← All classes
CLASS 9June 23 · AI Remix Jam

"Argue with it,until you get something you like."

Tony Jones
Taught byTony JonesCourse Instructor, Pratt AI Design Certificate
CreativeAI Academy

The class in brief

Tony ran the room through a full music-video pipeline in one sitting: concept it with an LLM, write and compose a song in Suno, then a cover, keyframes, and a short video, posted to Miro before the night ended. The GOLD prompt and the "Wrestle With AI for Concepting" 7 principles carried the writing; Suno's own mechanics carried the sound. After this page you can write a GOLD prompt yourself instead of asking AI for one, direct lyrics with bracket and parenthesis cues, and argue with a first draft until it's actually yours.

The night at a glance

Why this matters · 6:20 PM

Study the top tracks before you write a single lyric.

Tony's brief for the night: research and wrestle with an idea using an LLM before writing anything, and study Suno's own top tracks first to learn the vocabulary, the same tool-review-before-generating habit the room had already built with images . The chain ran the whole night: research and vocabulary, a GOLD prompt, lyrics with an LLM, composing in Suno, a break, then art direction, three looks, keyframes, a short video, uploaded back into Suno, and a link posted to Miro.

10
stages the agenda broke the night into, research through posting the finished link to Miro.
~5
generations the free Suno tier covers, at roughly 10 credits per Create against ~50 free credits. Listen fully before re-rolling.

The framework · 6:33 PM

Write your own GOLD prompt

Tony's instruction was specific: write the prompt yourself, don't ask the AI to write your song for you. GOLD structures that first move into four parts.

G

Goalwhat you're actually after

"My goal is to write a song," stated plainly, before anything else gets specified.

O

Outputideas, not a finished piece

"The output is ideas for the song, not necessarily the song itself." Stage it deliberately rather than asking for a finished draft in one shot.

L

Limitationsstay in conversation

Limit the AI to a back-and-forth rather than a single output; nothing gets locked in on the first pass.

D

Datatopic, artists, styles

The concrete material: what the song's about, and the music you actually like, fed in as the starting vocabulary.

Directional lyrics: brackets and parentheses
Directional lyrics: brackets and parentheses · 6:33 PM

"My goal is to write a song. The output is ideas for the song, not the song itself."

Tony, modeling a GOLD prompt live for the room

The exercise · 6:57 PM

Wrestle with AI for concepting

The 7 principles

How to actually argue with an LLM until a lyric is worth keeping.

The core slide of the night : be methodical, stage it theme to imagery to verses to chorus to polish. Start with the hook, the song's gravitational center. Interrogate every idea rather than accepting the first draft. Generate 3 to 5 variations, not one. Change the angle of attack when stuck, a new character or a new genre. Draw on named artists, "in the voice of X." Refine with constraints: rhyme, syllables, mood words.

"Try to argue with it until you get to something you like."

The board that catches it all

Every deliverable had a home before anyone started: slogan, favorite artist or style, the AI tool used, the master prompt, the AI-output lyrics, and the finished cover, six cells on a shared classwork board .

Don't settle for one

The room's live coaching, repeated during the image-direction stretch: don't take the first result, keep pushing until it's actually right, then generate the set you need from there. The interrogation principle, applied in real time.

The craft · 7:01 PM onward

One song, built in Suno, then carried into a short video.

Suno itself runs on two fields, Lyrics and Styles, the second a short list of non-conflicting tags; the room's rule of thumb was to ask an LLM to boil a style down to five essentials before pasting them in. Remix > Reuse Prompt borrows a track's own prompt to study; a free voice toggle covers male and female, with "baritone" or "chest voice" for a lower register.

The video half chained two more tools onto the song: a start frame and an end frame, generated separately, then handed to Adobe Firefly (firefly.adobe.com, Video > Generate Video, roughly 8 seconds from two images) or to Krea, whose LTX and Veo 3.1 Light models take the same start-plus-end-frame input. The finished clip uploads back into Suno, replacing the track's cover image, and loops.

2
frames are all a video model needs: a start and an end. Everything between them, it invents.
2
tools do the video step: Adobe Firefly or Krea, both accepting the same start-plus-end-frame pair.

Methods and prompts

Five methods to take with you

METHOD 01 · GOLD part of: structure your ask

Write your own GOLD prompt

Goal, Output, Limitations, Data, written by you before AI touches the idea. The discipline is in staging the output as ideas, not a finished piece, on the first pass.

Where it came fromTaught by Tony Jones in class 9's music-video pipeline, where he had the room write their own Goal, Output, Limitations, and Data prompt for a song idea rather than asking AI to write it for them.Use it whenUse this at the start of any creative project when you want to hand AI a clear brief instead of a vague idea, and keep the process open to revision.

Working prompt

My goal is to [what you actually want, e.g. write a song about X]. The output I want right now is ideas, not a finished piece, stay in conversation with me and don't lock anything in yet. My limitations: ask me one question at a time. My data: [topic, artists or styles I like]. Start by asking me what you're missing.

You will know it worked whenit opens by asking you one question at a time about what's missing, and it doesn't hand back a finished piece on the first pass.

METHOD 02 · INTERROGATE part of: reject the first draft part of: keep the judgment human

Argue with the first draft

Don't accept the first version. Judge it yourself first, then have the model check your read, and push the direction you actually chose.

Where it came fromPart of Tony Jones's Wrestle With AI for Concepting principles in class 9, which told students to judge the AI's first ideas themselves and push back before accepting any direction.Use it whenUse this after AI gives you a first round of ideas and you want to test your own judgment before committing to a direction.

Working prompt

Here are the first ideas you gave me: [paste]. I'll say first what's wrong with each one and why, then you check me: did I miss a reason to reject one, or a reason to keep one I cut? Then give me a version that's more [tragic / playful / specific], whichever direction I chose.

You will know it worked whenit points out a specific idea you cut or kept that your own reasoning missed, then delivers a version pushed toward the direction you named.

METHOD 03 · DIRECTIONAL LYRICS part of: give it a job

Direct the lyrics with brackets and parentheses

Structure tags in [brackets], delivery cues in (parentheses). Suno reads both as instructions, not lyrics, so it's the difference between a flat take and a directed one.

Where it came fromTaught by Tony Jones in class 9 as the way Suno reads structure and delivery cues, marking song sections in brackets and performance notes in parentheses so the tool follows real direction instead of flat text.Use it whenUse this when writing lyrics for Suno or a similar AI music tool and you want control over song structure and vocal delivery.

Working prompt

Write lyrics for [song idea], and mark every section with [brackets] for structure ([Verse], [Chorus], [Instrumental]) and (parentheses) for delivery cues like (whispered) or (building). I'll paste this straight into Suno.

You will know it worked whenevery section carries a bracketed structure tag and every delivery cue sits in parentheses, ready to paste straight into a music tool without reformatting.

METHOD 04 · GENERATE MULTIPLES part of: generate multiples

Refine with constraints

Ask for several versions before picking one, then push the winner against real constraints instead of accepting it as-is.

Where it came fromOne of Tony Jones's seven concepting principles in class 9, generating three to five versions of a line before picking a direction and refining it against real constraints like rhyme and syllable count.Use it whenUse this once you have a favorite draft of a verse or hook and want to sharpen it against specific rules rather than accept it as is.
Same idea elsewhereThe 2x2 grid trick (class 8)

Working prompt

Give me 3 to 5 versions of this [verse / hook / line]. Then I'll pick a direction, and you refine it against these constraints: [rhyme scheme, syllable count, mood words].

You will know it worked whenthe refined version actually fits the rhyme scheme, syllable count, and mood words you named, not just a reworded version of the one you picked.

METHOD 05 · STYLE TAGS part of: structure your ask

Boil the style down to 5 tags

Suno rewards a short, non-conflicting tag list over a paragraph of description. Let the LLM do the compression.

Where it came fromTaught in class 9 as the room's rule of thumb for Suno's Styles field, asking an LLM to compress a freeform description of a sound into five non-conflicting tags.Use it whenUse this when you have a clear sense of the mood or genre you want but need it condensed into short tags a music tool can read.

Working prompt

Here's what I want this track to sound like: [describe freely, genres, artists, mood]. Boil it down to 5 essential style tags, comma-separated, non-conflicting, ready to paste into Suno's Styles field.

You will know it worked whenyou get exactly five comma-separated tags that don't contradict each other, ready to paste into a music tool's style field.

The shelf

Tools and references

Tools that night

  • Suno (suno.com), Suno Labs Genre Wheel for reverse style discovery
  • Nano Banana (Gemini image model), a cover-art option
  • Adobe Firefly (firefly.adobe.com), video from two frames
  • Krea (LTX / Veo 3.1 Light), start-plus-end-frame video
  • ChatGPT, Gemini, or Claude for the GOLD prompt and lyrics

Named in the room

  • GOLD: Goal, Output, Limitations, Data, the night's prompt skeleton
  • Wrestle With AI for Concepting, the 7-principle songwriting framework
  • The Miro board, where every finished song link and cover landed
← Class 8 · Node-Based Workflows in Krea CLASS 9 OF 24 Class 10 → AI-Enabled Ideation