Her background spanning engineering and visual arts gives her a genuine edge. She has previously used AI to create embroidered alphabets and surrealist interpretations of games. That technical-artistic foundation matters because meta-prompting is not simply feeding requests into a machine. It is teaching an AI to become an expert prompt engineer in its own right, understanding nuance, artistic direction, and material specificity.
When Bortsova asks Gemini for prompts, she does not receive brief instructions. Instead, Gemini generates multiple detailed prompts, sometimes five to ten variations, spanning several pages each. These are not generic requests. They specify textures, pacing, emotional registers, and aesthetic frameworks that would take a human hours to articulate. The initial instruction to Gemini about prompt writing becomes the decisive variable separating mediocre from extraordinary video outputs.
Crafting Instructions for Maximum Creative Output
The mechanics of meta-prompting follow a specific architecture. First, you define the exact task for Gemini: "Generate detailed prompts that a video synthesis model will understand." Second, you specify constraints and format. Third, you evoke emotional or sensory outcomes. This structured approach, seemingly mechanical, unlocks surprising creative depth.
Bortsova's methodology includes five core principles. You must be specific about deliverables, clearly defining "detailed prompt for video generation." You then set format and stylistic parameters. For video, this might mean specifying duration, animation technique, and visual aesthetic. Next comes constraint specification: rather than generic instructions, you suggest specific materials or qualities. "Use foil paper or shiny paper" guides the AI toward richer texture variation than "use paper" ever could.
The emotional dimension proves crucial. Bortsova found that prompts explicitly requesting "scenes which are satisfying to watch" or "a meditative, unhurried pace" generate more engaging outputs. You are teaching Gemini to understand that the viewer's experience matters, not just the technical specifications. Finally, you iterate. Each prompt generation reveals new possibilities, allowing you to refine instructions and push creative boundaries further.
From Theory to ASMR Videos
Bortsova's most successful experiments involve ASMR-style videos created through Veo. She meta-prompted Gemini for detailed instructions that would generate stop-motion paper-engineering scenes: a skewer of crumpled paper meat barbecuing over paper coals, a pink flamingo with paper wings flapping rhythmically, intricate paper folding sequences revealed in satisfying detail. The results have been celebrated internally at Google and noticed by external marketing teams.
The key difference from manual instruction is specificity about material properties and sound design. Bortsova's prompts to Gemini emphasise how paper behaves: the rustling sounds, the light reflection off foil, the tactile satisfaction of watching something carefully constructed. Veo's audio generation then produces remarkably satisfying sounds of crinkling paper, creating genuine ASMR experiences from the algorithmic collaboration between the two models.
This approach scales well beyond ASMR. Bortsova has meta-prompted Gemini for nature documentaries, surrealist animations, technical explanations, and experimental narrative sequences. Each domain benefits from having an AI teacher shape another AI's creative output. The results consistently demonstrate that algorithmic guidance produces more sophisticated material than attempting to manually describe complex visual concepts.
Why This Matters for European Creative Professionals
The European AI creative sector is not standing still. Researchers at ETH Zurich's Computational Creativity Lab have been examining how instruction-chaining between models affects output quality, with findings suggesting that structured meta-instruction reduces prompt iteration cycles significantly compared to direct prompting approaches. Meanwhile, Mistral AI, the Paris-based frontier lab, has publicly discussed multi-model orchestration as a priority area for its enterprise clients, pointing to similar dynamics in text-based workflows that Bortsova is exploiting in the video domain.
For European creative agencies operating under tightening budgets and accelerating content demands, the efficiency argument is hard to dismiss. Industry estimates suggest meta-prompting reduces iteration cycles by 60 to 70 per cent compared to manual approaches. Marketing teams, content creators, and documentary makers across the continent are beginning to recognise that the bottleneck is rarely the generation model itself; it is the quality of instruction going in.
Practical Implementation for Creative Professionals
Bortsova's meta-prompting technique is accessible to any creative professional with access to Gemini and a video generation tool. The process begins with defining your creative vision broadly, then asking Gemini to translate that vision into executable prompts for Veo or similar models. Teaching Gemini your aesthetic preferences through iterative refinement is the central discipline.
You might, for example, ask Gemini: "Generate eight detailed prompts for stop-motion style videos showcasing food preparation. Each prompt should specify movement pace, camera angles, lighting mood, and sound design. The final video should feel meditative and satisfying to watch." Gemini responds with eight fully formed prompts, each several paragraphs long, ready to feed directly into Veo.
This collaborative framework, where one AI teaches another to generate outputs aligned with human creative intent, represents a fundamental shift in how creative production can be organised. Rather than battling against algorithmic defaults, you are engineering the algorithmic process itself.
- Articulate your creative vision precisely: emotional tone, visual aesthetic, target audience, intended impact.
- Teach your instruction-writing AI your specific aesthetic preferences through examples and feedback.
- Request multiple prompt variations to explore different interpretations of your core concept.
- Use emotional and sensory language in your meta-prompts to guide the AI toward more sophisticated outputs.
- Iterate rapidly: each generation of prompts reveals new creative possibilities you can refine in subsequent requests.
Traditional AI content generation treats the model as a black box. You provide input, hope for output, iterate when unsatisfied. Meta-prompting inverts this relationship. You are actively shaping the way the generation model interprets requests, essentially constructing a custom instruction system specific to your creative goals.
This matters because it democratises sophisticated creative production. Without meta-prompting, achieving professional-quality video output requires either spending enormous time manually crafting prompts or hiring specialist prompt engineers, a significant cost for smaller European studios and independent creators. Meta-prompting allows creative professionals to leverage both Gemini's instruction-writing capability and Veo's execution capability, creating a genuinely collaborative creative process that punches above its weight in terms of resource efficiency.
Most creative professionals can grasp the basics within two to three hours of experimentation. The key is understanding that you are teaching an AI about your creative preferences, then leveraging that understanding to generate instructions for your output tool. Mastery develops through iteration as you refine how you articulate creative vision to instruction-writing models.
Comments
Sign in to join the conversation. Be civil, be specific, link your sources.