poteto Shares Workflow for Building Adaptive Game Music With AI
The takeaway is that vague aesthetic goals like 'seamless transitions' only become executable once translated into concrete tempo, voice-layering and channel-switching rules. Builders who lack domain vocabulary can borrow this two-step pattern: let the agent sharpen the requirement, then verify its understanding before any execution. The workflow also generalises to other media work, such as producing storyboards before full video.
poteto, a developer with no music production experience, used Grok Bot to build a music system for her game tibo.dog. She used the /sharpen skill from pstack to refine her requirements and /in-your-own-words to have the agent restate goals before execution. The system synthesises sound in real time via the browser's AudioWorklet, combining Game Boy-style voices, bass, pads and drums at a unified 128 BPM. Variations of one main melody shift per game region and the first Boss, with notes coming from pre-written sequences rather than live AI improvisation.
poteto 给我们分享：不懂音乐术语，也能与 AI 一起把创意变成音乐系统 这可能是咱们很多不懂音乐专业的产品研发们的真实痛点：我知道想要什么、却缺少专业词汇、不知道它的音乐名词是什么！这时可以先让 AI 帮你明确需求，再进入制作。 # 不急着执行，先确认双方想的是同一件事 poteto 没有音乐制作经验，起初只能描述：想要 Game Boy 风格，同一主旋律的不同变奏能无缝衔接，类似玩《原神》时的体验。 她直接告诉 Grok Bot：“我缺少描述自己想法的词汇。”随后用 /sharpen 深化需求，再用 /in-your-own-words 让 Agent 复述目标，检查理解是否一致。 这两个 skills 不是作曲工具，是在补齐创作前的沟通。制作解释视频时，作者也先确认分镜和动态分镜草稿，再制作完整版本。 # 实现的不是单首配乐，是随游戏变化的音乐系统 按 poteto 说明，声音通过浏览器的 AudioWorklet 实时合成，结合 Game Boy 风格声部、低音、铺底和鼓，并加入延迟与混响。 曲目统一为 128 BPM，不同区域和首个 Boss 的配乐围绕同一主题变化，随游戏强度逐层加入声部。需要区分的是：音符来自预先写好的序列，不是 AI 在游戏运行时即兴作曲。 # “无缝衔接”最终要变成具体规则 系统使用两个播放通道，按小节和乐句安排切换，并分别处理旋律与伴奏。同主题变奏可以叠加，其他组合则采用保留旧旋律、先换新伴奏等方式，避免直接切歌。 这说明，一个模糊的审美要求，最终需要落实为节奏、声部和切换规则，才能稳定执行。 lauren @poteto i asked grok bot to make a video about how the music in tibo.dog was made! i started by clumsily describing something i wanted (i have 0 experience making music): gameboyish music, seamlessly transitioning between variations of a main melody like another game i had played (genshin) one prompt i tried that helped me communicate my goal better was telling bot "i lack the vocabulary to describe what i want" and using the /sharpen skill from pstack. then the /in-your-own-words skill helped me confirm whether or not it understood what i was trying to say i also used this same trick when making this video, so my agent produced a storyboard and animatic before working on the full thing knowing the right words is very powerful Your browser does not support the video tag. 🔗 View on Twitter 🔗 View Quoted Tweet 💬 0 🔄 0 ❤️ 0 👀 245 ⚡
