Pratt AI Design CertificateSummer 2026 · 24 classes

The whole course,
yours to explore.

Tools, methods, and resources from the Pratt AI Design Certificate Course, in one place. Explore the classes in order, jump around, follow an idea across all of them, or load the notes into your preferred AI to develop custom tools and methods.

Start here

Four ways in

The classes

Every class in the course

Twenty-one of twenty-four classes are written and ready to read. The last three are the final-project stretch, arriving as it happens.

The teachers

Who taught what

Course Instructors

Tony Jones
Dominik Heinrich

Critical Intelligence

Geoff Gibbins, Corrix

Krea Onboarding

Tony Jones, Creative AI Academy

Prompt design, image generation and AI video

Sydney Seifert-Gram

AI-Enhanced Workflows

Irina Kelly, Salesforce

Node Workflows in Krea

Seb Saga

AI-Enabled Ideation

Ceren Topçu-Weigand

Data Prep for Agentic Workflows

Ekta Mody Vakil

Bias in Our AI Data

Wouter Oomen, Edelman

AI Strategic Foresight

Angella Tapé, Havas

Copy Craft + AI

Antonio Fragoso

Creating Synthetic Personas

Jaeyoung Lee, Coca-Cola

Systems Thinking + Multi-Order Effects

Katrin Zimmermann, Credera

Storytelling + Story Systems

Sharon Panelo, Stories & Strategy

Built from the CreativeAI curriculum, Summer 2026 · Made by Tim Petrochko with Claude

What we saved for you

The course's boards, decks, recordings, and links started disappearing the week it ended. Everything on this site was captured before it went: the slides, the prompts, the methods, and the moments between them. It is yours now, and it does not expire.

Take it with you

Keep it even offline

Turn your AI into a tutor

Copy the setup prompt below, add the files from the zip, and your AI can quiz you on any class, explain a method again, or help you apply one to your own work. Works in ChatGPT, Claude, Gemini, NotebookLM, or anything else that accepts files.

The setup prompt

You are my tutor for the Pratt AI Design Certificate, Summer 2026. I am giving you the course pack: the class pages, the prompt library, and the course resources file. Ground every answer in those files and name the class it came from. Three jobs: REMEMBER (answer questions about what was taught, with the class number), PRACTICE (quiz me with retrieval questions, let me answer first, then check me and tell me where I am wrong), APPLY (help me run a course method on my own real work, step by step, one step at a time). If the files do not cover something, say so instead of guessing. Start by asking which of the three I want today.

Download the course pack

One zip with everything: this entire site (it works offline), the course resources file, every prompt, and the slide captures. Yours to keep, even if this link ever goes away.

download the zip

Search everything

One box over every class section, method, and resource. Type a word from class and land on the spot that taught it.

open search →

Quiz yourself

Four recall questions per class, answers hidden until you commit. Recall beats rereading.

start a quiz →

The glossary

58 course terms in plain English, each linked to the class that taught it.

open the glossary →

The methods poster

All 105 methods on one printable page, grouped by the idea they belong to. Made for the wall next to your desk.

open and print →

Class 8 in motion

Four recovered demo clips with audio: the live node build, the video chain, the recap, and ComfyUI.

watch the demos →

Every prompt, one page

All 123 copyable prompts from the course, by class, with the method each belongs to. Also in the zip as a text file for your AI.

open the prompt library

Try the methods on your own work

Three fill-in forms: a GOLD block, a campaign system block, and a brief x-ray. Type, it assembles the prompt, you copy it.

open the practice page

Who taught what

The instructors and every guest lecturer, what each one taught, and the public profile they gave the class.

open the teachers page

Pratt AI Design Certificate · Summer 2026

CLASS 13 OF 24
CLASS 13July 7 · AI Strategic Foresight

"AI does the data journey.You are the judgment."

Angella Tapé
Taught byAngella TapéSVP Group Strategy Director, Havas

The class in brief

Guest strategist Angella Tapé taught the three-canvas framework her Havas team uses on client work: category first, human truth second, positioning last, with a custom GPT doing the research legwork. The class ran the full framework live on a Busch NA brief. The takeaway skill: directing AI like a junior analyst while the judgment stays yours.

Why this matters

Half of all TV advertising produces no emotional response at all. Strategy decides which half your work lands in.

That claim comes from System1's ad-testing data, which Angella opened with. Her framework is the answer to it: three canvases, worked in order, with AI as the analyst and you as the judge. And always the category before the product: start with the product and, in her words, "I will fail, force-feeding people."

52%
of UK TV ads produce a completely neutral response. "I feel nothing, I do nothing." (US: 47%. B2B is worse.)
2.3x
brand attachment for the most adaptable brands compared to the least. From the Age of DULL research.

The framework

The three canvases

01

Category Creationfrom conformists to creators

The longest stage on purpose. What market am I actually in? What is the paradigm, and what shift is coming? Where are the gaps? The product stays out of the room for the whole pass.

02

Human Truthfrom interruption to meaning

Who are the customers, why do they behave that way, and what single insight sits under it all? Brands that win align to me, my community, or the world.

03

Brand Positioningborrow equity, or build it

Borrow from an adjacent category, or build from scratch the way Liquid Death did. Step away from the head-to-head mindset and the space opens. Then be single-minded: pick one.

The exercise

Working the Busch NA brief live

The brief

Fuel new growth for Busch Light through its non-alcoholic offering.

Light beer is a saturated category, and non-alcoholic drinkers are a growing audience. The ask: use AI deep research to evolve Busch NA's positioning, building on the brand's core equity (Mountains of Busch, the great outdoors, and midwestern values), then identify a growth audience and define new rituals for how Busch NA gets used.

The brief slide appears below, in From the board

Open the class Miro board
How the exercise ran

Five steps, from her workflow slide: upload the data pack, let the agent run deep research, do the thinking and strategizing yourself in Miro, upload your canvases back to the agent, and finish by letting AI challenge the positioning to sharpen it.

Category first, product last

The first canvas bans the product from the room: what market is this, what paradigm, what shift is coming, where are the gaps. Start with the product and you end up force-feeding people.

A market for people who don't like beer

One classmate, who doesn't drink and doesn't like the taste of beer, asked the analyst how big the market is for people who want the ritual without the taste. It came back with real segments, and the class watched a personal observation turn into a researchable audience in minutes.

Pushing past the obvious occasions

Another run kept getting camping, tailgating, and boating back from the model, all summer, all weekend. The fix was a direct order: bring it into the days of the week. The lesson inside it: the model defaults to the most photographed version of an audience until you push.

Another run left the brief entirely

Same canvases, aimed at repositioning a church in Madison County. The framework held anyway. That is how you know it is a framework and not a template.

From the board

What the class made in Miro

The three-canvas framework slide: Category Creation, Human Truth, Brand Positioning
The three-canvas framework, from her deck
The closing recap slide: the three-canvas framework with its supporting visuals
The recap: all three canvases with their visuals
The Busch NA AI Brief slide: objective and ask
The Busch NA AI brief

Methods and prompts

Five methods to take with you

METHOD 01

Boss of a junior analyst

Treat the model like a bright junior: direct it, redirect it, and ask for conclusions instead of accepting a data dump.

Working prompt

Synthesize everything above into exactly 2 categories of opportunity. Table format. End with one short question for me. Do not ask anything else.

METHOD 02

Ask for what's missing

The idea usually lives in what the research does not say. Ask for the missing data, not more of the found data. Her words: "Tell me what does NOT exist. From there you get the idea."

Working prompt

Based on this research: tell me what does NOT exist in this market, and what data I am missing. List the absences, not the findings.

METHOD 03

Give it an executive's job

Renaming the model's role from assistant to executive changes tone, depth, and brevity everywhere at once. One word doing the work of a page of formatting rules.

Working prompt

From now on you are an executive strategist, not an assistant. Max 5 sentences per answer, tables where useful, no jargon, answer your own research questions instead of asking me. Confirm and continue.

METHOD 04

Say what you want rather than what you do not

Negatives confuse it. Her full list for reining it in: executive style, five sentences max, table format, no jargon, stop asking me questions, answer your own research questions.

Working prompt

Rewrite your instructions to yourself as positive directives only: what you WILL do, in what format, at what length. Then follow them.

METHOD 05

Build the tool rather than the chat

A workflow you run twice deserves to be a tool. Know the workflow in your head first, then write it as strict, numbered steps with a named role. Custom GPT or Claude Project, either way the magic is the prompt.

Working prompt

Help me turn this workflow into a reusable assistant. Here are my steps: [list them]. Rewrite them as strict sequential instructions with a named role, an intake step, staged framework steps, and a fixed output format, always addressing the user.

Deeper detail

Inside her custom GPT

She opened the GPT and showed the class what's inside. Know your workflow in your head first, then write it as strict, numbered steps with a named role, always addressing the user. The same thing works as a Claude Project. Her words: the magic is the prompt, and it moves between tools.

1 · NAME + ROLE
Who the tool is
Stated like a job description.
2 · INTAKE
What it collects first
Everything it asks the user for before any work starts.
3 · STEPS + OUTPUT
The framework, numbered
Strict sequential instructions and a locked output format, so every run ends the same shape.
Open the Strategic Foresight GPT

The shelf

Tools and references

Tools that night

Cases she mentioned

  • BTS: the community that never gives up on you
  • Liquid Death: brand equity built from nothing
  • McDonald's Taiwan: pit stops for cyclists
  • Norway's macho non-alcoholic beer, now #1 with new mothers
CLASS 13 OF 24
CLASS 14 OF 24
CLASS 14July 8 · Copy Craft + AI

"AI doesn't need better prompts.It needs better context."

Antonio Fragoso
Taught byAntonio FragosoFreelance Creative Director, OpenAI
Former Global Creative Director, TikTok

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. The takeaways: an eight-part context block reusable for any campaign, and three prompts for judging your own longlist.

Why this matters

The model remixes what already exists. That makes it predictable. You are not.

Antonio's 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. The craft is feeding them that context before asking for a word.

70%
is how much of your own longlist Antonio tells the model to kill: "Kill 70% of the ideas, improve the remaining 30%, and explain why."
3
messaging pillars, maximum. More than that "and you'll say too much and say nothing."

The framework

The 8-element campaign system

01

Concept and audiencethe idea and who it is for

The concept is the copywritten expression of the idea, the frame every execution pays off to. Nike's idea was "if you have a body, you're an athlete." The concept was "Just Do It," and it has paid off for thirty years.

02

Voice, tension and emotionthe human element

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.

03

Territories, guardrails and outputswhere it goes and what it never does

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 exercise

The World Cup campaign systems

The brief

Build a complete campaign system for a World Cup team.

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 · one campaign system per person · results shared in the room

Recruiting the fans whose teams lost

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.

The shoe that already dropped

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. Its author's takeaway was Antonio's whole lesson: front-load the work and the back end gets easy.

The model flattered someone out of her own opinion

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 for half the room: "We are the final judgment criteria."

From the board

What the class made in Miro

The 8-element AI campaign system slide
The 8-element campaign system
Bad prompt versus good prompt slide
Bad prompt vs good prompt
Antonio's Campaign DNA cheat sheet slide
The Campaign DNA cheat sheet

Methods and prompts

Five methods to take with you

METHOD 01

Feed it the thinking first

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.

METHOD 02

Build the campaign system

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.

METHOD 03

The three judge prompts

Generating is cheap; curating is the skill. Antonio's working set, used on your own longlist before you pick anything.

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.

METHOD 04

Use it as a stand-in audience

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.

METHOD 05

Run the test in a clean room

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.

Deeper detail

The one-page cheat sheet

The whole system fits on one page, and the deck has it: 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.

Antonio's Campaign DNA cheat sheet: eleven lines from Purpose to Judge
The Campaign DNA cheat sheet, from Antonio's deck. The full deck ships in the course pack.
WRITE IT
The system, once
Fill the sheet for one real project. This is the slow, human part.
RUN IT
One concept in many outputs
Ask for different executions from the same block and check they all pay off the concept.
JUDGE IT
You make the call
The three judge prompts thin the pile. You are the final judgment criteria.

The shelf

Tools and references

Tools that night

  • ChatGPT and Claude, run side by side in separate chats for clean comparisons
  • Antonio's one-page campaign-system cheat sheet (in the course pack)
  • Figma Make and the Figma connector, from Sydney's coded-design segment

Cases he mentioned

  • Nike, Just Do It: one concept, thirty years of executions
  • "If you have a body, you're an athlete": the idea underneath the concept
  • TikTok: where your copy competes with everything, not just competitors
CLASS 14 OF 24