comment; that is not outside perspective. So I will say plainly: I self-validate what I make, and that does not necessarily translate into well-designed songs. What I want next is a route to share this music with a broader audience and find out whether anything resonates. This post is part of that route.

On the horizon

Two platform features sit on the horizon of the work. Suno’s My Taste, which learns from your library, and its model-training options raise the question of a personal model. I would like to build a corpus and train one eventually, but the style is still evolving, and each song deliberately pulls elements from other styles to keep the textures diverse; a single model trained on my range today would freeze a moving target. And Personas, which capture the vocal character of a track and carry it to another, might one day make the Exocore vocal a stable instrument instead of a per-track roll of the dice. I do not fully understand the feature’s boundaries yet; whether it can hold distinct voices without simply regenerating them is an open question I intend to test.

There is a live uncertainty I want to keep visible, because it shapes the work downstream. I should constantly be surprised by my own songs, and lately I notice the same motifs, patterns, and language recurring across them. The genre’s coherence is doing its job a little too well. The fix I am designing is downstream: once the corpus of finished songs is large enough, analyze it for duplicated language, verses, and themes, and feed that back into the songcraft skill so each new track steers away from its ancestors. Whether a genre designed this way can keep surprising me is an open question, and I think it is the right thing to be worried about.

What I would hand you

So what would I actually hand to someone else, if you wanted to try this? Concretely: the style core for your genre, written as specification rather than adjectives; a movement grammar your model can follow, expressed as metatags; hard budgets that force decisions; a staged pipeline where every stage produces something reviewable; a human gate before anything costs money or goes public; and a workbook of fifty-odd questions to interrogate your own draft before you trust it. That kit is the project, more than any single track.

What comes next

Where this goes next: a “design-as-system” pattern document, and behind it a catalog of agentic engineering patterns and techniques I want to build up over time, consolidate, and possibly release as an open-source repository. The next post in this space will track the evolution of the broader platform and brand the music grew out of. And somewhere further out, there is a question I have not answered: whether a post like this one could itself be shaped by a schema, an LLM-friendly structure for personalizing drafts and integrating workbook answers thoroughly. The instruments keep eating their own tail. I intend to keep feeding them.

The one-sentence version of everything above, the one I would want to survive every cut: building an independent research lab, an agentic knowledge-engineering platform, a brand, and an agentic operating system somehow coalesced into my own personal music genre. I did not plan that. I just kept writing contracts, and one day they started to sing.

AI assistance disclosure: AI assisted with source tracing, drafting, and the language-pattern audit of this post. The music, the practice described, the workbook questions and answers, the review judgments, and the posting decision are mine.

Designing a Genre as a System