The class in brief
Guest creative director Antonio Fragoso taught how to get real copy out of a model: build the full creative context first, then ask for the writing. The class built complete campaign systems live, one per World Cup team. After this page you can build the 8-element campaign system for a real project and judge your own longlist with the three judge prompts.
The night at a glance
Why this matters · 6:25 PM
The model remixes what already exists. That makes it predictable. You are not.
Antonio's opening argument: language models recombine what they were trained on, so left alone they produce the average of everything. The unpredictable part of great copy, the emotion, the human tension, the lived culture, has to come from you. His question for the night, “” got its answer by 6:39, after the room debated it live: the line this whole page is named after .
The craft · 6:44 PM
Concept at the center, six spokes around it: brand voice, emotion, human tension, culture, surprise, memorability. Emotion, tension, and lived culture are "the things AI doesn't understand yet." That's the human element, and it's also the job description.
The distinction that anchors the night: the idea is the solution ("if you have a body, you're an athlete"). The concept is its copywritten expression ("Just Do It"), the frame every execution pays off to, for thirty years . The night's roadmap ran from principles to co-creative direction .
The framework · 7:11 PM
The concept is the copywritten expression of the idea, the frame every execution pays off to. Every element that follows exists to protect it.
Brand voice needs a rationale, not adjectives: "friendly like the friend who tells you the truth but is snarky about it" beats "friendly." Human tension is the problem you're addressing; emotion is what the audience should feel.
A creative territory is one way of exploring the big idea, and every territory must ladder back to the concept. Guardrails are the always and never rules. Outputs are what you actually need made.
The system arrived as the night's pivot: concept locked, define the rest of your guidelines and turn them into a campaign system. In Antonio's words: "the best context possible to create the best prompt possible." The proof is a side-by-side , and the payoff is expansion: one creative thought into many executions . Change one element and the work changes with it: play with the outputs and that's "when AI's magic shines."
The exercise · 6:41 PM, debriefed 7:34
Pick a brand and a country still in the tournament, build all eight elements as a context block, and have the model produce campaign work that pays off your concept . This exercise feeds the final project.
Worked live · first as concept-finding , then as full systems
Everyone ran their brief both ways and compared . The consensus matched the thesis: same model, better context, better copy. One classmate's takeaway became the practical rule: front-load the work and the back end gets easy.
One run aimed Norway's campaign at Latin American fans whose own teams were already out. The model went Spanish unprompted and produced a "barrio" wordplay poster and a lotéria-style "El Ídolo" card, then started adding new lines inside the posters on its own.
A Nike England run built around Harry Kane: "The other shoe already dropped. He played on." Discarded rival shoes on the ground, Kane on a pedestal.
One classmate disagreed with the model's pick of its own best ideas, and it caved instantly: "you're so bright, nothing gets past you." Antonio's response became the quote of the night.
The judgment · 8:15 PM
Generating is cheap. Curating is the skill.
The future creative works in four stages: AI brainstorms, AI curates, humans direct, humans refine . The last exercise pointed the model at itself: write a prompt that makes it your co-creative director, then test your campaign against it .
"We are the final judgment criteria."
Antonio, after the sycophancy catch
Methods and prompts
Write the human work down before asking for a single headline: the problem, the tension, the concept. Hand that over, then ask for the writing.
Working prompt
Before you write anything: here is the problem [x], the human tension [x], and the concept in one sentence [x]. Confirm you understand the concept, then hold all copy against it.
Build your own campaign system block →You will know it worked whenit confirms the concept back to you before writing anything, and every line of copy it produces afterward still traces back to that one sentence.
All eight elements as one reusable block: concept, audience, voice, territories, tension, emotion, guardrails, outputs. One creative thought into many executions.
Working prompt
Here is my campaign system: Concept [x]. Audience [x]. Brand voice [3-5 adjectives, each with a rationale]. Territories [x]. Human tension [x]. Emotion [x]. Guardrails: always [x], never [x]. Now produce [output] that pays off the concept.
You will know it worked whenthe output it produces actually pays off the concept you stated, not just a generic execution of the audience and voice fields.
Antonio's working set, used on your own longlist before you pick anything. Slide above, in The judgment.
Working prompt
Judge the ideas above three ways. First: kill 70%, improve the remaining 30%, explain why. Second: judge them like the audience would, find the gaps. Third: will any of these stand out against ALL competing content? Explain why.
You will know it worked whenit actually kills most of the ideas and explains why, names a gap the audience would notice, and says plainly if none of them stand out.
Sometimes you are not the audience. Describe who is, let the model react as them, then compare its judgment with your own before deciding.
Working prompt
You are my stand-in audience: [describe them]. React to this copy as that audience would, in their words. Then I will tell you my own judgment and we compare.
You will know it worked whenthe reaction reads in the audience's own words and voice, not a strategist's summary of what that audience might think.
When you want a fair comparison, run the context block in a separate chat "so it doesn't bring the memory back." Front-load the human work: the more time you put in up front, the better the result at the end.
Working prompt
This is a fresh evaluation with no history. Here is a complete campaign context block and one output. Judge the output only against this block.
You will know it worked whenthe judgment holds up even with no memory of your earlier chat, based only on the context block and output you just gave it.
The close · 9:01 PM
Antonio closed with the Campaign DNA cheat sheet: purpose, audience, human tension, the concept in one sentence, voice adjectives with their rationale, three messaging pillars at most, territories, emotion, guardrails, outputs, and the judging prompts. Plus a reading list . The full deck ships in the course pack.
The shelf
42 captures, in order. Click any one to see it full size.









































