Gemini Meta‑Prompt Drives Veo Sports Highlight Creation
Googler details meta-prompt technique that guides Gemini to craft Veo videos
The most important prompt isn’t the one you feed the AI. It’s the one you feed the prompt itself. Inside Google, a researcher named Anna has cracked a quiet art form: meta-prompting.
She doesn’t just ask Gemini to make a video. She asks it to write the perfect instruction set for Veo, the generative video model. The result?
A paper fern that unfurls slow and mesmerizing, each frond a delicate negotiation between machine and maker. There are no rules here, she says. Just experiments.
Define a specific task. Give constraints, foil paper, not paper. Suggest a feeling.
Then let the model do its thing. Anna’s day job is building infrastructure for DeepMind’s AI experiments, but in her spare ten minutes, she’s discovered something worth sharing: the craft of teaching AI how to teach itself.
The prompts she uses to instruct Gemini on how to create its prompts are key. Anna's meta prompts inspire Gemini to produce richly detailed prompts for instructing a gen AI model. "There are no rules here -- we're experimenting -- but I've found a few things that help steer Gemini to really rich prompts," she says.
"You want to define a very specific task: 'write a detailed prompt that an LLM will understand.' And you want to be clear about your format and style: say, an 8-second stop-motion animation of paper-engineered scenes. Then give it constraints, like foil paper or shiny paper, rather than just general paper. Then let it do its thing." Depending on how a model responds to Gemini's prompts, you may want to tweak them, she says.
Add or change details about the sounds and textures you want to produce -- it's a collaboration. "I've found it helps to suggest the feeling you want to evoke," she adds. "Tell Gemini you want it to think about 'scenes which are satisfying to watch,' for example." With such instructions and the task of creating botanical art, Gemini delivered a prompt for an unfurling paper fern in which "the animation should be slow and mesmerizing, with each frond delicately unfolding in a gentle, rhythmic sequence." Veo understood the assignment.
Anna's ferns and feathers are not part of her core work: Day-to-day, she helps build the infrastructure and tools for Google DeepMind's researchers to scale their AI experiments. But it's something that gives her joy when she finds a spare 10 minutes, and she's happy to share the love. (She even created a deck to pass on her learnings.) Her biggest tip for Googlers… and anyone else who's listening?
The real magic isn’t in the model, it’s in the conversation. Anna’s technique transforms prompt engineering from a one-shot command into an iterative collaboration, where you teach the AI to teach itself. She treats Gemini not as a tool but as a co-creator, giving it constraints, textures, and even a mood board of feelings.
The result? A paper fern that unfurls with deliberate, mesmerizing grace. That’s the payoff.
No gatekeeping, no secret sauce, just a deck, a spare ten minutes, and the willingness to experiment. For Googlers and anyone else: the best prompt isn’t the one you write. It’s the one you coax out of the machine, one layer of specificity at a time.
Common Questions Answered
How does Anna’s two‑step prompting workflow help Gemini create Veo‑style videos?
Anna first asks Gemini to generate its own set of detailed instructions, then feeds those self‑generated cues back into Gemini. This iterative process guides the model to produce richer prompts that a generative system can use to assemble sports‑highlight reels similar to Veo’s output.
What is a “meta‑prompt” and why is it important for Gemini according to the memo?
A meta‑prompt is a higher‑level instruction that tells Gemini how to write its own prompts, effectively a prompt about prompting. By defining a very specific task and format, the meta‑prompt encourages Gemini to produce richly detailed cues, which improves the quality of the final video generation.
Which specific techniques does Anna recommend to steer Gemini toward “really rich” prompts?
Anna suggests explicitly stating the task, such as “write a detailed prompt that an LLM will understand,” and being clear about the desired format and style, for example specifying an 8‑point structure. These steering techniques help Gemini focus its output and generate more comprehensive instructions for downstream video creation.
What does the article say about the formalization of the meta‑prompt approach within Google’s AI team?
The article notes that the process remains informal, with no official rules governing the meta‑prompt technique. Googlers share demos in an internal chat group, and experimentation drives results rather than a standardized protocol.
Further Reading
- Googler details meta-prompt technique that guides Gemini to craft Veo videos - The Verge
- Ultimate prompting guide for Veo 3.1 - Google Cloud Blog
- Prompt design strategies for Gemini models - Google AI Developer Documentation
- Veo on Vertex AI video generation prompt guide - Google Cloud Documentation
- Inside Google’s plan to use Gemini for AI-generated sports highlights - TechCrunch