Creative DNA Working Session
A working session with your data team. Your ads. Your models. Live.
Not a demo — a 45-minute build session. We decompose a slice of your own Meta ad library on screen, cluster it, name the themes, and leave your team a running notebook and a seeded workspace they keep. For data science, ML, and creative-analytics teams evaluating whether to build this or buy it.
Your corpus, decomposed live
We ingest a sample of your actual ad library and run the full pipeline — embeddings, clustering, LLM-named themes — in the room, on your creative.
A notebook you keep
Your team leaves with a runnable Jupyter notebook — raw corpus to the DNA axes — against a workspace that stays live after the call.
The build-vs-buy answer
Honest scoping of what it takes to run this in-house vs on the API — where multi-vector, multimodal retrieval is the hard part you'd rather not own.
A scoped next step
We leave with a bounded POC plan on your library with a measurable success metric — not a slide, a plan.
Honest scope: competitor teardowns come from public Meta Ad Library data — longest-running, highest-signal creative, not claimed ROAS. Conditioning components on your actual performance data is what we build together in a pilot, on your numbers — it is not an off-the-shelf claim.
Prefer to poke at it yourself first? Explore the Creative DNA template in Studio